Pasar al contenido principal

PROCESAMIENTO DE FLUJO DISTRIBUIDO EN SISTEMAS DE NIEBLA Y BORDE MEDIANTE COMPUTACION TRANSPRECISA

PCI2019-111850-2

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos Programación Conjunta Internacional
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 51
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

On-device training of machine learning models on microcontrollers with a look at federated learning

  • Monfort Grau, Marc
  • Pueyo Centelles, Roger|||0000-0002-3133-0657
  • Freitag, Fèlix|||0000-0001-5438-479X
Recent progress in machine learning frameworks makes it now possible to run an inference with sophisticated machine learning models on tiny microcontrollers. Model training, however, is typically done separately on powerful computers. There, the training process has abundant CPU and memory resources to process the stored datasets. In this work, we explore a different approach: training the model directly on the microcontroller. We implement this approach for a keyword spotting task. Then, we extend the training process using federated learning among microcontrollers. Our experiments with model training show an overall trend of decreasing loss with the increase of training epochs., This work was partially funded by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111850-2 (DiPET CHIST-ERA), PCI2019-111851-2 (LeadingEdge CHIST-ERA), and the Generalitat de Catalunya as Consolidated Research Group 2017- SGR-990., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Dataset for anomaly detection in a production wireless mesh community network

  • Cerdà Alabern, Llorenç|||0000-0002-2799-6173
  • Iuhasz, Gabriel
Wireless community networks, WCN, have proliferated around the world. Cheap off-the-shelf WiFi devices have enabled this new network paradigm where users build their own network infrastructure in a do-it-yourself alternative to traditional network operators. The fact that users are responsible for the administration of their own nodes makes the network very dynamic. There are frequent reboots of the networking devices, and users that join and leave the network. In addition, the unplanned deployment of the network makes it very heterogeneous, with both high and low capacity links. Therefore, anomaly detection in such dynamic scenario is challenging. In this paper we provide a dataset gathered from a production WCN. The data was obtained from a central server that collects data from the mesh nodes that build the network. In total, 63 different nodes were encountered during the data collection. The WCN is used daily to access the Internet from 17 subscribers of the local ISP available on the mesh. We have produced a dataset gathering a large set of features related not only to traffic, but other parameters such as CPU and memory. Furthermore, we provide the network topology of each sample in terms of the adjacency matrix, routing table and routing metrics. In the data we provide there is a known unprovoked gateway failure. Therefore, the dataset can be used to investigate the performance of unsupervised machine learning algorithms for fault detection in WCN. To our knowledge, this is the first dataset that allows fault detection to be investigated from a production WCN., This work has received funding through the DiPET CHIST-ERA under grant agreement PCI2019-111850-2; Spanish grant PID2019- 106774RB-C21; Romanian DIPET (62652/15.11.2019) project funded via PN 124/2020; and has been partially supported by the EU research project SERRANO (101017168) and hardware resources courtesy of the Romanian Ministry of Research and Innovation UEFISCDI COCO research project PN III-P4-ID-PCE-2020-0407., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Towards a monitoring system for a LoRa mesh network

  • Capella del Solar, Alejandro Jesús
  • Miquel Solé, Joan|||0000-0003-3737-376X
  • Freitag, Fèlix|||0000-0001-5438-479X
LoRa is a popular communication technology used in Internet of Things (IoT) applications. Typically, in the LoRaWAN architecture, an end node periodically sends a LoRaWAN message to a gateway connected to the Internet. Recent works, however, showed the possibility of LoRa mesh networks where LoRa nodes communicate with each other. In this paper we present a monitoring system as a tool for observing the traffic and the operation of such LoRa mesh networks. The client side is implemented at the LoRa nodes which periodically send to a server detailed information about the nodes' in-and outgoing LoRa packets. The server visualizes the information through a dashboard. Thus the monitoring tool allows network administrators to further analyze such LoRa mesh networks., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019- 111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Demo: An experimental environment based on mini-PCs for federated learning research

  • Freitag, Fèlix|||0000-0001-5438-479X
  • Vilchez Blanco, Pedro
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
  • Koutsopoulos, Iordanis
There is a growing research interest in Federated Learning (FL), a promising approach for data privacy preservation and proximity of training to the network edge, where data is generated. Resource consumption for Machine Learning (ML) training and inference is important for edge nodes, but most of the proposed protocols and algorithms for FL are evaluated by simulations. In this demo paper, we present an environment based on distributed mini-PCs to enable experimental study of FL protocols and algorithms. We have installed low-capacity mini-PCs within a wireless city-level mesh network and deployed container-based FL components on these nodes. We show the deployed FL clients and server at different nodes in the city and demonstrate how an FL experiment can be set and run in a real environment., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871582 — NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA). The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2150486 and #2006612). I Koutsopoulos acknowledges support from the CHIST-ERA grant CHIST-ERA-18-SDCDN-004 (GSRI grant number T11EPA4-00056)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Beyond the star of stars: An introduction to multihop and mesh for LoRa and LoRaWAN

  • Pueyo Centelles, Roger|||0000-0002-3133-0657
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Meseguer Pallarès, Roc|||0000-0002-9414-646X
  • Navarro Moldes, Leandro|||0000-0003-4775-5526
LoRa has emerged in recent years as a wireless technology providing long-range communication for low-power Internet-of-Things (IoT) devices. The LoRaWAN architecture adds the medium access control (MAC) and application layers, and defines a star of stars topology suitable for many and diverse IoT applications. However, in a number of scenarios, a more flexible network topology than LoRaWAN’s is needed. We review the state of the art of the design and implementation of multihop and mesh solutions for LoRa and LoRaWAN. We discuss the remaining challenges for multihop and mesh solutions to overcome in order to unlock the opportunities that decentralized, self-organizing, and infrastructure-less LoRa networks can bring to IoT applications., This work was in part supported by the Spanish Government under Contract PID2019-106774RB-C21, Contract PCI2019-111850-2 (DiPET CHIST-ERA), and Contract PCI2019-111851-2 (LeadingEdge CHIST-ERA), and in part by the Generalitat de Catalunya as Consolidated Research Group 2017-SGR-990., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

An IoT-based infrastructure to enhance self-evacuations in natural hazardous events

  • Finochietto, José Mariano
  • Micheletto, Matías
  • Eggly, Gabriel M.
  • Pueyo Centelles, Roger|||0000-0002-3133-0657
  • Santos, Rodrigo
  • Ochoa, Sergio F.
  • Meseguer Pallarès, Roc|||0000-0002-9414-646X
  • Orozco, Javier
Regardless of the extensive research conducted on large-scale evacuations, the instrumentation of these processes still represents an open issue for first response organizations. Self-evacuation of civilians that follows evacuation plans has shown to be feasible as early response to several natural disasters; however, the typical lack of interaction capability of the evacuees with first response organizations and emergency managers jeopardizes the effectiveness of these processes. This article proposes an IoT-based infrastructure that supports self-evacuation of civilians in mass processes, allowing people to participate as information providers and consumers. This infrastructure is the backbone of an ambient intelligence system used as a bridge between evacuees, first response units, and the emergency operation center managing the process. Depending on the people location and the status of the area, the system implements breadcrumbs that guide people to shelters and safe places. The proposed infrastructure includes (1) an architecture that captures the core design aspects of the solution and makes it reusable for other researchers, (2) an implementation of the system based on Raspberry Pi 3 devices with LoRa radio connectivity, (3) a mobile application that allows evacuees to interact with the evacuation system, and (4) a simplified algorithm to support the deployment of the IoT-based infrastructure into an urban area. The solution was evaluated using real measurements and simulations, and the obtained results are highly encouraging., This work was partially funded by the Spanish Government under contract PID2019-106774RB-C21, the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 and PCI2019-111851-2 and the Generalitat de Catalunya as Consolidated Research Group 2017-SGR-990., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

BePOCH: Improving federated learning performance in resource-constrained computing devices

  • Ibraimi, Lenart
  • Selimi, Mennan
  • Freitag, Fèlix|||0000-0001-5438-479X
Inference with trained machine learning models is now possible with small computing devices while only a few years ago it was run mostly in the cloud only. The recent technique of Federated Learning offers now a way to do also the training of the machine learning models on small devices by distributing the computing effort needed for the training over many distributed machines. But, the training on these low-capacity devices takes a long time and often consumes all the available CPU resource of the device. Therefore, for Federated Learning to be done by low-capacity devices in practical environments, the training process must not only target for the highest accuracy, but also on reducing the training time and the resource consumption. In this paper, we present an approach which uses a dynamic epoch parameter in the model training. We propose the BePOCH (Best Epoch) algorithm to identify what is the best number of epochs per training round in Federated Learning. We show in experiments with medical datasets how with the BePOCH suggested number of epochs, the training time and resource consumption decreases while keeping the level of accuracy. Thus, BePOCH makes machine learning model training on low-capacity devices more feasible and furthermore, decreases the overall resource consumption of the training process, which is an important asnect towards greener machine learning techniques., This work was partially funded by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111850- 2 (DiPET CHIST-ERA), PCI2019-111851-2 (LeadingEdge CHIST-ERA), and the Generalitat de Catalunya as Consolidated Research Group 2017-SGR-990. Suport was given also by the Agency for Electronic Communications (AEK) of North Macedonia., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Exploring blockchain-based management for LoRa IoT nodes

  • Cruz Harillo, Eloi
  • Freitag, Fèlix|||0000-0001-5438-479X
We consider open IoT applications in which the IoT devices, i.e. sensor nodes and gateways, can be contributed by volunteer participants. Since the contribution of sensor deployments and their data is critical for the value of such IoT applications, we propose to account for each participant her donation of both the measured data and the hardware, and translate this information into rewards to create incentives. The system architecture we propose uses a blockchain-based backend and aims to extend properties of the blockchain to the IoT sensor layer in order to achieve the trusted accounting of each contribution. A potential use case that can benefit from this concept are environmental monitoring applications that need to integrate IoT sensor nodes from third parties for increasing their geographic reach., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957228 — TruBlo and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

The effects of weight quantization on online federated learning for the IoT: a case study

  • Llisterri Giménez, Nil
  • Lee, Junkyu
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Vandierendonck, Hans
Many weight quantization approaches were explored to save the communication bandwidth between the clients and the server in federated learning using high-end computing machines. However, there is a lack of weight quantization research for online federated learning using TinyML devices which are restricted by the mini-batch size, the neural network size, and the communication method due to their severe hardware resource constraints and power budgets. We name Tiny Online Federated Learning (TinyOFL) for online federated learning using TinyML devices in the Internet of Things (IoT). This paper performs a comprehensive analysis of the effects of weight quantization in TinyOFL in terms of accuracy, stability, overfitting, communication efficiency, energy consumption, and delivery time, and extracts practical guidelines on how to apply the weight quantization to TinyOFL. Our analysis is supported by a TinyOFL case study with three Arduino Portenta H7 boards running federated learning clients for a keyword spotting task. Our findings include that in TinyOFL, a more aggressive weight quantization can be allowed than in online learning without FL, without affecting the accuracy thanks to TinyOFL’s quasi-batch training property. For example, using 7-bit weights achieved the equivalent accuracy to 32-bit floating point weights, while saving communication bandwidth by 4.6× . Overfitting by increasing network width rarely occurs in TinyOFL, but may occur if strong weight quantization is applied. The experiments also showed that there is a design space for TinyOFL applications by compensating for the accuracy loss due to weight quantization with an increase of the neural network size., This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Program (ASSIST-IoT) under Grant 957258, in part by the Spanish Government (DiPET CHIST-ERA) under Contract PID2019-106774RB-C21 and Contract PCI2019-111850-2, and in part by the Generalitat de Catalunya as Consolidated Research Group under Grant 2021-SGR-01059., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Poster: Testbed in wireless city mesh network with application to federated learning experiments

  • Freitag, Fèlix|||0000-0001-5438-479X
  • Vilchez Blanco, Pedro
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
The increase of the computing capacity of IoT devices and the appearance of lightweight machine learning frameworks have led to the situation that machine learning can nowadays be run in IoT applications at the network edge. There is an opportunity to implement machine learning algorithms with the more and more computationally powerful edge nodes and using the ever increasing amount of local data coming from nearby sensors. For this purpose, federated learning becomes a promising machine learning approach, where a machine learning model is trained by various nodes using their local data. For performing practical federated learning experiments, we have built a testbed deployed within a wireless city mesh network with geographically distributed low capacity devices. We describe the testbed implementation and show its potential to experimentally study federated learning protocols and algorithms in real edge environments., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871582 — NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RBC21, PCI2019-111850-2 (DiPET CHIST-ERA), PCI2019-111851-2 (LeadingEdge CHIST-ERA). The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2006612 and #2150486)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Anomaly detection for fault detection in wireless community networks using machine learning

  • Cerdà Alabern, Llorenç|||0000-0002-2799-6173
  • Iuhasz, Gabriel
  • Gemmi, Gabriele
Machine learning has received increasing attention in computer science in recent years and many types of methods have been proposed. In computer networks, little attention has been paid to the use of ML for fault detection, the main reason being the lack of datasets. This is motivated by the reluctance of network operators to share data about their infrastructure and network failures. In this paper, we attempt to fill this gap using anomaly detection techniques to discern hardware failure events in wireless community networks. For this purpose we use 4 unsupervised machine learning, ML, approaches based on different principles. We have built a dataset from a production wireless community network, gathering traffic and non-traffic features, e.g. CPU and memory. For the numerical analysis we investigated the ability of the different ML approaches to detect an unprovoked gateway failure that occurred during data collection. Our numerical results show that all the tested approaches improve to detect the gateway failure when non-traffic features are also considered. We see that, when properly tuned, all ML methods are effective to detect the failure. Nonetheless, using decision boundaries and other analysis techniques we observe significant different behavior among the ML methods., This work has received funding through the DiPET CHIST-ERA under grant agreement PCI2019-111850-2; Spanish grant PID2019-106774RB-C21; Romanian DIPET (62652/15.11.2019) project funded via PN 124/2020; and has been partially supported by the EU research project SERRANO (101017168) and hardware resources courtesy of the Romanian Ministry of Research and Innovation UEFISCDI COCO research project PN III-P4-ID-PCE-2020-0407., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

LoRaCoin: Towards a blockchain-based platform for managing LoRa devices

  • Cruz Harillo, Eloi
  • Freitag, Fèlix|||0000-0001-5438-479X
We propose LoRaCoin, a decentralized blockchainbased service to manage the generation and storage of sensor data generated by IoT devices. A novel feature of LoRaCoin is that it rewards both IoT devices that generate data and gateways that offer the Internet connectivity to the sensor nodes. With such double rewards, LoRaCoin aims to incentivize individuals to host sensor nodes and gateways and contribute to the growing need of the society for environmental monitoring applications., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019- 111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

On-device training of machine learning models on microcontrollers with federated learning

  • Llisterri Giménez, Nil
  • Monfort Grau, Marc
  • Pueyo Centelles, Roger|||0000-0002-3133-0657
  • Freitag, Fèlix|||0000-0001-5438-479X
Recent progress in machine learning frameworks has made it possible to now perform inference with models using cheap, tiny microcontrollers. Training of machine learning models for these tiny devices, however, is typically done separately on powerful computers. This way, the training process has abundant CPU and memory resources to process large stored datasets. In this work, we explore a different approach: training the machine learning model directly on the microcontroller and extending the training process with federated learning. We implement this approach for a keyword spotting task. We conduct experiments with real devices to characterize the learning behavior and resource consumption for different hyperparameters and federated learning configurations. We observed that in the case of training locally with fewer data, more frequent federated learning rounds more quickly reduced the training loss but involved a cost of higher bandwidth usage and longer training time. Our results indicate that, depending on the specific application, there is a need to determine the trade-off between the requirements and the resource usage of the system., This work has received funding from the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

A simheuristic algorithm for service placement in community networks

  • Panadero Martínez, Javier
  • Calvet Liñán, Laura
  • Bayliss, Christopher
  • Marques Puig, Joan Manuel
  • Selimi, Mennan
  • Freitag, Fèlix|||0000-0001-5438-479X
The growing demand for network connectivity has boosted the number of community networks (CNs). CNs are decentralized and self-organized communication networks owned and managed at the edge by volunteers. Due to the heterogeneity of edge node characteristics, high software and hardware diversity, irregular topology and unreliable behavior of the network, the performance of its services varie depending on where they are hosted. These characteristics of CNs and edge platforms running on them require of advanced simulation-optimization methods to place services. In this context, we propose a simheuristic algorithm to address this stochastic problem. The core of this approach relies on a multi-start metaheuristic with a multi-objective optimization method. Our approach combines Monte Carlo simulation and the multi-criteria optimal placement heuristic, The method is tested using real traces of Guifi.net CN, which is considered to be largest CN worldwide., This work has been partially supported by the Spanish Ministry of Science, Innovation and Universities under contract PGC2018-097599-B-100 and by the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 and PCI2019-111851-2., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Towards information-centric edge platform for mesh networks: The case of CityLab testbed

  • Selimi, Mennan
  • Navarro Moldes, Leandro|||0000-0003-4775-5526
  • Braem, Bart
  • Freitag, Fèlix|||0000-0001-5438-479X
By leveraging resources from the Fed4Fire+ City-Lab testbed, we design the PiGeon edge computing platform that experiments solution that enable ICN based edge services in wireless mesh networks (WMNs). PiGeon combines into a platform several trends in edge computing namely the ICN (Information-Centric Networking), the containerization of services exemplified by Docker, novel service placement algorithms and the increasing availability of energy efficient but still powerful hardware at user premises (Raspberry Pi, mini-PCs, and enhanced home gateways). We underpin the PiGeon platform with Docker container-based service that can be seamlessly delivered, cached and deployed at the network edge. The core of the PiGeon platform is the Decision Engine making a decision on where and when to deploy a service instance to satisfy the service requirements while considering the network status and available hardware resources. We collect network data from a real citywide mesh network such as CityLab FIRE testbed located at the city of Antwerp, Belgium. The collected data is used to feed our service placement heuristic within the PiGeon platform. Through a real deployment in CityLab testbed, we show that our service placement heuristic improves the response time up to 37% for stateful services (Web2.0 service). Apart from improving the QoS for end-users, our results show that ICN plays a key role in improving the service delivery time as well as reducing the traffic consumption in WMNs. The overall effect of ICN in our platform is that most content and service delivery requests can be satisfied very close to the client device, many times just one hop away, decoupling QoS from intra-network traffic and origin server load., This work was supported by the European H2020 framework programme project Fed4Fire+ (732638), by the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 and PCI2019-111851-2, and the Catalan government AGAUR SGR 990., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

REDEMON: Resilient Decentralized Monitoring system for edge Infrastructures

  • Pueyo Centelles, Roger|||0000-0002-3133-0657
  • Selimi, Mennan
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Navarro Moldes, Leandro|||0000-0003-4775-5526
The Guifi.net community network has evolved during the past 15 years into a telecommunications infrastructure that offers Internet access to more than 80.000 people. The monitoring system currently in place for this network is lagging behind the growth of the infrastructure, requiring manual intervention and counting several single points of failure. In this paper we present REDEMON, a resilient decentralized monitoring system, hosted on distributed and interconnected edge devices, for a reliable, eventually-consistent monitoring of the Guifi.net network, leveraging CRDT-based data structures implemented on AntidoteDB. We developed the REDEMON system as a prototype featuring resilience, decentralization and automation, in order to replace the legacy monitoring system. To assess the system, this prototype was deployed on resource-constraint edge nodes in the Guifi.net production network and evaluated under realistic conditions. The decentralized assignment mechanism successfully achieves setting the minimum number of monitoring servers per network device that satisfies the established system requirements. Besides, by concentrating the workload on the minimum required number of servers running at their maximum capacity, the remaining devices can idle away, reducing the consumption footprint of the system. With regard to computing resources, we measure a moderate CPU and RAM usage by the monitoring system on low-capacity devices, while we observe that a considerable network traffic is required for achieving a resilient and consistent data storage layer. This resilient and decentralized architecture could lay the basis for other edge applications in the cloud computing domain that need to coordinate over distributed and consistent shared data., This work was supported by the European H2020 framework programme project LightKone (H2020-732505), by the Spanish State Research Agency (AEI) under contracts PCI2019- 111850-2 and PCI2019-111851-2, and the Catalan government AGAUR SGR 990., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Embedded federated learning over a LoRa mesh network

  • Llisterri i Giménez, Nil|||0000-0003-1896-2868
  • Miquel Solé, Joan|||0000-0003-3737-376X
  • Freitag, Fèlix|||0000-0001-5438-479X
In on-device training of machine learning models on microcontrollers a neural network is trained on the device. A specific approach for collaborative on-device training is federated learning. In this paper, we propose embedded federated learning on microcontroller boards using the communication capacity of a LoRa mesh network. We apply a dual board design: The machine learning application that contains a neural network is trained for a keyword spotting task on the Arduino Portenta H7. For the networking of the federated learning process, the Portenta is connected to a TTGO LORA32 board that operates as a router within a LoRa mesh network. We experiment the federated learning application on the LoRa mesh network and analyze the network, system, and application level performance. The results from our experimentation suggest the feasibility of the proposed system and exemplify an implementation of a distributed application with re-trainable compute nodes, interconnected over LoRa, entirely deployed at the tiny edge., This work was supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Demonstration of a library prototype to build LoRa mesh networks for the IoT

  • Miquel Solé, Joan|||0000-0003-3737-376X
  • Miralles Nogués, Sergi
  • Pueyo Centelles, Roger|||0000-0002-3133-0657
  • Freitag, Fèlix|||0000-0001-5438-479X
LoRa has become popular in the Internet of Things (IoT) domain as a Low Power, Wide Area Network (LPWAN) radio technology providing low-power and long-range communication. In a typical IoT application, the LoRaWAN architecture is applied, where LoRa end nodes communicate their data to a gateway, which then over the Internet sends these data to a cloud-based service for further processing. However, LoRa can also be used standalone for the communication between LoRa nodes forming a mesh network. In this demo paper we present a library called LoRaMesher, which runs on LoRa nodes and forms a mesh network among these nodes. By implementing a distance vector routing protocol, LoRaMesher enables two nodes to communicate data packets with each other while the other nodes in the mesh network operate as routers. LoRaMesher can open the possibility for new distributed applications hosted only on such tiny IoT nodes., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019- 111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Designing a double LoRa connectivity for the Arduino Portenta H7

  • López Pino, Daniel
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Selimi, Mennan
Machine learning is moving to the smallest computing devices. Today machine learning is applied even in tiny IoT microcontroller boards. In the IoT, LoRa is a popular communication technology to connect remote devices with gateways. Still, the confluence of machine learning in microcontrollers and networked LoRa connectivity is not yet fully exploited. In this paper we design a new LoRa connectivity for the Arduino Portenta H7, a recent microcontroller board equipped with embedded sensors suitable for diverse machine learning tasks. With the solution that we found the Arduino Portenta H7 is able to become part of a LoRa mesh network. This capacity increases the Portenta's range of applications. For the vision of distributed machine learning at the tiny edge, we can add with the Portenta an important board to become a smart compute node within a LoRa mesh network., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Comparison of two microcontroller boards for on-device model training in a keyword spotting task

  • Llisterri i Giménez, Nil|||0000-0003-1896-2868
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Lee, JunKyu
  • Vandierendonck, Hans
Machine learning applications on resource-constrained devices such as microcontroller units often use models trained externally on more powerful devices. This approach, however, limits a later adaptation of the machine learning model in the device to changing data. Differently, on-device training allows the model to be updated for new datasets, but the training process needs to take into account the resource limitations of the device. This paper compares on-device training performance for a keyword spotting task using two popular microcontroller boards, Arduino Nano 33 BLE Sense and Arduino Portenta H7, in terms of inference accuracy, training latency, and current consumption. We use feedforward neural networks having a single hidden layer for models. The inference accuracy has been significantly improved using the Portenta H7 board by employing more neurons fitted to its memory budget, compared to the Nano board. With a neural network having 25 neurons for a hidden layer, the 5.0 x inference and 4.2 x training speedups are achieved using the Arduino Portenta H7 board, compared to the Arduino Nano 33 BLE Sense. While the memory of the Arduino Nano 33 BLE Sense is capable to train a neural network for the keyword spotting task, the Arduino Portenta H7 gives new possibilities for exploring more complex models for more complex problems thanks to a larger memory budget and adapting a model to new data in lower latency., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111850-2 (DiPET CHIST-ERA CHIST-ERA-SDCDN-002), PCI2019-111851-2 (LeadingEdge CHIST-ERA), and UK Engineering and Physical Sciences Research Council (EP/T022345/1)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Capítulo o parte de un libro (BookPart)

Server-side adaptive federated learning over wireless mesh network

  • Freitag, Fèlix|||0000-0001-5438-479X
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
  • Veiga, Luis
In federated learning, distributed nodes train a local machine learning model and exchange it through a central aggregator. In real environments, these training nodes are heterogeneous in computing capacity and bandwidth, thus their specific characteristics influence the performance of the federated learning process. We propose for such situations the design of a federated learning server that is able to adapt dynamically to the heterogeneity of the training nodes. In experiments with real devices deployed in a wireless mesh network, we observed that the designed adaptive federated learning server successfully exploited the idle times of the fast nodes by assigning them larger training workloads, which led to a higher global model performance without increasing the training time., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871582 — NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA), and by national funds through FCT, Fundação para a Ciência e a Tecnologia, Portugal, under project UIDB/50021/2020. The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2006612 and #2150486)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Implementation of a LoRa Mesh library

  • Miquel Solé, Joan|||0000-0003-3737-376X
  • Pueyo Centelles, Roger|||0000-0002-3133-0657
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Meseguer Pallarès, Roc|||0000-0002-9414-646X
LoRa is a popular communication technology in the Internet of Things (IoT) domain, providing low-power and long-range communications. Most LoRa IoT applications use the LoRaWAN architecture, which builds a star topology between LoRa end nodes and the gateway they connect to. However, LoRa can also be used for the communication between end nodes themselves, forming a mesh network topology. In this paper, we present a library that allows to integrate LoRa end nodes into a LoRa mesh network, in which a routing protocol is used. Thus, an IoT application running on these nodes can use the library to send and receive data packets to and from other nodes in the LoRa mesh network. The designed routing protocol is proactive, and maintains the routing table at each node updated by sending routing messages between neighboring nodes. The implemented library has been tested on embedded boards featuring an ESP32 microcontroller and a LoRa single-channel radio. By using our LoRa mesh library, nodes do not need to connect to a LoRaWAN gateway, but among themselves. This opens the possibility for new, distributed applications solely built upon tiny IoT nodes., This work was supported by the Ministry of Science and Innovation of the Spanish Government through the State Research Agency (AEI) under Project PID2019-106774RB-C21, Project PCI2019-111851-2 (LeadingEdge CHIST-ERA), and Project PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Capítulo o parte de un libro (BookPart)

Performance evaluation of federated learning over wireless mesh Networks with low-capacity devices

  • Freitag, Fèlix|||0000-0001-5438-479X
  • Vilchez Blanco, Pedro
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
Federated learning is a distributed learning technique in which a machine learning model is trained collaboratively among several nodes. While the privacy preservation of the training data is one of the important promises of federated learning, there is also an opportunity to use low capacity devices for machine learning model training by taking advantage of the fact that the training effort is divided among many nodes. In this paper, we conduct experiments with a federated learning network deployed on several low capacity devices connected to a wireless mesh network. The measurements show the hardware capacity and link bandwidth of the clients on the federated learning process. The results suggest that for heterogeneous networks the federated learning clients should be extended with more autonomous decision capacities according to the network and local conditions., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 871582 - NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA). The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2006612 and #2150486)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Stateful adaptive streams with approximate computing and elastic scaling

  • Francisco, João
  • Coimbra, Miguel E.
  • Neto, Pedro F.
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Veiga, Luis
The model of approximate computing can be used to increase performance or optimize resource usage in stream and graph processing. It can be used to satisfy performance requirements (e.g., throughput, lag) in stream processing by reducing the effort that applications need to process datasets. There are currently multiple stream processing platforms, and most of them do not natively support approximate results. A recent one, Stateful Functions, is an API that uses Flink to enable developers to easily build stream and graph processing applications. It also retains Flink's features like stateful computations, fault-tolerance, scalability, control events and its graph processing library Gelly. Herein we present Approxate, an extension over this platform to support approximate results. It can also support more efficient stream and graph processing by allocating available resources adaptively, driven by user-defined requirements on throughput, lag, and latency. This extension enables flexibility in computational trade-offs such as trading accuracy for performance. The user can choose which metrics should be guaranteed at the cost of others, and/or the accuracy. Approxate incorporates approximate computing (using load shedding) with adaptive accuracy and resource manegement in state-of-the-art stream processing platforms, which are not targeted in other relevant related work. It does not require significant modifications to application code, and minimizes imbalance in data source representation when dropping events., This work was supported by national funds through FCT, Fundação para a Ciência e a Tecnologia, under project UIDB/50021/2020. DL 60/2018, de 3-08 – Aquisição necessária para a atividade de I&D do INESC-ID, no âmbito do projeto SmartRetail (02/C-05i01/2022). This work was partially supported by the Spanish Government under research contracts PID2019-106774RB-C21 and PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

A two-stage multi-criteria optimization method for service placement in decentralized edge micro-clouds

  • Panadero, Javier
  • Selimi, Mennan
  • Calvet Liñán, Laura
  • Marques Puig, Joan Manuel
  • Freitag, Fèlix|||0000-0001-5438-479X
Community networks are becoming increasingly popular due to the growing demand for network connectivity in both rural and urban areas. Community networks are owned and managed at the edge by volunteers. Their irregular topology, the heterogeneity of resources and their unreliable behavior claim for advanced optimization methods to place services in the network. In particular, an efficient service placement method is key for the performance of these systems. This work presents the Multi-Criteria Optimal Placement method, a novel and fast two-stage multi-objective method to place services in decentralized community network edge micro-clouds. A comprehensive set of computational experiments is carried out using real traces of Guifi.net, which is the largest production community network worldwide. According to the results, the proposed method outperforms both the random placement method used currently in Guifi.net and the Bandwidth-aware Service Placement method, which provides the best known solutions in the literature, by a mean gap in bandwidth gain of about 53% and 10%, respectively, while it also reduces the number of resources used., This work has been partially supported by the Spanish Ministry of Science, Innovation and Universities (PGC2018-097599-B-100 and PID2019-106774RB-C21), and by the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 (DiPET CHIST-ERA) and PCI2019-111851-2 (LeadingEdge CHIST-ERA)., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

An IoT-based infrastructure to enhance self-evacuations in natural hazardous events

  • Finochietto, José Mariano
  • Micheletto, Matías
  • Eggly, Gabriel M.
  • Pueyo Centelles, Roger
  • Santos, Rodrigo
  • Ochoa, Sergio F.
  • Meseguer Pallarès, Roc
  • Orozco, Javier
Regardless of the extensive research conducted on large-scale evacuations, the instrumentation of these processes still represents an open issue for first response organizations. Self-evacuation of civilians that follows evacuation plans has shown to be feasible as early response to several natural disasters; however, the typical lack of interaction capability of the evacuees with first response organizations and emergency managers jeopardizes the effectiveness of these processes. This article proposes an IoT-based infrastructure that supports self-evacuation of civilians in mass processes, allowing people to participate as information providers and consumers. This infrastructure is the backbone of an ambient intelligence system used as a bridge between evacuees, first response units, and the emergency operation center managing the process. Depending on the people location and the status of the area, the system implements breadcrumbs that guide people to shelters and safe places. The proposed infrastructure includes (1) an architecture that captures the core design aspects of the solution and makes it reusable for other researchers, (2) an implementation of the system based on Raspberry Pi 3 devices with LoRa radio connectivity, (3) a mobile application that allows evacuees to interact with the evacuation system, and (4) a simplified algorithm to support the deployment of the IoT-based infrastructure into an urban area. The solution was evaluated using real measurements and simulations, and the obtained results are highly encouraging., This work was partially funded by the Spanish Government under contract PID2019-106774RB-C21, the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 and PCI2019-111851-2 and the Generalitat de Catalunya as Consolidated Research Group 2017-SGR-990., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Anomaly detection for fault detection in wireless community networks using machine learning

  • Cerdà Alabern, Llorenç
  • Iuhasz, Gabriel
  • Gemmi, Gabriele
Machine learning has received increasing attention in computer science in recent years and many types of methods have been proposed. In computer networks, little attention has been paid to the use of ML for fault detection, the main reason being the lack of datasets. This is motivated by the reluctance of network operators to share data about their infrastructure and network failures. In this paper, we attempt to fill this gap using anomaly detection techniques to discern hardware failure events in wireless community networks. For this purpose we use 4 unsupervised machine learning, ML, approaches based on different principles. We have built a dataset from a production wireless community network, gathering traffic and non-traffic features, e.g. CPU and memory. For the numerical analysis we investigated the ability of the different ML approaches to detect an unprovoked gateway failure that occurred during data collection. Our numerical results show that all the tested approaches improve to detect the gateway failure when non-traffic features are also considered. We see that, when properly tuned, all ML methods are effective to detect the failure. Nonetheless, using decision boundaries and other analysis techniques we observe significant different behavior among the ML methods., This work has received funding through the DiPET CHIST-ERA under grant agreement PCI2019-111850-2; Spanish grant PID2019-106774RB-C21; Romanian DIPET (62652/15.11.2019) project funded via PN 124/2020; and has been partially supported by the EU research project SERRANO (101017168) and hardware resources courtesy of the Romanian Ministry of Research and Innovation UEFISCDI COCO research project PN III-P4-ID-PCE-2020-0407., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Demonstration of a library prototype to build LoRa mesh networks for the IoT

  • Miquel Solé, Joan
  • Miralles Nogués, Sergi
  • Pueyo Centelles, Roger
  • Freitag, Fèlix
LoRa has become popular in the Internet of Things (IoT) domain as a Low Power, Wide Area Network (LPWAN) radio technology providing low-power and long-range communication. In a typical IoT application, the LoRaWAN architecture is applied, where LoRa end nodes communicate their data to a gateway, which then over the Internet sends these data to a cloud-based service for further processing. However, LoRa can also be used standalone for the communication between LoRa nodes forming a mesh network. In this demo paper we present a library called LoRaMesher, which runs on LoRa nodes and forms a mesh network among these nodes. By implementing a distance vector routing protocol, LoRaMesher enables two nodes to communicate data packets with each other while the other nodes in the mesh network operate as routers. LoRaMesher can open the possibility for new distributed applications hosted only on such tiny IoT nodes., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019- 111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación

Server-side adaptive federated learning over wireless mesh network

  • Freitag, Fèlix
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
  • Veiga, Luis
In federated learning, distributed nodes train a local machine learning model and exchange it through a central aggregator. In real environments, these training nodes are heterogeneous in computing capacity and bandwidth, thus their specific characteristics influence the performance of the federated learning process. We propose for such situations the design of a federated learning server that is able to adapt dynamically to the heterogeneity of the training nodes. In experiments with real devices deployed in a wireless mesh network, we observed that the designed adaptive federated learning server successfully exploited the idle times of the fast nodes by assigning them larger training workloads, which led to a higher global model performance without increasing the training time., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871582 — NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA), and by national funds through FCT, Fundação para a Ciência e a Tecnologia, Portugal, under project UIDB/50021/2020. The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2006612 and #2150486)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

The effects of weight quantization on online federated learning for the IoT: a case study

  • Llisterri Giménez, Nil
  • Lee, Junkyu
  • Freitag, Fèlix
  • Vandierendonck, Hans
Many weight quantization approaches were explored to save the communication bandwidth between the clients and the server in federated learning using high-end computing machines. However, there is a lack of weight quantization research for online federated learning using TinyML devices which are restricted by the mini-batch size, the neural network size, and the communication method due to their severe hardware resource constraints and power budgets. We name Tiny Online Federated Learning (TinyOFL) for online federated learning using TinyML devices in the Internet of Things (IoT). This paper performs a comprehensive analysis of the effects of weight quantization in TinyOFL in terms of accuracy, stability, overfitting, communication efficiency, energy consumption, and delivery time, and extracts practical guidelines on how to apply the weight quantization to TinyOFL. Our analysis is supported by a TinyOFL case study with three Arduino Portenta H7 boards running federated learning clients for a keyword spotting task. Our findings include that in TinyOFL, a more aggressive weight quantization can be allowed than in online learning without FL, without affecting the accuracy thanks to TinyOFL’s quasi-batch training property. For example, using 7-bit weights achieved the equivalent accuracy to 32-bit floating point weights, while saving communication bandwidth by 4.6× . Overfitting by increasing network width rarely occurs in TinyOFL, but may occur if strong weight quantization is applied. The experiments also showed that there is a design space for TinyOFL applications by compensating for the accuracy loss due to weight quantization with an increase of the neural network size., This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Program (ASSIST-IoT) under Grant 957258, in part by the Spanish Government (DiPET CHIST-ERA) under Contract PID2019-106774RB-C21 and Contract PCI2019-111850-2, and in part by the Generalitat de Catalunya as Consolidated Research Group under Grant 2021-SGR-01059., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Stateful adaptive streams with approximate computing and elastic scaling

  • Francisco, João
  • Coimbra, Miguel E.
  • Neto, Pedro F.
  • Freitag, Fèlix
  • Veiga, Luis
The model of approximate computing can be used to increase performance or optimize resource usage in stream and graph processing. It can be used to satisfy performance requirements (e.g., throughput, lag) in stream processing by reducing the effort that applications need to process datasets. There are currently multiple stream processing platforms, and most of them do not natively support approximate results. A recent one, Stateful Functions, is an API that uses Flink to enable developers to easily build stream and graph processing applications. It also retains Flink's features like stateful computations, fault-tolerance, scalability, control events and its graph processing library Gelly. Herein we present Approxate, an extension over this platform to support approximate results. It can also support more efficient stream and graph processing by allocating available resources adaptively, driven by user-defined requirements on throughput, lag, and latency. This extension enables flexibility in computational trade-offs such as trading accuracy for performance. The user can choose which metrics should be guaranteed at the cost of others, and/or the accuracy. Approxate incorporates approximate computing (using load shedding) with adaptive accuracy and resource manegement in state-of-the-art stream processing platforms, which are not targeted in other relevant related work. It does not require significant modifications to application code, and minimizes imbalance in data source representation when dropping events., This work was supported by national funds through FCT, Fundação para a Ciência e a Tecnologia, under project UIDB/50021/2020. DL 60/2018, de 3-08 – Aquisição necessária para a atividade de I&D do INESC-ID, no âmbito do projeto SmartRetail (02/C-05i01/2022). This work was partially supported by the Spanish Government under research contracts PID2019-106774RB-C21 and PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Poster: Testbed in wireless city mesh network with application to federated learning experiments

  • Freitag, Fèlix
  • Vilchez Blanco, Pedro
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
The increase of the computing capacity of IoT devices and the appearance of lightweight machine learning frameworks have led to the situation that machine learning can nowadays be run in IoT applications at the network edge. There is an opportunity to implement machine learning algorithms with the more and more computationally powerful edge nodes and using the ever increasing amount of local data coming from nearby sensors. For this purpose, federated learning becomes a promising machine learning approach, where a machine learning model is trained by various nodes using their local data. For performing practical federated learning experiments, we have built a testbed deployed within a wireless city mesh network with geographically distributed low capacity devices. We describe the testbed implementation and show its potential to experimentally study federated learning protocols and algorithms in real edge environments., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871582 — NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RBC21, PCI2019-111850-2 (DiPET CHIST-ERA), PCI2019-111851-2 (LeadingEdge CHIST-ERA). The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2006612 and #2150486)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A simheuristic algorithm for service placement in community networks

  • Panadero Martínez, Javier
  • Calvet Liñán, Laura
  • Bayliss, Christopher
  • Marques Puig, Joan Manuel
  • Selimi, Mennan
  • Freitag, Fèlix
The growing demand for network connectivity has boosted the number of community networks (CNs). CNs are decentralized and self-organized communication networks owned and managed at the edge by volunteers. Due to the heterogeneity of edge node characteristics, high software and hardware diversity, irregular topology and unreliable behavior of the network, the performance of its services varie depending on where they are hosted. These characteristics of CNs and edge platforms running on them require of advanced simulation-optimization methods to place services. In this context, we propose a simheuristic algorithm to address this stochastic problem. The core of this approach relies on a multi-start metaheuristic with a multi-objective optimization method. Our approach combines Monte Carlo simulation and the multi-criteria optimal placement heuristic, The method is tested using real traces of Guifi.net CN, which is considered to be largest CN worldwide., This work has been partially supported by the Spanish Ministry of Science, Innovation and Universities under contract PGC2018-097599-B-100 and by the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 and PCI2019-111851-2., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

On-device training of machine learning models on microcontrollers with federated learning

  • Llisterri Giménez, Nil
  • Monfort Grau, Marc
  • Pueyo Centelles, Roger
  • Freitag, Fèlix
Recent progress in machine learning frameworks has made it possible to now perform inference with models using cheap, tiny microcontrollers. Training of machine learning models for these tiny devices, however, is typically done separately on powerful computers. This way, the training process has abundant CPU and memory resources to process large stored datasets. In this work, we explore a different approach: training the machine learning model directly on the microcontroller and extending the training process with federated learning. We implement this approach for a keyword spotting task. We conduct experiments with real devices to characterize the learning behavior and resource consumption for different hyperparameters and federated learning configurations. We observed that in the case of training locally with fewer data, more frequent federated learning rounds more quickly reduced the training loss but involved a cost of higher bandwidth usage and longer training time. Our results indicate that, depending on the specific application, there is a need to determine the trade-off between the requirements and the resource usage of the system., This work has received funding from the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Designing a double LoRa connectivity for the Arduino Portenta H7

  • López Pino, Daniel
  • Freitag, Fèlix
  • Selimi, Mennan
Machine learning is moving to the smallest computing devices. Today machine learning is applied even in tiny IoT microcontroller boards. In the IoT, LoRa is a popular communication technology to connect remote devices with gateways. Still, the confluence of machine learning in microcontrollers and networked LoRa connectivity is not yet fully exploited. In this paper we design a new LoRa connectivity for the Arduino Portenta H7, a recent microcontroller board equipped with embedded sensors suitable for diverse machine learning tasks. With the solution that we found the Arduino Portenta H7 is able to become part of a LoRa mesh network. This capacity increases the Portenta's range of applications. For the vision of distributed machine learning at the tiny edge, we can add with the Portenta an important board to become a smart compute node within a LoRa mesh network., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Dataset for anomaly detection in a production wireless mesh community network

  • Cerdà Alabern, Llorenç
  • Iuhasz, Gabriel
Wireless community networks, WCN, have proliferated around the world. Cheap off-the-shelf WiFi devices have enabled this new network paradigm where users build their own network infrastructure in a do-it-yourself alternative to traditional network operators. The fact that users are responsible for the administration of their own nodes makes the network very dynamic. There are frequent reboots of the networking devices, and users that join and leave the network. In addition, the unplanned deployment of the network makes it very heterogeneous, with both high and low capacity links. Therefore, anomaly detection in such dynamic scenario is challenging. In this paper we provide a dataset gathered from a production WCN. The data was obtained from a central server that collects data from the mesh nodes that build the network. In total, 63 different nodes were encountered during the data collection. The WCN is used daily to access the Internet from 17 subscribers of the local ISP available on the mesh. We have produced a dataset gathering a large set of features related not only to traffic, but other parameters such as CPU and memory. Furthermore, we provide the network topology of each sample in terms of the adjacency matrix, routing table and routing metrics. In the data we provide there is a known unprovoked gateway failure. Therefore, the dataset can be used to investigate the performance of unsupervised machine learning algorithms for fault detection in WCN. To our knowledge, this is the first dataset that allows fault detection to be investigated from a production WCN., This work has received funding through the DiPET CHIST-ERA under grant agreement PCI2019-111850-2; Spanish grant PID2019- 106774RB-C21; Romanian DIPET (62652/15.11.2019) project funded via PN 124/2020; and has been partially supported by the EU research project SERRANO (101017168) and hardware resources courtesy of the Romanian Ministry of Research and Innovation UEFISCDI COCO research project PN III-P4-ID-PCE-2020-0407., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

LoRaCoin: Towards a blockchain-based platform for managing LoRa devices

  • Cruz Harillo, Eloi
  • Freitag, Fèlix
We propose LoRaCoin, a decentralized blockchainbased service to manage the generation and storage of sensor data generated by IoT devices. A novel feature of LoRaCoin is that it rewards both IoT devices that generate data and gateways that offer the Internet connectivity to the sensor nodes. With such double rewards, LoRaCoin aims to incentivize individuals to host sensor nodes and gateways and contribute to the growing need of the society for environmental monitoring applications., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019- 111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Demo: An experimental environment based on mini-PCs for federated learning research

  • Freitag, Fèlix
  • Vilchez Blanco, Pedro
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
  • Koutsopoulos, Iordanis
There is a growing research interest in Federated Learning (FL), a promising approach for data privacy preservation and proximity of training to the network edge, where data is generated. Resource consumption for Machine Learning (ML) training and inference is important for edge nodes, but most of the proposed protocols and algorithms for FL are evaluated by simulations. In this demo paper, we present an environment based on distributed mini-PCs to enable experimental study of FL protocols and algorithms. We have installed low-capacity mini-PCs within a wireless city-level mesh network and deployed container-based FL components on these nodes. We show the deployed FL clients and server at different nodes in the city and demonstrate how an FL experiment can be set and run in a real environment., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871582 — NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA). The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2150486 and #2006612). I Koutsopoulos acknowledges support from the CHIST-ERA grant CHIST-ERA-18-SDCDN-004 (GSRI grant number T11EPA4-00056)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Towards a monitoring system for a LoRa mesh network

  • Capella del Solar, Alejandro Jesús
  • Miquel Solé, Joan
  • Freitag, Fèlix
LoRa is a popular communication technology used in Internet of Things (IoT) applications. Typically, in the LoRaWAN architecture, an end node periodically sends a LoRaWAN message to a gateway connected to the Internet. Recent works, however, showed the possibility of LoRa mesh networks where LoRa nodes communicate with each other. In this paper we present a monitoring system as a tool for observing the traffic and the operation of such LoRa mesh networks. The client side is implemented at the LoRa nodes which periodically send to a server detailed information about the nodes' in-and outgoing LoRa packets. The server visualizes the information through a dashboard. Thus the monitoring tool allows network administrators to further analyze such LoRa mesh networks., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019- 111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Exploring blockchain-based management for LoRa IoT nodes

  • Cruz Harillo, Eloi
  • Freitag, Fèlix
We consider open IoT applications in which the IoT devices, i.e. sensor nodes and gateways, can be contributed by volunteer participants. Since the contribution of sensor deployments and their data is critical for the value of such IoT applications, we propose to account for each participant her donation of both the measured data and the hardware, and translate this information into rewards to create incentives. The system architecture we propose uses a blockchain-based backend and aims to extend properties of the blockchain to the IoT sensor layer in order to achieve the trusted accounting of each contribution. A potential use case that can benefit from this concept are environmental monitoring applications that need to integrate IoT sensor nodes from third parties for increasing their geographic reach., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 957228 — TruBlo and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

On-device training of machine learning models on microcontrollers with a look at federated learning

  • Monfort Grau, Marc
  • Pueyo Centelles, Roger
  • Freitag, Fèlix
Recent progress in machine learning frameworks makes it now possible to run an inference with sophisticated machine learning models on tiny microcontrollers. Model training, however, is typically done separately on powerful computers. There, the training process has abundant CPU and memory resources to process the stored datasets. In this work, we explore a different approach: training the model directly on the microcontroller. We implement this approach for a keyword spotting task. Then, we extend the training process using federated learning among microcontrollers. Our experiments with model training show an overall trend of decreasing loss with the increase of training epochs., This work was partially funded by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111850-2 (DiPET CHIST-ERA), PCI2019-111851-2 (LeadingEdge CHIST-ERA), and the Generalitat de Catalunya as Consolidated Research Group 2017- SGR-990., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

BePOCH: Improving federated learning performance in resource-constrained computing devices

  • Ibraimi, Lenart
  • Selimi, Mennan
  • Freitag, Fèlix
Inference with trained machine learning models is now possible with small computing devices while only a few years ago it was run mostly in the cloud only. The recent technique of Federated Learning offers now a way to do also the training of the machine learning models on small devices by distributing the computing effort needed for the training over many distributed machines. But, the training on these low-capacity devices takes a long time and often consumes all the available CPU resource of the device. Therefore, for Federated Learning to be done by low-capacity devices in practical environments, the training process must not only target for the highest accuracy, but also on reducing the training time and the resource consumption. In this paper, we present an approach which uses a dynamic epoch parameter in the model training. We propose the BePOCH (Best Epoch) algorithm to identify what is the best number of epochs per training round in Federated Learning. We show in experiments with medical datasets how with the BePOCH suggested number of epochs, the training time and resource consumption decreases while keeping the level of accuracy. Thus, BePOCH makes machine learning model training on low-capacity devices more feasible and furthermore, decreases the overall resource consumption of the training process, which is an important asnect towards greener machine learning techniques., This work was partially funded by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111850- 2 (DiPET CHIST-ERA), PCI2019-111851-2 (LeadingEdge CHIST-ERA), and the Generalitat de Catalunya as Consolidated Research Group 2017-SGR-990. Suport was given also by the Agency for Electronic Communications (AEK) of North Macedonia., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Implementation of a LoRa Mesh library

  • Miquel Solé, Joan
  • Pueyo Centelles, Roger
  • Freitag, Fèlix
  • Meseguer Pallarès, Roc
LoRa is a popular communication technology in the Internet of Things (IoT) domain, providing low-power and long-range communications. Most LoRa IoT applications use the LoRaWAN architecture, which builds a star topology between LoRa end nodes and the gateway they connect to. However, LoRa can also be used for the communication between end nodes themselves, forming a mesh network topology. In this paper, we present a library that allows to integrate LoRa end nodes into a LoRa mesh network, in which a routing protocol is used. Thus, an IoT application running on these nodes can use the library to send and receive data packets to and from other nodes in the LoRa mesh network. The designed routing protocol is proactive, and maintains the routing table at each node updated by sending routing messages between neighboring nodes. The implemented library has been tested on embedded boards featuring an ESP32 microcontroller and a LoRa single-channel radio. By using our LoRa mesh library, nodes do not need to connect to a LoRaWAN gateway, but among themselves. This opens the possibility for new, distributed applications solely built upon tiny IoT nodes., This work was supported by the Ministry of Science and Innovation of the Spanish Government through the State Research Agency (AEI) under Project PID2019-106774RB-C21, Project PCI2019-111851-2 (LeadingEdge CHIST-ERA), and Project PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Embedded federated learning over a LoRa mesh network

  • Llisterri i Giménez, Nil
  • Miquel Solé, Joan
  • Freitag, Fèlix
In on-device training of machine learning models on microcontrollers a neural network is trained on the device. A specific approach for collaborative on-device training is federated learning. In this paper, we propose embedded federated learning on microcontroller boards using the communication capacity of a LoRa mesh network. We apply a dual board design: The machine learning application that contains a neural network is trained for a keyword spotting task on the Arduino Portenta H7. For the networking of the federated learning process, the Portenta is connected to a TTGO LORA32 board that operates as a router within a LoRa mesh network. We experiment the federated learning application on the LoRa mesh network and analyze the network, system, and application level performance. The results from our experimentation suggest the feasibility of the proposed system and exemplify an implementation of a distributed application with re-trainable compute nodes, interconnected over LoRa, entirely deployed at the tiny edge., This work was supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Comparison of two microcontroller boards for on-device model training in a keyword spotting task

  • Llisterri i Giménez, Nil
  • Freitag, Fèlix
  • Lee, JunKyu
  • Vandierendonck, Hans
Machine learning applications on resource-constrained devices such as microcontroller units often use models trained externally on more powerful devices. This approach, however, limits a later adaptation of the machine learning model in the device to changing data. Differently, on-device training allows the model to be updated for new datasets, but the training process needs to take into account the resource limitations of the device. This paper compares on-device training performance for a keyword spotting task using two popular microcontroller boards, Arduino Nano 33 BLE Sense and Arduino Portenta H7, in terms of inference accuracy, training latency, and current consumption. We use feedforward neural networks having a single hidden layer for models. The inference accuracy has been significantly improved using the Portenta H7 board by employing more neurons fitted to its memory budget, compared to the Nano board. With a neural network having 25 neurons for a hidden layer, the 5.0 x inference and 4.2 x training speedups are achieved using the Arduino Portenta H7 board, compared to the Arduino Nano 33 BLE Sense. While the memory of the Arduino Nano 33 BLE Sense is capable to train a neural network for the keyword spotting task, the Arduino Portenta H7 gives new possibilities for exploring more complex models for more complex problems thanks to a larger memory budget and adapting a model to new data in lower latency., This work was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111850-2 (DiPET CHIST-ERA CHIST-ERA-SDCDN-002), PCI2019-111851-2 (LeadingEdge CHIST-ERA), and UK Engineering and Physical Sciences Research Council (EP/T022345/1)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Beyond the star of stars: An introduction to multihop and mesh for LoRa and LoRaWAN

  • Pueyo Centelles, Roger
  • Freitag, Fèlix
  • Meseguer Pallarès, Roc
  • Navarro Moldes, Leandro
LoRa has emerged in recent years as a wireless technology providing long-range communication for low-power Internet-of-Things (IoT) devices. The LoRaWAN architecture adds the medium access control (MAC) and application layers, and defines a star of stars topology suitable for many and diverse IoT applications. However, in a number of scenarios, a more flexible network topology than LoRaWAN’s is needed. We review the state of the art of the design and implementation of multihop and mesh solutions for LoRa and LoRaWAN. We discuss the remaining challenges for multihop and mesh solutions to overcome in order to unlock the opportunities that decentralized, self-organizing, and infrastructure-less LoRa networks can bring to IoT applications., This work was in part supported by the Spanish Government under Contract PID2019-106774RB-C21, Contract PCI2019-111850-2 (DiPET CHIST-ERA), and Contract PCI2019-111851-2 (LeadingEdge CHIST-ERA), and in part by the Generalitat de Catalunya as Consolidated Research Group 2017-SGR-990., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

REDEMON: Resilient Decentralized Monitoring system for edge Infrastructures

  • Pueyo Centelles, Roger
  • Selimi, Mennan
  • Freitag, Fèlix
  • Navarro Moldes, Leandro
The Guifi.net community network has evolved during the past 15 years into a telecommunications infrastructure that offers Internet access to more than 80.000 people. The monitoring system currently in place for this network is lagging behind the growth of the infrastructure, requiring manual intervention and counting several single points of failure. In this paper we present REDEMON, a resilient decentralized monitoring system, hosted on distributed and interconnected edge devices, for a reliable, eventually-consistent monitoring of the Guifi.net network, leveraging CRDT-based data structures implemented on AntidoteDB. We developed the REDEMON system as a prototype featuring resilience, decentralization and automation, in order to replace the legacy monitoring system. To assess the system, this prototype was deployed on resource-constraint edge nodes in the Guifi.net production network and evaluated under realistic conditions. The decentralized assignment mechanism successfully achieves setting the minimum number of monitoring servers per network device that satisfies the established system requirements. Besides, by concentrating the workload on the minimum required number of servers running at their maximum capacity, the remaining devices can idle away, reducing the consumption footprint of the system. With regard to computing resources, we measure a moderate CPU and RAM usage by the monitoring system on low-capacity devices, while we observe that a considerable network traffic is required for achieving a resilient and consistent data storage layer. This resilient and decentralized architecture could lay the basis for other edge applications in the cloud computing domain that need to coordinate over distributed and consistent shared data., This work was supported by the European H2020 framework programme project LightKone (H2020-732505), by the Spanish State Research Agency (AEI) under contracts PCI2019- 111850-2 and PCI2019-111851-2, and the Catalan government AGAUR SGR 990., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A two-stage multi-criteria optimization method for service placement in decentralized edge micro-clouds

  • Panadero, Javier
  • Selimi, Mennan
  • Calvet Liñán, Laura
  • Marques Puig, Joan Manuel
  • Freitag, Fèlix
Community networks are becoming increasingly popular due to the growing demand for network connectivity in both rural and urban areas. Community networks are owned and managed at the edge by volunteers. Their irregular topology, the heterogeneity of resources and their unreliable behavior claim for advanced optimization methods to place services in the network. In particular, an efficient service placement method is key for the performance of these systems. This work presents the Multi-Criteria Optimal Placement method, a novel and fast two-stage multi-objective method to place services in decentralized community network edge micro-clouds. A comprehensive set of computational experiments is carried out using real traces of Guifi.net, which is the largest production community network worldwide. According to the results, the proposed method outperforms both the random placement method used currently in Guifi.net and the Bandwidth-aware Service Placement method, which provides the best known solutions in the literature, by a mean gap in bandwidth gain of about 53% and 10%, respectively, while it also reduces the number of resources used., This work has been partially supported by the Spanish Ministry of Science, Innovation and Universities (PGC2018-097599-B-100 and PID2019-106774RB-C21), and by the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 (DiPET CHIST-ERA) and PCI2019-111851-2 (LeadingEdge CHIST-ERA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación

Performance evaluation of federated learning over wireless mesh Networks with low-capacity devices

  • Freitag, Fèlix
  • Vilchez Blanco, Pedro
  • Wei, Lu
  • Liu, Chun-Hung
  • Selimi, Mennan
Federated learning is a distributed learning technique in which a machine learning model is trained collaboratively among several nodes. While the privacy preservation of the training data is one of the important promises of federated learning, there is also an opportunity to use low capacity devices for machine learning model training by taking advantage of the fact that the training effort is divided among many nodes. In this paper, we conduct experiments with a federated learning network deployed on several low capacity devices connected to a wireless mesh network. The measurements show the hardware capacity and link bandwidth of the clients on the federated learning process. The results suggest that for heterogeneous networks the federated learning clients should be extended with more autonomous decision capacities according to the network and local conditions., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 871582 - NGIatlantic.eu and was partially supported by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111851-2 (LeadingEdge CHIST-ERA), PCI2019-111850-2 (DiPET CHIST-ERA). The work of C.-H. Liu was supported in part by the U.S. National Science Foundation (NSF) under Award CNS-2006453 and in part by Mississippi State University under Grant ORED 253551-060702. The work of L. Wei is supported in part by the U.S. National Science Foundation (#2006612 and #2150486)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Towards information-centric edge platform for mesh networks: The case of CityLab testbed

  • Selimi, Mennan
  • Navarro Moldes, Leandro
  • Braem, Bart
  • Freitag, Fèlix
By leveraging resources from the Fed4Fire+ City-Lab testbed, we design the PiGeon edge computing platform that experiments solution that enable ICN based edge services in wireless mesh networks (WMNs). PiGeon combines into a platform several trends in edge computing namely the ICN (Information-Centric Networking), the containerization of services exemplified by Docker, novel service placement algorithms and the increasing availability of energy efficient but still powerful hardware at user premises (Raspberry Pi, mini-PCs, and enhanced home gateways). We underpin the PiGeon platform with Docker container-based service that can be seamlessly delivered, cached and deployed at the network edge. The core of the PiGeon platform is the Decision Engine making a decision on where and when to deploy a service instance to satisfy the service requirements while considering the network status and available hardware resources. We collect network data from a real citywide mesh network such as CityLab FIRE testbed located at the city of Antwerp, Belgium. The collected data is used to feed our service placement heuristic within the PiGeon platform. Through a real deployment in CityLab testbed, we show that our service placement heuristic improves the response time up to 37% for stateful services (Web2.0 service). Apart from improving the QoS for end-users, our results show that ICN plays a key role in improving the service delivery time as well as reducing the traffic consumption in WMNs. The overall effect of ICN in our platform is that most content and service delivery requests can be satisfied very close to the client device, many times just one hop away, decoupling QoS from intra-network traffic and origin server load., This work was supported by the European H2020 framework programme project Fed4Fire+ (732638), by the Spanish State Research Agency (AEI) under contracts PCI2019-111850-2 and PCI2019-111851-2, and the Catalan government AGAUR SGR 990., Peer Reviewed, Postprint (author's final draft)
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

A two-stage multi-criteria optimization method for service placement in decentralized edge micro-clouds

  • Panadero, Javier|||0000-0002-3793-3328
  • Selimi, Mennan|||0000-0001-9644-5415
  • Calvet, Laura|||0000-0001-8425-1381
  • Marquès Puig, Joan Manuel
  • Freitag, Felix|||0000-0001-5438-479X
Community networks are becoming increasingly popular due to the growing demand for network connectivity in both rural and urban areas. Community networks are owned and managed at the edge by volunteers. Their irregular topology, the heterogeneity of resources and their unreliable behavior claim for advanced optimization methods to place services in the network. In particular, an efficient service placement method is key for the performance of these systems. This work presents the Multi-Criteria Optimal Placement method, a novel and fast two-stage multi-objective method to place services in decentralized community network edge micro-clouds. A comprehensive set of computational experiments is carried out using real traces of Guifi.net, which is the largest production community network worldwide. According to the results, the proposed method outperforms both the random placement method used currently in Guifi.net and the Bandwidth-aware Service Placement method, which provides the best known solutions in the literature, by a mean gap in bandwidth gain of about 53% and 10%, respectively, while it also reduces the number of resources used.