Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

An autoconfiguration strategy for very large scale long range wide area network deployments in smart cities

  • Torres-Sanz, Vicente
  • Sangüesa, Julio A.
  • Martinez, Francisco J.
  • Garrido, Piedad
  • Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
[EN] LoRa has proven to be an ideal solution for Internet of Things networks and applications that require long-distance communications, such as those related to smart cities or precision agriculture. Its low cost combined with the wide availability of LoRa-compatible devices make it possible to easily deploy a large number of sensors capable of collecting and transmitting key information for new services and applications. However, the process of adding new devices into a Long Range Wide Area Network (LoRaWAN) network represents a significant challenge on a large scale, as each device must be individually configured and manually registered to join the network. This manual approach is costly and impractical when it comes to deploying a very large number of devices. To address this problem, this paper proposes two deployment strategies (semi-automatic and automatic) to simplify and streamline the process of activating and registering LoRaWAN devices. These strategies facilitate the deployment of large-scale devices in smart cities, and their adoption can significantly enhance the deployment of LoRaWAN devices. Experimental results clearly demonstrate the benefits of our solution. Specifically, for 500 devices, the semi-automatic deployment is 3.75 times more efficient, and the automatic deployment is an impressive 394.87 times faster than the manual deployment., Government of Aragon and the European Social Fund "Construyendo Europadesde Aragon",Grant/Award Number: T40 23D; MCIN/AEI/10.13039/501100011033and 'ERDFA way of making Europe', Grant/Award Number: PID2021-122580NB-I00;National Cybersecurity Institute, Grant/Award Number: C077/23.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Adaptive Energy-Saving Control for Hygrothermal Chambers Under Dynamic Electricity Pricing

  • Donate, Pablo
  • Torres-Sanz, Vicente
  • Martinez, Francisco J.
  • Garrido, Piedad
  • Sangüesa, Julio A.
  • Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
[EN] Many industrial processes rely on climate control systems whose thermal or hygrothermal inertia allows for a degree of temporal flexibility in electricity consumption, which can be exploited through load-shifting strategies toward lower-price time slots. This work presents an Internet of Things (IoT) system for electricity cost optimization in this type of process. The system integrates a data acquisition layer for industrial process and electricity market data, a data-driven process model automatically extracted from historical data, and a simulation engine with coupled humidity-power flow. Based on this engine, three optimization strategies (E1-E3) of increasing complexity are defined, designed with a view to deployment on embedded devices. The system is validated on an industrial drying chamber in the cheese sector over one full annual cycle, comprising 355 evaluated days between February 2025 and February 2026. The best strategy achieves annual savings of 44.65 % under the most aggressive configuration evaluated (three saving windows of four hours per day), and between 11.3 % and 36.0 % under more conservative ones. The evaluation is complemented by a leave-one-month-out cross-validation and by an external validation on a second drying chamber with different setpoints and load. The results show that simulation-based strategies substantially outperform purely price-based selection, and that the strategy with prior pruning (E2) constitutes an effective approximation of the exhaustive search (E3), with a difference of at most 0.25 percentage points and a computational complexity compatible with embedded hardware., This work was supported in part by the Government of Aragón and the European Social Fund Construyendo Europa desde Aragón through Research Group under Grant T40_23D; and in part by the MORELLINO Research Project, funded by the Direcció General de Ciència i Investigació of the Generalitat Valenciana, Spain, under Grant CIPROM/2023/29.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

MoBiSea: A Binary Search Algorithm for Product Clustering in Industry 4.0

  • Herrero, Ángel C.
  • Sanguesa, Julio A.
  • Garrido, Piedad
  • Martinez, Francisco J.
  • Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
[EN] Proprietary systems used to modernize Industry 4.0 usually involve high financial costs. Consequently, using low-cost devices with the same functionalities, capable of replacing these proprietary systems but at a lower cost, has become an incipient trend. However, these low-cost devices usually come with electromagnetic interference problems as they are encapsulated in electrical panels, sitting alongside electromechanical devices. In this article, we present Mode Binary Search, an algorithm specifically designed for use in a low-cost automated-industrial-productivity-data-collection system. Specifically, productivity data are obtained from the availability and sealing signals of the thermoplastic sealing machines in production lines belonging to the agri-food industry. Mode Binary Search was designed to cluster sealing signals, thus enabling us to identify which products have been made. Furthermore, the algorithm determines when the manufacturing of each product starts and ends, in other words, the exact moment a product change occurs and all this without the need for operator supervision or intervention. Finally, we compared our algorithm, based on binary search, with three clustering mechanisms: k-means, k-rms and x-means. Out of all the cases we analyzed, the maximum error committed by Mode Binary Search is limited to 2.69%, thereby outperforming all others., This work has been partially supported by the Government of Aragón and the European Social Fund Construyendo Europa desde Aragón (T40_23D Research Group) and also by R&D project PID2021-122580NB-I00, funded by MCIN/AEI/10.13039/501100011033 and ERDF A way of making Europe .
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

MoBiSea: a binary search algorithm for product clustering in Industry 4.0

  • Herrero, Angel C.
  • Sanguesa, Julio A.
  • Garrido, Piedad
  • Martinez, Francisco J.
  • Calafate, Carlos T.
Proprietary systems used to modernize Industry 4.0 usually involve high financial costs. Consequently, using low-cost devices with the same functionalities, capable of replacing these proprietary systems but at a lower cost, has become an incipient trend. However, these low-cost devices usually come with electromagnetic interference problems as they are encapsulated in electrical panels, sitting alongside electromechanical devices. In this article, we present Mode Binary Search, an algorithm specifically designed for use in a low-cost automated-industrial-productivity-data-collection system. Specifically, productivity data are obtained from the availability and sealing signals of the thermoplastic sealing machines in production lines belonging to the agri-food industry. Mode Binary Search was designed to cluster sealing signals, thus enabling us to identify which products have been made. Furthermore, the algorithm determines when the manufacturing of each product starts and ends, in other words, the exact moment a product change occurs and all this without the need for operator supervision or intervention. Finally, we compared our algorithm, based on binary search, with three clustering mechanisms: k-means, k-rms and x-means. Out of all the cases we analyzed, the maximum error committed by Mode Binary Search is limited to 2.69%, thereby outperforming all others.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

An autoconfiguration strategy for very large scale long range wide area network deployments in smart cities

  • Torres-Sanz, Vicente
  • Sangüesa, Julio A.
  • Martínez, Francisco J.
  • Garrido, Piedad
  • Calafate, Carlos T.
LoRa has proven to be an ideal solution for Internet of Things networks and applications that require long‐distance communications, such as those related to smart cities or precision agriculture. Its low cost combined with the wide availability of LoRa‐compatible devices make it possible to easily deploy a large number of sensors capable of collecting and transmitting key information for new services and applications. However, the process of adding new devices into a Long Range Wide Area Network (LoRaWAN) network represents a significant challenge on a large scale, as each device must be individually configured and manually registered to join the network. This manual approach is costly and impractical when it comes to deploying a very large number of devices. To address this problem, this paper proposes two deployment strategies (semi‐automatic and automatic) to simplify and streamline the process of activating and registering LoRaWAN devices. These strategies facilitate the deployment of large‐scale devices in smart cities, and their adoption can significantly enhance the deployment of LoRaWAN devices. Experimental results clearly demonstrate the benefits of our solution. Specifically, for 500 devices, the semi‐automatic deployment is 3.75 times more efficient, and the automatic deployment is an impressive 394.87 times faster than the manual deployment.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Analysis of the Influence of Terrain on LoRaWAN-based IoT Deployments

  • Torres-Sanz, Vicente
  • Sanguesa, Julio A.
  • Serna, Felix
  • Martinez, Francisco J.
  • Garrido, Piedad
  • Calafate, Carlos T.
Long Range Wide Area Network (LoRaWAN) is a network protocol specifically designed to leverage the advantages of Long Range technology. LoRaWAN is employed to connect Internet of Things devices through a long-range network infrastructure, providing a secure and efficient communication layer that facilitates connectivity for a vast number of devices in a LoRa network. The aim of this study is to assess the real-life performance of LoRaWAN in different topographical environments. In particular, two scenarios (one flat and one mountainous) are compared, with an analysis of the success rate in data packet reception. The purpose is to examine how topography influences communication between LoRa devices and gateways, as well as to explore alternatives for overcoming challenges in rugged terrain environments. Therefore, in the mountainous environment, the study also investigates whether the use of drones could enhance communications. The findings of this study reveal that the topography of the terrain significantly impacts LoRa communications, resulting in a 58.63% decrease in the number of successfully received packets compared to a flat environment. Moreover, one-third of the nodes failed to establish communication with the ground gateway, and a partial improvement in connectivity was achieved by using gateways deployed on drones.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

SecureAutoLoRa: An Automated Secure Registration Procedure for LoRaWAN Devices

  • Mallen, Lucas
  • Sanguesa, Julio A.
  • Roldán-Gómez, José
  • Torres-Sanz, Vicente
  • Martinez, Francisco J.
Device registration in LoRaWAN systems can be a tedious process, particularly when managing a large number of devices. To automate this task, we previously developed the AutoLoraConfig protocol, although it includes vulnerabilities that attackers can exploit. To solve this, in this work we introduce the SecureAutoLoRa, a protocol designed to enhance security in the automated device registration process for LoRaWAN networks. SecureAutoLoRa blocks abuse of the guest DevEUI used in automated joins by obfuscating registration messages and enforcing a configurable positional security code that dictates where the real DevEUI appears across packets, markedly hindering unauthorized registrations.Results show that SecureAutoLoRa sharply reduces attackers’ success. Compared with AES-128 and SPECK, it complements standard encryption to provide a practical, layered defense suitable for large-scale LoRaWAN onboarding.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Predicting Home EV Charging Practices Using Machine Learning

  • Donate, Pablo
  • Sanguesa, Julio A.
  • Garrido, Piedad
  • Torres-Sanz, Vicente
  • Martinez, Francisco J.
  • Calafate, Carlos T.
The rapid adoption of electric vehicles (EVs) demands advanced residential charging solutions, where user behavior varies widely due to factors like electricity tariffs and weather conditions. Such conditions make charging predictions particularly complex. This study addresses this challenge by predicting the time an EV remains connected to a residential charger using a dataset of 106,260 sessions. To this end, we propose the Connection Time Neural Model (CTNM), a deep neural network designed to model the complex dynamics of domestic charging, and we introduce the Weighted Error Metric (WEM), a novel metric that penalizes overestimations and under-estimations differently to reflect their real-world impacts on both grid management and user experience. Utilizing bidirectional charger data, we focus solely on connection time, bypassing energy prediction. CTNM is benchmarked against state-of-the-art methods (i.e., Random Forest, Dense Neural Network, XGBoost, and Support Vector Regression) using Mean Absolute Error, Root Mean Squared Error, and WEM as performance metrics. Results demonstrate CTNM’s superiority, reducing average error by 18%, and weighted error by 31% compared to Random Forest, thanks to its deep architecture and integration of contextual features, like variable tariffs and weather.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

ReChat: A Task‐Based Chatbot for EV Charging Management Optimization

  • Donate, Pablo
  • Sanguesa, Julio A.
  • Garrido, Piedad
  • Torres-Sanz, Vicente
  • Martinez, Francisco J.
  • Calafate, Carlos T.
The increasing adoption of electric vehicles (EVs) and the evolution of connected vehicle systems have led to a growing need for intelligent charging management solutions. This article introduces ReChat, a task‐based multilingual chatbot designed to optimize EV charging management through reliable task‐oriented intent understanding and safe action dispatch. By leveraging natural language processing (NLP), ReChat enables seamless user interaction with charging systems across six languages (Spanish, English, German, French, Italian and Portuguese). A custom dataset was developed to train and evaluate the chatbot's intent‐classification capabilities, ensuring robust performance in diverse linguistic contexts. A comparative analysis of multilingual Bidirectional Encoder Representations from Transformers (mBERT)‐based intent classifiers shows that a single pooled multilingual mBERT model achieves macro‐1 values between 68.0% and 78.4% across languages, while language‐specific mBERT models yields 64.7% to 78.9%. This work advances the development of robust conversational AI systems for smart transportation, outlining a modular architecture and empirical evidence on multilingual adaptability in real‐world applications.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

LLMs for industrial databases: an agro-food production plant use case

  • Dranca, Lacramioara
  • Donate, Pablo
  • Sanguesa, Julio A.
  • Garrido, Piedad
  • Torres-Sanz, Vicente
  • Martinez, Francisco J.
Introduction: Extracting value from industrial time-series databases such as InfluxDB 2.0 requires expertise in specialized query languages (InfluxQL, Flux) that domain experts typically lack, and no labeled corpora exist for translating natural language into them. Methods: We present a modular system that translates questions written in Spanish into executable InfluxQL and Flux queries over an InfluxDB 2.0 instance deployed in a real agro-food production plant operating under a self-consumption energy scheme. It comprises a semantic layer implemented as a knowledge graph encoding the InfluxDB schema and its correspondence with the plant's physical components; a hierarchical entity-linking module; a lightweight language model fine-tuned for NL-to-query generation; and a query validation and sanitization module. To obtain training data, we develop a fully automated synthetic dataset distillation pipeline that uses a large teacher model with contextual retrieval from the official InfluxDB 2.0 documentation; each candidate undergoes parsing, AST extraction, and semantic checking against the knowledge graph, and only validated samples are retained. The corpus fine-tunes compact Small Language Models through domain-level conditioning followed by task-specific instruction tuning. Results: Performance is evaluated on a manually curated suite of 56 Spanish queries, evenly distributed across seven operationally relevant query families. Compact models reliably generate syntactically valid queries, but functional evaluation against the live instance reveals a three-layer pattern-high parser validity, moderate execution success, and lower result correctness-that locates the residual gap at the semantic layer. Discussion: The contributions are a complete NL-to-InfluxDB pipeline grounded in an explicit semantic representation of a real industrial schema; a documentation-driven synthetic data generation process with automatic syntactic and semantic verification; and a parameter-efficient fine-tuning strategy enabling query generation with lightweight models suitable for resource-constrained environments.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

A terrain-aware Fresnel zone simulator for LoRa link feasibility in non-Urban areas

  • Torres-Sanz, Vicente
  • Donate, Pablo
  • Sanguesa, Julio A.
  • Garrido, Piedad
  • Martinez, Francisco J.
Planning reliable LoRaWAN deployments in non-urban environments demands tools that move beyond distance-based models to account for the complex interplay between terrain and radio wave propagation. This work addresses this need by introducing the Fresnel Zone Simulator (FresSim), an open-source web tool for terrain-aware LoRa link feasibility assessment in LoRaWAN deployments. FresSim is not intended to model the complete LoRaWAN PHY/MAC protocol stack or packet-level network dynamics. Instead, FresSim focuses on LoRa link feasibility by combining high-resolution Digital Elevation Models (DEMs) with first Fresnel Zone clearance analysis, providing a physically grounded metric to assess coverage viability for each node-gateway link. A key innovation of our tool is its dual operational mode: it supports both pre-deployment planning, generating extensive coverage maps (up to 50 km2), and post-deployment validation by seamlessly importing and analyzing real-world data from major LoRaWAN network servers (The Things Network and ChirpStack). To evaluate its predictive capability, we conducted an empirical validation using real deployment traces across diverse terrains. The results obtained show that FresSim correctly predicted all terrain-aware link feasibility outcomes in the evaluated scenarios, achieving higher agreement with field observations than LoRaSim, which does not account for terrain or Fresnel Zone effects. These results indicate that incorporating detailed topographic information and Fresnel Zone clearance can be critical for accurate LoRaWAN deployment planning in topographically complex, non-urban environments.