Pasar al contenido principal

Resultados relacionados

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

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Data-driven cellular mobility management via Bayesian optimization and reinforcement learning

  • Benzaghta, Mohamed
  • Ammar, Sahar
  • López Pérez, David
  • Shihada, Basem
  • Geraci, Giovanni
Mobility management in cellular networks faces increasing complexity due to network densification and heterogeneous user mobility characteristics. Traditional handover (HO) mechanisms, which rely on predefined parameters such as A3-offset and time-to-trigger (TTT), often fail to optimize mobility performance across varying speeds and deployment conditions. Fixed A3-offset and TTT configurations either delay HOs, increasing radio link failures (RLFs), or accelerate them, leading to excessive ping-pong effects. To address these challenges, we propose two distinct data-driven mobility management approaches leveraging high-dimensional Bayesian optimization (HD-BO) and deep reinforcement learning (DRL). While HD-BO optimizes predefined HO parameters such as A3-offset and TTT, DRL provides a parameter-free alternative by allowing an agent to select serving cells based on real-time network conditions. We systematically compare these two approaches in real-world site-specific deployment scenarios (employing Sionna ray tracing for site-specific channel propagation modeling), highlighting their complementary strengths. Results show that both HD-BO and DRL outperform 3GPP set-1 (TTT of 480 ms and A3-offset of 3 dB) and set-5 (TTT of 40 ms and A3-offset of -1 dB) benchmarks. We augment HD-BO with transfer learning so it can generalize across a range of user speeds. Applying the same transfer-learning strategy to the DRL method reduces its training time by a factor of 2.5 while preserving optimal HO performance, showing that it adapts efficiently to the mobility of aerial users such as UAVs. Simulations further reveal that HD-BO remains more sample-efficient than DRL, making it more suitable for scenarios with limited training data., This work was supported in part by the HORIZON-SESAR-2023-DES-ER-02 Project ANTENNAE under Grant 101167288; in part by Spanish Ministry of Economic Affairs and Digital Transformation and European Union NextGenerationEU under Grant CNS2023-145384 and Grant CNS2023-144333; in part by Spanish State Research Agency under Grant PID2021-123999OB-I00, Grant PID2024-156488OB-I00, and Grant CEX2021-001195-M; in part by the Generalitat Valenciana, Spain, through the CIDEGENT PlaGenT (Project iTENTE) under Grant CIDEXG/2022/17; and in part by the Universitat Pompeu Fabra (UPF)-Fractus Chair.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Energy-Efficient Sleep Mode Optimization in 5G mmWave Networks via Multi-Agent Deep Reinforcement Learning

  • Masrur, Saad
  • Guvenc, Ismail
  • López-Pérez, David
[EN] Dynamic sleep mode optimization (SMO) in millimeter-wave (mmWave) networks is essential for maximizing energy efficiency (EE) under stringent quality-of-service (QoS) constraints. However, existing optimization and reinforcement learning (RL)-based approaches rely on aggregated, static base station (BS) traffic models that fail to capture non-stationary traffic dynamics and suffer from prohibitively large state-action spaces, limiting their real-world deployment. To address these challenges, this paper proposes a Multi-Agent Deep Reinforcement Learning (MARL) framework employing a Double Deep Q-Network (DDQN), referred to as MARL-DDQN, for adaptive SMO in a 3D urban environment using a time-varying and community-based user equipment (UE) mobility model. Unlike conventional single-agent RL, the proposed MARL-DDQN enables scalable, distributed decision-making with minimal signaling overhead. A realistic BS power consumption model and beamforming are integrated to accurately quantify EE, while QoS is uniquely defined in terms of throughput. The proposed method adaptively learns SMO policies to maximize EE while mitigating inter-cell interference and ensuring throughput fairness. Extensive simulations demonstrate that MARL-DDQN consistently outperforms state-of-the-art SM strategies, including the All On, iterative QoS-aware load-based (IT-QoS-LB), MARL-DDPG, and MARL-PPO, achieving up to 0.60 Mbit/Joule EE, 8.5 Mbps 10th-percentile throughput, and satisfying QoS constraints 95% of the time under dynamic network scenarios., This work was supported in part by NSF under Award CNS-2332835, in part by the Generalitat Valenciana through the Convocatoria d'Incorporacio i Reincorporacio de Personal Investigador d'Excellencia (CIDEGENT) PlaGenT under Grant CIDEXG/2022/17, and in part by the Project iTENTE funded by Ministry of Science, Innovation and Universities (MCIN)/State Research Agency (AEI)/10.13039/501100011033 and European Union "NextGenerationEU"/PRTR" under Grant CNS2023-144333.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Data-Driven Energy Efficiency Modeling in Large-Scale Networks: An Expert Knowledge and ML-Based Approach

  • López-Pérez, David
  • De Domenico, Antonio
  • Piovesan, Nicola
  • Debbah, Merouane
[EN] The energy consumption of mobile networks poses a critical challenge. Mitigating this concern necessitates the deployment and optimization of network energy-saving solutions, such as carrier shutdown, to dynamically manage network resources. Traditional optimization approaches encounter complexity due to factors like the large number of cells, stochastic traffic, channel variations, and intricate trade-offs. This paper introduces the simulated reality of communication networks (SRCON) framework, a novel, data-driven modeling paradigm that harnesses live network data and employs a blend of machine learning (ML)- and expert-based models. These mix of models accurately characterizes the functioning of network components, and predicts network energy efficiency and user equipment (UE) quality of service for any energy carrier shutdown configuration in a specific network. Distinguishing itself from existing methods, SRCON eliminates the reliance on expensive expert knowledge, drive testing, or incomplete maps for predicting network performance. This paper details the pipeline employed by SRCON to decompose the large network energy efficiency modeling problem into ML- and expert-based submodels. It demonstrates how, by embracing stochasticity, and carefully crafting the relationship between such submodels, the overall computational complexity can be reduced and prediction accuracy enhanced. Results derived from real network data underscore the paradigm shift introduced by SRCON, showcasing significant gains over a state-of-the-art method used by a operator for network energy efficiency modeling. The reliability of this local, data-driven modeling of the network proves to be a key asset for network energy-saving optimization., This work was supported in part by NSF Project under Grant CNS 1910153; in part by the Generalitat Valenciana through the CIDEGENTPlaGenT, Project iTENTE, under Grant CIDEXG/2022/17; and in part by the MCIN/AEI/10.13039/501100011033 and the European Union''NextGenerationEU/PRTR'' under Grant CNS2023-144333.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Wi-Fi: 25 Years and Counting

  • Geraci, Giovanni
  • Meneghello, Francesca
  • Wilhelmi, Francesc
  • Val, Inaki
  • Giordano, Lorenzo Galati
  • Cordeiro, Carlos
  • Ghosh, Monisha
  • Knightly, Edward
  • Bellalta, Boris
  • López-Pérez, David
[EN] Today, Wi-Fi is over 25 years old. Yet, despite sharing the same branding name, today's Wi-Fi boasts entirely new capabilities that were not even on the roadmap 25 years ago. This article aims to provide a holistic and comprehensive technical and historical tutorial on Wi-Fi, beginning with Institute of Electrical and Electronics Engineers 802.11b (Wi-Fi 1) and looking forward to IEEE 802.11bn (Wi-Fi 8). This is the first tutorial article to span these eight generations. Rather than a generation-by-generation exposition, we describe the key mechanisms that have advanced Wi-Fi. We begin by discussing spectrum allocation and coexistence, and detailing the IEEE 802.11 standardization cycle. Second, we provide an overview of the physical layer (PHY) and describe key elements that have enabled data rates to increase by over 1000 & times;. Third, we describe how Wi-Fi medium access control (MAC) has been enhanced from the original distributed coordination function (DCF) to now include capabilities spanning from frame aggregation to wideband spectrum access. Fourth, we describe how Wi-Fi 5 first broke the one-user-at-a-time paradigm and introduced multi-user (MU) access. Fifth, given the increasing use of mobile, battery-powered devices, we describe Wi-Fi's energy-saving mechanisms over the generations. Sixth, we discuss how Wi-Fi was enhanced to seamlessly aggregate spectrum across 2.4-, 5-, and 6-GHz bands to improve throughput, reliability, and latency. Finally, we describe how Wi-Fi enables nearby access points (APs) to coordinate in order to improve performance and efficiency. In the Appendix, we further discuss Wi-Fi developments beyond 802.11bn, including integrated millimeter-wave (IMMW) operations, sensing, security and privacy extensions, and the adoption of artificial intelligence (AI)/machine learning (ML)., This work was supported in part by Spanish Research Agency under Grant PID2021-123999OB-I00, Grant PID2021-123995NB-I00, Grant PID2024-156488OB-I00, Grant CEX2021-001195-M, Grant CNS2023-145384, Grant CNS2023-144333, Grant PID2024-155470NB-I00; in part by SGR 00955-2021 AGAUR; in part by ICREA Academia; in part by European Union-Next Generation EU through Italian National Recovery and Resilience Plan (NRRP), Mission 4, Component 2, Investment 1.2, CUP C93C24004880002, Project "CAMELIA"; in part by the Generalitat Valenciana, Spain, under Grant CIDEXG/2022/17; in part by Nokia; in part by Cisco; in part by Intel; and in part by NSF under Grant 2433923, Grant 2402783, Grant 2211618, Grant 2346413, and Grant 2229387.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Federated learning: A cutting-edge survey of the latest advancements and applications

  • Akhtarshenas, Azim
  • López-Pérez, David
  • Vahedifar, Mohammad Ali
  • Ayoobi, Navid
  • Maham, Behrouz
  • Alizadeh, Tohid
  • Ebrahimi, Sina
[EN] Robust machine learning (ML) models can be developed by leveraging large volumes of data and distributing the computational tasks across numerous devices or servers. Federated learning (FL) is a technique in the realm of ML that facilitates this goal by utilizing cloud infrastructure to enable collaborative model training among a network of decentralized devices. Beyond distributing the computational load, FL targets the resolution of privacy issues and the reduction of communication costs simultaneously. To protect user privacy, FL requires users to send model updates rather than transmitting large quantities of raw and potentially confidential data. Specifically, individuals train ML models locally using their own data and then upload the results in the form of weights and gradients to the cloud for aggregation into the global model. This strategy is also advantageous in environments with limited bandwidth or high communication costs, as it prevents the transmission of large data volumes. With the increasing volume of data and rising privacy concerns, alongside the emergence of large-scale ML models like Large Language Models (LLMs), FL presents itself as a timely and relevant solution. It is therefore essential to review current FL algorithms to guide future research that meets the rapidly evolving ML demands. This survey provides a comprehensive analysis and comparison of the most recent FL algorithms, evaluating them on various fronts including mathematical frameworks, privacy protection, resource allocation, and applications. Beyond summarizing existing FL methods, this survey identifies potential gaps, open areas, and future challenges based on the performance reports and algorithms used in recent studies. This survey enables researchers to readily identify existing limitations in the FL field for further exploration., This research is supported by the Generalitat Valenciana through the CIDEGENT PlaGenT, Grant CIDEXG/2022/17, Project iTENTE, and the action CNS2023-144333, financed by MCIN/AEI/10.13039/501100011033 and the European Union "NextGenerationEU"/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Cellular Network Design for UAV Corridors via Data-Driven High-Dimensional Bayesian Optimization

  • Benzaghta, M
  • Geraci, G
  • Valcarce, Alvaro
  • López-Pérez, David
[EN] We address the challenge of designing cellular networks for uncrewed aerial vehicles (UAVs) corridors through a novel data-driven approach. We assess multiple state-of-the-art high-dimensional Bayesian optimization (HD-BO) techniques to jointly optimize the cell antenna tilts and half-power beamwidth (HPBW). We find that some of these approaches achieve over 20dB gains in median SINR along UAV corridors, with negligible degradation to ground user performance. Furthermore, we explore the HD-BO's capabilities in terms of model generalization via transfer learning, where data from a previously observed scenario source is leveraged to predict the optimal solution for a new scenario target. We provide examples of scenarios where such transfer learning is successful and others where it fails. Moreover, we demonstrate that HD-BO enables multi-objective optimization, identifying optimal design trade-offs between data rates on the ground versus UAV coverage reliability. We observe that aiming to provide UAV coverage across the entire sky can lower the rates for ground users compared to setups specifically optimized for UAV corridors. Finally, we validate our approach through a case study in a real-world cellular network, where HD-BO identifies optimal and non-obvious antenna configurations that result in more than double the rates along 3D UAV corridors with negligible ground performance loss., This work was supported in part by HORIZON-SESAR-2023-DES-ER-02 Project ANTENNAE under Grant 101167288; inpart by Spanish Ministry of Economic Affairs and Digital Transformation and European Union NextGenerationEU under Grant CNS2023-145384and Grant CNS2023-144333; in part by the UNICO 5G I+D SORUS Project; in part by Spanish State Research Agency under Grant PID2021-123999OB-I00 and Grant CEX2021-001195-M; in part by the Generalitat Valenciana, Spain, through CIDEGENT PlaGenT, Project iTENTE, underGrant CIDEXG/2022/17; and in part by the Universitat Pompeu Fabra (UPF)-Fractus Chair on Tech Transfer and 6G.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Deployment Strategy of Intelligent Omni-Surface-Assisted Outdoor-to-Indoor Millimeter-Wave Communications

  • Liu, Zhiyu
  • Chu, Xiaoli
  • Tang, Na
  • López-Pérez, David
[EN] Intelligent omni-surfaces (IOSs) have been considered for assisting outdoor-to-indoor millimeter-wave (mmWave) communications. Nevertheless, the existing works have not adequately investigated how the number or the deployment locations of IOSs should be optimized for serving multiple indoor users. In this paper, we study IOS-assisted outdoor-to-indoor mmWave communications where IOSs are installed in an exterior wall of a building to refract mmWave signals from an outdoor base station (BS) to indoor users that locate among indoor blockages. Given a fixed total number of refracting elements, we formulate an optimization problem to maximize the downlink energy efficiency of the outdoor BS while satisfying the dowlink data rate requirements of the indoor users by jointly optimizing the number, locations and phase shifts of IOSs and the beamforming vectors of the BS. To address the varying dimensionality and the non-convexity of the optimization problem, we decompose it into two subproblems that optimize the IOSs' phase shifts together with the BS beamforming vectors and the number and locations of IOSs, respectively, and devise successive convex approximation and Continuous Population-Based Incremental Learning-based algorithms to solve them alternately. Simulation results demonstrate that the proposed algorithms can obtain the optimal number and locations of IOSs, resulting in significantly enhanced energy efficiency of the outdoor BS compared to benchmark schemes., This work was supported in part by the Horizon Europe Research and Innovation Program under Grant 101086219; in part by U.K. Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/X038971/1; in part by the Generalitat Valenciana, Spain, through the CIDEGENT PlaGenT, Project iTENTE, and the Action financed by MCIN/AEI/10.13039/501100011033 under Grant CIDEXG/2022/17 and Grant CNS2023-144333; and in part by the European Union "NextGenerationEU"/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Gradient-Based Optimization of Terrestrial Cellular Networks for Aerial Highways

  • Bernabe, Matteo|||0009-0005-5432-3053
  • López-Pérez, David
  • Piovesan, Nicola
  • Gesbert, David
[EN] Unmanned aerial vehicles (UAVs), owing to their ability to navigate 3D space and encounter line of sight (LoS) conditions, often experience high channel gains across multiple cells. This phenomena results in comparable signal power from various neighboring cells, causing significant interference and reduced signal-to-interference-plus-noise ratio (SINR), which complicates their integration into terrestrial networks. In this paper, we investigate how prior knowledge of planned aerial highways (AHs) can be leveraged by network operators to efficiently optimize their infrastructures for seamless unmanned aerial vehicle (UAV) connectivity. In particular, we propose a gradient-based optimization algorithm to adjust the vertical tilts of 4G long term evolution (LTE) cells, ensuring optimal power distribution between ground and sky, while meeting minimum connectivity requirements along the AHs. Moving towards 5G new radio (NR), we also investigate how multi-antenna systems can be leveraged, together with the information of the planned AHs, to provide further enhanced coverage and performance. In this line, we propose an optimization framework that utilizes gradient computations to design optimal coverage and data beams from NR network cells. Simulation results show significant enhancement in coverage, SINR, and data rates for UAVs. Specifically, considering LTE, our approach yields up to 7 dB in SINR along with a fivefold increase in rates, allowing to satisfy requirements and eliminate coverage gaps. While within NR, our solution achieves up to 13 dB SINR gains and a sixfold improvement in UAV data rate, thereby overcoming previous-generation limitations and further improving aerial connectivity. These findings provide valuable recommendations for network operators aiming to support UAVs services with existing terrestrial infrastructures., This work was supported in part by Generalitat Valenciana, Spain, through CIDEGENT PlaGenT under Grant CIDEXG/2022/17, in part by Project iTENTE, in part by action under Grant CNS2023-144333, funded by MCIN/AEI/10.13039/501100011033, and in part by European Union"NextGenerationEU"/PRTR .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Data-Driven Cellular Mobility Management Via Bayesian Optimization and Reinforcement Learning

  • Benzaghta, Mohamed
  • Ammar, Sahar
  • Shihada, Basem
  • Geraci, Giovanni
  • López-Pérez, David
[EN] Mobility management in cellular networks faces increasing complexity due to network densification and heterogeneous user mobility characteristics. Traditional handover (HO) mechanisms, which rely on predefined parameters such as A3-offset and time-to-trigger (TTT), often fail to optimize mobility performance across varying speeds and deployment conditions. Fixed A3-offset and TTT configurations either delay HOs, increasing radio link failures (RLFs), or accelerate them, leading to excessive ping-pong effects. To address these challenges, we propose two distinct data-driven mobility management approaches leveraging high-dimensional Bayesian optimization (HD-BO) and deep reinforcement learning (DRL). While HD-BO optimizes predefined HO parameters such as A3-offset and TTT, DRL provides a parameter-free alternative by allowing an agent to select serving cells based on real-time network conditions. We systematically compare these two approaches in real-world site-specific deployment scenarios (employing Sionna ray tracing for site-specific channel propagation modeling), highlighting their complementary strengths. Results show that both HD-BO and DRL outperform 3GPP set-1 (TTT of 480 ms and A3-offset of 3 dB) and set-5 (TTT of 40 ms and A3-offset of -1 dB) benchmarks. We augment HD-BO with transfer learning so it can generalize across a range of user speeds. Applying the same transfer-learning strategy to the DRL method reduces its training time by a factor of 2.5 while preserving optimal HO performance, showing that it adapts efficiently to the mobility of aerial users such as UAVs. Simulations further reveal that HD-BO remains more sample-efficient than DRL, making it more suitable for scenarios with limited training data., This work was supported in part by the HORIZON-SESAR-2023-DES-ER-02 Project ANTENNAE under Grant 101167288; in part by Spanish Ministry of Economic Affairs and Digital Transformation and European Union NextGenerationEU under Grant CNS2023-145384 and Grant CNS2023-144333; in part by Spanish State Research Agency under Grant PID2021-123999OB-I00, Grant PID2024-156488OB-I00, and Grant CEX2021-001195-M; in part by the Generalitat Valenciana, Spain, through the CIDEGENT PlaGenT(Project iTENTE) under Grant CIDEXG/2022/17; and in part by the Universitat Pompeu Fabra (UPF)-Fractus Chair.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

CNN Autoencoder Resizer: A Power-Efficient LoS/NLoS Detector in MIMO-Enabled UAV Networks

  • Akhtarshenas, Azim
  • López-Pérez, David
  • Ayoobi, Navid
  • Toosi, Ramin
  • Amoozadeh, Matin
[EN] Optimizing the design, performance, and resource efficiency of wireless networks (WNs) necessitates the ability to discern Line of Sight (LoS) and Non-Line of Sight (NLoS) scenarios across diverse applications and environments. Unmanned Aerial Vehicles (UAVs) exhibit significant potential in this regard due to their rapid mobility, aerial capabilities, and payload characteristics. Particularly, UAVs can serve as vital nonterrestrial base stations (NTBS) in the event of terrestrial base station (TBS) failures or downtime. In this paper, we propose CNN autoencoder resizer (CAR) as a framework that improves the accuracy of LoS/NLoS detection without demanding extra power consumption. Our proposed method increases the mean accuracy of detecting LoS/NLoS signals from 66% to 86%, while maintaining consistent power consumption levels. In addition, the resolution provided by CAR shows that it can be employed as a preprocessing tool in other methods to enhance the quality of signals., This research is supported by the Generalitat Valenciana through the CIDEGENT PlaGenT, Grant CIDEXG/2022/17, Project iTENTE, and by the action CNS2023-144333, financed by MCIN/AEI/10.13039/501100011033 and the European Union NextGenerationEU /PRTR.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Data-driven cellular mobility management via Bayesian optimization and reinforcement learning

  • Benzaghta, Mohamed
  • Ammar, Sahar
  • López Pérez, David
  • Shihada, Basem
  • Geraci, Giovanni
Mobility management in cellular networks faces increasing complexity due to network densification and heterogeneous user mobility characteristics. Traditional handover (HO) mechanisms, which rely on predefined parameters such as A3-offset and time-to-trigger (TTT), often fail to optimize mobility performance across varying speeds and deployment conditions. Fixed A3-offset and TTT configurations either delay HOs, increasing radio link failures (RLFs), or accelerate them, leading to excessive ping-pong effects. To address these challenges, we propose two distinct data-driven mobility management approaches leveraging high-dimensional Bayesian optimization (HD-BO) and deep reinforcement learning (DRL). While HD-BO optimizes predefined HO parameters such as A3-offset and TTT, DRL provides a parameter-free alternative by allowing an agent to select serving cells based on real-time network conditions. We systematically compare these two approaches in real-world site-specific deployment scenarios (employing Sionna ray tracing for site-specific channel propagation modeling), highlighting their complementary strengths. Results show that both HD-BO and DRL outperform 3GPP set-1 (TTT of 480 ms and A3-offset of 3 dB) and set-5 (TTT of 40 ms and A3-offset of -1 dB) benchmarks. We augment HD-BO with transfer learning so it can generalize across a range of user speeds. Applying the same transfer-learning strategy to the DRL method reduces its training time by a factor of 2.5 while preserving optimal HO performance, showing that it adapts efficiently to the mobility of aerial users such as UAVs. Simulations further reveal that HD-BO remains more sample-efficient than DRL, making it more suitable for scenarios with limited training data., This work was supported in part by the HORIZON-SESAR-2023-DES-ER-02 Project ANTENNAE under Grant 101167288; in part by Spanish Ministry of Economic Affairs and Digital Transformation and European Union NextGenerationEU under Grant CNS2023-145384 and Grant CNS2023-144333; in part by Spanish State Research Agency under Grant PID2021-123999OB-I00, Grant PID2024-156488OB-I00, and Grant CEX2021-001195-M; in part by the Generalitat Valenciana, Spain, through the CIDEGENT PlaGenT (Project iTENTE) under Grant CIDEXG/2022/17; and in part by the Universitat Pompeu Fabra (UPF)-Fractus Chair.