Boris Bellalta

Francesc Wilhelmi, Jernej Hribar, Selim F. Yilmaz et al.

As wireless standards evolve, more complex functionalities are introduced to address the increasing requirements in terms of throughput, latency, security, and efficiency. To unleash the potential of such new features, artificial intelligence (AI) and machine learning (ML) are currently being exploited for deriving models and protocols from data, rather than by hand-programming. In this paper, we explore the feasibility of applying ML in next-generation wireless local area networks (WLANs). More specifically, we focus on the IEEE 802.11ax spatial reuse (SR) problem and predict its performance through federated learning (FL) models. The set of FL solutions overviewed in this work is part of the 2021 International Telecommunication Union (ITU) AI for 5G Challenge.

Gabriel Martins Dias, Toni Adame, Boris Bellalta et al.

Wireless sensor networks (WSNs) have been adopted as merely data producers for years. However, the data collected by WSNs can also be used to manage their operation and avoid unnecessary measurements that do not provide any new knowledge about the environment. The benefits are twofold because wireless sensor nodes may save their limited energy resources and also reduce the wireless medium occupancy. We present a self-managed platform that collects and stores data from sensor nodes, analyzes its contents and uses the built knowledge to adjust the operation of the entire network. The system architecture facilitates the incorporation of traditional WSNs into the Internet of Things by abstracting the lower communication layers and allowing decisions based on the data relevance. Finally, we demonstrate the platform optimizing a WSN's operation at runtime, based on different real-time data analysis.

Rashid Ali, Boris Bellalta

Next-generation Wi-Fi networks are looking forward to introducing new features like multi-link operation (MLO) to both achieve higher throughput and lower latency. However, given the limited number of available channels, the use of multiple links by a group of contending Basic Service Sets (BSSs) can result in higher interference and channel contention, thus potentially leading to lower performance and reliability. In such a situation, it could be better for all contending BSSs to use less links if that contributes to reduce channel access contention. Recently, reinforcement learning (RL) has proven its potential for optimizing resource allocation in wireless networks. However, the independent operation of each wireless network makes difficult -- if not almost impossible -- for each individual network to learn a good configuration. To solve this issue, in this paper, we propose the use of a Federated Reinforcement Learning (FRL) framework, i.e., a collaborative machine learning approach to train models across multiple distributed agents without exchanging data, to collaboratively learn the the best MLO-Link Allocation (LA) strategy by a group of neighboring BSSs. The simulation results show that the FRL-based decentralized MLO-LA strategy achieves a better throughput fairness, and so a higher reliability -- because it allows the different BSSs to find a link allocation strategy which maximizes the minimum achieved data rate -- compared to fixed, random and RL-based MLO-LA schemes.

Gabriel Martins Dias, Simon Oechsner, Boris Bellalta

In this work, we present a method that exploits a scenario with inter-Wireless Sensor Networks (WSNs) information exchange by making predictions and adapting the workload of a WSN according to their outcomes. We show the feasibility of an approach that intelligently utilizes information produced by other WSNs that may or not belong to the same administrative domain. To illustrate how the predictions using data from external WSNs can be utilized, a specific use-case is considered, where the operation of a WSN measuring relative humidity is optimized using the data obtained from a WSN measuring temperature. Based on a dedicated performance score, the simulation results show that this new approach can find the optimal operating point associated to the trade-off between energy consumption and quality of measurements. Moreover, we outline the additional challenges that need to be overcome, and draw conclusions to guide the future work in this field.

Francesc Wilhelmi, Boris Bellalta, Miguel Casasnovas et al.

Spatial Reuse (SR) is a cost-effective technique for improving spectral efficiency in dense IEEE 802.11 deployments by enabling simultaneous transmissions. However, the decentralized optimization of SR parameters -- transmission power and Carrier Sensing Threshold (CST) -- across different Basic Service Sets (BSSs) is challenging due to the lack of global state information. In addition, the concurrent operation of multiple agents creates a highly non-stationary environment, often resulting in suboptimal global configurations (e.g., using the maximum possible transmission power by default). To overcome these limitations, this paper introduces a decentralized learning algorithm based on regret-matching, grounded in internal regret minimization. Unlike standard decentralized ``selfish'' approaches that often converge to inefficient Nash Equilibria (NE), internal regret minimization guides competing agents toward Correlated Equilibria (CE), effectively mimicking coordination without explicit communication. Through simulation results, we showcase the superiority of our proposed approach and its ability to reach near-optimal global performance. These results confirm the not-yet-unleashed potential of scalable decentralized solutions and question the need for the heavy signaling overheads and architectural complexity associated with emerging centralized solutions like Multi-Access Point Coordination (MAPC).

Ibrahim Aboushehada, Boris Bellalta, Giovanni Geraci et al.

Coordinated beamforming (Co-BF) is a key multi-access-point coordination (MAPC) technique for dense Wi-Fi deployments, but its performance can be hindered by the large channel state information (CSI) feedback required through channel sounding across overlapping basic service sets (OBSS). This work proposes an autoencoder (AE)-based CSI compression mechanism integrated into a standards-aligned IEEE 802.11bn MAC design. Using an event-driven simulator with realistic channels generated through Sionna RT, we evaluate the tradeoff between AE reconstruction accuracy and feedback size by measuring their impact on channel sounding overhead and data latency. Our results show that AE-based compression reduces channel sounding overhead by more than 50% compared to IEEE 802.11 CSI compression, with a compression ratio of 1/4 providing the best accuracy/feedback-size tradeoff for lowest data latency. Compared to legacy transmissions without MAPC, IEEE 802.11 CSI compression limits Co-BF due to high channel sounding overhead, causing it to underperform the legacy in some situations. However, AE-based CSI compression enables better Co-BF performance with substantial gains in throughput and data latency compared to legacy, demonstrating its promise as an enabler of efficient MAPC operation in future Wi-Fi systems.

Francesc Wilhelmi, Boris Bellalta, Szymon Szott et al.

Multi-Access Point Coordination (MAPC) and Artificial Intelligence and Machine Learning (AI/ML) are expected to be key features in future Wi-Fi, such as the forthcoming IEEE 802.11bn (Wi-Fi~8) and beyond. In this paper, we explore a coordinated solution based on online learning to drive the optimization of Spatial Reuse (SR), a method that allows multiple devices to perform simultaneous transmissions by controlling interference through Packet Detect (PD) adjustment and transmit power control. In particular, we focus on a Multi-Agent Multi-Armed Bandit (MA-MAB) setting, where multiple decision-making agents concurrently configure SR parameters from coexisting networks by leveraging the MAPC framework, and study various algorithms and reward-sharing mechanisms. We evaluate different MA-MAB implementations using Komondor, a well-adopted Wi-Fi simulator, and demonstrate that AI-native SR enabled by coordinated MABs can improve the network performance over current Wi-Fi operation: mean throughput increases by 15%, fairness is improved by increasing the minimum throughput across the network by 210%, while the maximum access delay is kept below 3 ms.

Francesc Wilhelmi, Szymon Szott, Katarzyna Kosek-Szott et al.

Artificial intelligence (AI) and machine learning (ML) are nowadays mature technologies considered essential for driving the evolution of future communications systems. Simultaneously, Wi-Fi technology has constantly evolved over the past three decades and incorporated new features generation after generation, thus gaining in complexity. As such, researchers have observed that AI/ML functionalities may be required to address the upcoming Wi-Fi challenges that will be otherwise difficult to solve with traditional approaches. This paper discusses the role of AI/ML in current and future Wi-Fi networks and depicts the ways forward. A roadmap towards AI/ML-native Wi-Fi, key challenges, standardization efforts, and major enablers are also discussed. An exemplary use case is provided to showcase the potential of AI/ML in Wi-Fi at different adoption stages.

Francesc Wilhelmi, David Góez, Paola Soto et al.

With the advent of Artificial Intelligence (AI)-empowered communications, industry, academia, and standardization organizations are progressing on the definition of mechanisms and procedures to address the increasing complexity of future 5G and beyond communications. In this context, the International Telecommunication Union (ITU) organized the first AI for 5G Challenge to bring industry and academia together to introduce and solve representative problems related to the application of Machine Learning (ML) to networks. In this paper, we present the results gathered from Problem Statement~13 (PS-013), organized by Universitat Pompeu Fabra (UPF), which primary goal was predicting the performance of next-generation Wireless Local Area Networks (WLANs) applying Channel Bonding (CB) techniques. In particular, we overview the ML models proposed by participants (including Artificial Neural Networks, Graph Neural Networks, Random Forest regression, and gradient boosting) and analyze their performance on an open dataset generated using the IEEE 802.11ax-oriented Komondor network simulator. The accuracy achieved by the proposed methods demonstrates the suitability of ML for predicting the performance of WLANs. Moreover, we discuss the importance of abstracting WLAN interactions to achieve better results, and we argue that there is certainly room for improvement in throughput prediction through ML.

Álvaro López-Raventós, Boris Bellalta

Enterprise Wireless Local Area Networks (WLANs) consist of multiple Access Points (APs) covering a given area. Finding a suitable network configuration able to maximize the performance of enterprise WLANs is a challenging task given the complex dependencies between APs and stations. Recently, in wireless networking, the use of reinforcement learning techniques has emerged as an effective solution to efficiently explore the impact of different network configurations in the system performance, identifying those that provide better performance. In this paper, we study if Multi-Armed Bandits (MABs) are able to offer a feasible solution to the decentralized channel allocation and AP selection problems in Enterprise WLAN scenarios. To do so, we empower APs and stations with agents that, by means of implementing the Thompson sampling algorithm, explore and learn which is the best channel to use, and which is the best AP to associate, respectively. Our evaluation is performed over randomly generated scenarios, which enclose different network topologies and traffic loads. The presented results show that the proposed adaptive framework using MABs outperform the static approach (i.e., using always the initial default configuration, usually random) regardless of the network density and the traffic requirements. Moreover, we show that the use of the proposed framework reduces the performance variability between different scenarios. Results also show that we achieve the same performance (or better) than static strategies with less APs for the same number of stations. Finally, special attention is placed on how the agents interact. Even if the agents operate in a completely independent manner, their decisions have interrelated effects, as they take actions over the same set of channel resources.

Francesc Wilhelmi, Marc Carrascosa, Cristina Cano et al.

Without any doubt, Machine Learning (ML) will be an important driver of future communications due to its foreseen performance when applied to complex problems. However, the application of ML to networking systems raises concerns among network operators and other stakeholders, especially regarding trustworthiness and reliability. In this paper, we devise the role of network simulators for bridging the gap between ML and communications systems. In particular, we present an architectural integration of simulators in ML-aware networks for training, testing, and validating ML models before being applied to the operative network. Moreover, we provide insights on the main challenges resulting from this integration, and then give hints discussing how they can be overcome. Finally, we illustrate the integration of network simulators into ML-assisted communications through a proof-of-concept testbed implementation of a residential Wi-Fi network.

Francesc Wilhelmi, Boris Bellalta, Cristina Cano et al.

Reinforcement Learning is gaining attention by the wireless networking community due to its potential to learn good-performing configurations only from the observed results. In this work we propose a stateless variation of Q-learning, which we apply to exploit spatial reuse in a wireless network. In particular, we allow networks to modify both their transmission power and the channel used solely based on the experienced throughput. We concentrate in a completely decentralized scenario in which no information about neighbouring nodes is available to the learners. Our results show that although the algorithm is able to find the best-performing actions to enhance aggregate throughput, there is high variability in the throughput experienced by the individual networks. We identify the cause of this variability as the adversarial setting of our setup, in which the most played actions provide intermittent good/poor performance depending on the neighbouring decisions. We also evaluate the effect of the intrinsic learning parameters of the algorithm on this variability.

Gabriel Martins Dias, Maddalena Nurchis, Boris Bellalta

Monitoring Wireless Sensor Networks (WSNs) are composed of sensor nodes that report temperature, relative humidity, and other environmental parameters. The time between two successive measurements is a critical parameter to set during the WSN configuration because it can impact the WSN's lifetime, the wireless medium contention and the quality of the reported data. As trends in monitored parameters can significantly vary between scenarios and within time, identifying a sampling interval suitable for several cases is also challenging. In this work, we propose a dynamic sampling rate adaptation scheme based on reinforcement learning, able to tune sensors' sampling interval on-the-fly, according to environmental conditions and application requirements. The primary goal is to set the sampling interval to the best value possible so as to avoid oversampling and save energy, while not missing environmental changes that can be relevant for the application. In simulations, our mechanism could reduce up to 73% the total number of transmissions compared to a fixed strategy and, simultaneously, keep the average quality of information provided by the WSN. The inherent flexibility of the reinforcement learning algorithm facilitates its use in several scenarios, so as to exploit the broad scope of the Internet of Things.

Gabriel Martins Dias, Boris Bellalta, Simon Oechsner

In 2008, the CEO of the company that manages and maintains the public bicycle service in Barcelona recognized that one may not expect to always find a place to leave the rented bike nearby their destination, similarly to the case when, driving a car, people may not find a parking lot. In this work, we make predictions about the statuses of the stations of the public bicycle service in Barcelona. We show that it is feasible to correctly predict nearly half of the times when the stations are either completely full of bikes or completely empty, up to 2 days before they actually happen. That is, users might avoid stations at times when they could not return a bicycle that they have rented before, or when they would not find a bike to rent. To achieve that, we apply the Random Forest algorithm to classify the status of the stations and improve the lifetime of the models using publicly available data, such as information about the weather forecast. Finally, we expect that the results of the predictions can be used to improve the quality of the service and make it more reliable for the users.