Search

The next generation of Wi-Fi, i.e., the IEEE 802.11bn (aka Wi-Fi 8), is not only expected to increase its performance and provide extended capabilities but also aims to offer a reliable service. Given that one of the main sources of unreliability in IEEE 802.11 stems from the current distributed channel access, which is based on Listen-Before-Talk (LBT), the development of novel contention schemes gains importance for Wi-Fi 8 and beyond. In this paper, we propose a new channel contention mechanism, "It's Your Turn" (IYT), that extends the existing Distributed Coordination Function (DCF) and aims at improving the reliability of distributed LBT by providing ordered device transmissions thanks to neighboring activity awareness. Using simulation results, we show that our mechanism strives to provide reliable performance by controlling the channel access delay. We prove the versatility of IYT against different topologies, coexistence with legacy devices, and increasing network densities.

IEEE 802.11 networks continuously adapt to meet the stringent requirements of emerging applications like cloud gaming, eXtended Reality (XR), and video streaming services, which require high throughput, low latency, and high reliability. To address these challenges, Coordinated Spatial Reuse (C-SR) can potentially contribute to optimizing spectrum resource utilization. This mechanism is expected to enable a higher number of simultaneous transmissions, thereby boosting spectral efficiency in dense environments and increasing the overall network performance. In this paper, we focus on the performance analysis of C-SR in Wi-Fi 8 networks. In particular, we consider an implementation of C-SR where channel access and inter-Access Point (AP) communication are performed over-the-air using the Distributed Coordination Function (DCF). For such a purpose, we leverage the well-known Bianchi's throughput model and extend it to support multi-AP transmissions via C-SR. Numerical results in a WLAN network that consists of four APs show C-SR throughput gains ranging from 54% to 280% depending on the inter-AP distance and the position of the stations in the area.

Extended Reality (XR) has stringent throughput and delay requirements that are hard to meet with current wireless technologies. Missing these requirements can lead to worsened picture quality, perceived lag between user input and corresponding output, and even dizziness for the end user. In this paper, we study the capability of upcoming Wi-Fi 7, and its novel support for Multi-Link Operation (MLO), to cope with these tight requirements. Our study is based on simulation results extracted from an MLO-compliant simulator that realistically reproduces VR traffic. Results show that MLO can sustain VR applications. By jointly using multiple links with independent channel access procedures, MLO can reduce the overall delay, which is especially useful in the uplink, as it has more stringent requirements than the downlink, and is instrumental in delivering the expected performance. We show that using MLO can allow more users per network than an equivalent number of links using SLO. We also show that while maintaining the same overall bandwidth, a higher number of MLO links with narrow channels leads to lower delays than a lower number of links with wider channels.

Will AI/ML-defined radios become a reality in the near future? In this paper, we introduce the concept of an AI/ML-defined radio - a radio architecture specifically designed to support AI/ML-based optimization and decision-making in communication functions - and depict its promised benefits and potential challenges. Additionally, we discuss a potential roadmap for the development and adoption of AI/ML-defined radios, and highlight the enablers for addressing their associated challenges. While we offer a general overview of the AI/ML-defined radio concept, our focus throughout the paper remains on Wi-Fi, a wireless technology that may significantly benefit from the integration of AI/ML-defined radios, owing to its inherent decentralized management and operation within unlicensed frequency bands.

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.

This paper proposes a novel mechanism to enforce contention-free channel access in the unlicensed spectrum, as opposed to the traditional contention-based approach. To achieve this objective, we build on the Wi-Fi~7 multi-link operation (MLO) and define the means whereby independent channel access attempts are performed in all the addressable links to ensure one available channel/link is ready for transmission at all times, such that a sequence of continuous acquired channels can be maintained. We call this method continuous multi-link operation (ConMLO). In this work, we aim to verify the applicability of ConMLO, its ability to retain spectrum resources for a given duration of time, and its fairness with respect existing approaches, namely legacy single-link operation (SLO) and MLO. To this end, we use realistic data traffic measurements acquired in a crowded football stadium as an exemplary case of challenging spectrum occupation. Our results show that the proposed ConMLO can effectively guarantee continuous channel acquisition under different occupancy scenarios without compromising fairness of channel access compared to existing legacy modes., Comment: 5 pages, 6 figures, conference paper

The increasing cloudification and softwarization of networks foster the interplay among multiple independently managed deployments. An appealing reason for such an interplay lies in distributed Machine Learning (ML), which allows the creation of robust ML models by leveraging collective intelligence and computational power. In this paper, we study the application of the two cornerstones of distributed learning, namely Federated Learning (FL) and Knowledge Distillation (KD), on the Wi-Fi Access Point (AP) load prediction use case. The analysis conducted in this paper is done on a dataset that contains real measurements from a large Wi-Fi campus network, which we use to train the ML model under study based on different strategies. Performance evaluation includes relevant aspects for the suitability of distributed learning operation in real use cases, including the predictive performance, the associated communication overheads, or the energy consumption. In particular, we prove that distributed learning can improve the predictive accuracy centralized ML solutions by up to 93% while reducing the communication overheads and the energy cost by 80%.

In view of the need to find novel means to utilize the unlicensed spectrum to meet the rising latency and reliability requirements of new applications, we propose a novel mechanism that allows devices to transmit anytime that a packet has to be delivered. The proposed mechanism, Contention-free with Power Adaptation (ConPA), aims to bypass the contention periods of current Listen-Before-Talk (LBT) approaches, which are the main source of unreliability in unlicensed technologies like Wi-Fi. To assess the feasibility of ConPA, we provide an analytical method based on Markov chains, which allows deriving relevant performance metrics, including throughput, airtime, and quality of transmissions. Using such a model, we study the performance of ConPA in various scenarios, and compare it to baseline channel access approaches like the Distributed Coordination Function (DCF) and the IEEE 802.11ax Overlapping Basic Service Set (OBSS) Packet Detect (PD)-based Spatial Reuse (SR). Our results prove the effectiveness of ConPA in reusing the space to offer substantial throughput gains with respect to the baselines (up to 76% improvement).

Blockchain promises to enhance distributed machine learning (ML) approaches such as federated learning (FL) by providing further decentralization, security, immutability, and trust, which are key properties for enabling collaborative intelligence in next-generation applications. Nonetheless, the intrinsic decentralized operation of peer-to-peer (P2P) blockchain nodes leads to an uncharted setting for FL, whereby the concepts of FL round and global model become meaningless, as devices' synchronization is lost without the figure of a central orchestrating server. In this paper, we study the practical implications of outsourcing the orchestration of FL to a democratic setting such as in a blockchain. In particular, we focus on the effects that model staleness and inconsistencies, endorsed by blockchains' modus operandi, have on the training procedure held by FL devices asynchronously. Using simulation, we evaluate the blockchained FL operation by applying two different ML models (ranging from low to high complexity) on the well-known MNIST and CIFAR-10 datasets, respectively, and focus on the accuracy and timeliness of the solutions. Our results show the high impact of model inconsistencies on the accuracy of the models (up to a ~35% decrease in prediction accuracy), which underscores the importance of properly designing blockchain systems based on the characteristics of the underlying FL application.

Enterprise Wi-Fi networks can greatly benefit from Artificial Intelligence and Machine Learning (AI/ML) thanks to their well-developed management and operation capabilities. At the same time, AI/ML-based traffic/load prediction is one of the most appealing data-driven solutions to improve the Wi-Fi experience, either through the enablement of autonomous operation or by boosting troubleshooting with forecasted network utilization. In this paper, we study the suitability and feasibility of adopting AI/ML-based load prediction in practical enterprise Wi-Fi networks. While leveraging AI/ML solutions can potentially contribute to optimizing Wi-Fi networks in terms of energy efficiency, performance, and reliability, their effective adoption is constrained to aspects like data availability and quality, computational capabilities, and energy consumption. Our results show that hardware-constrained AI/ML models can potentially predict network load with less than 20% average error and 3% 85th-percentile error, which constitutes a suitable input for proactively driving Wi-Fi network optimization.

Cellular traffic prediction is a crucial activity for optimizing networks in fifth-generation (5G) networks and beyond, as accurate forecasting is essential for intelligent network design, resource allocation and anomaly mitigation. Although machine learning (ML) is a promising approach to effectively predict network traffic, the centralization of massive data in a single data center raises issues regarding confidentiality, privacy and data transfer demands. To address these challenges, federated learning (FL) emerges as an appealing ML training framework which offers high accurate predictions through parallel distributed computations. However, the environmental impact of these methods is often overlooked, which calls into question their sustainability. In this paper, we address the trade-off between accuracy and energy consumption in FL by proposing a novel sustainability indicator that allows assessing the feasibility of ML models. Then, we comprehensively evaluate state-of-the-art deep learning (DL) architectures in a federated scenario using real-world measurements from base station (BS) sites in the area of Barcelona, Spain. Our findings indicate that larger ML models achieve marginally improved performance but have a significant environmental impact in terms of carbon footprint, which make them impractical for real-world applications., Comment: International Symposium on Federated Learning Technologies and Applications (FLTA), 2023

Multi-Access Point Coordination (MAPC) is becoming the cornerstone of the IEEE 802.11bn amendment, alias Wi-Fi 8. Among the MAPC features, Coordinated Spatial Reuse (C-SR) stands as one of the most appealing due to its capability to orchestrate simultaneous access point transmissions at a low implementation complexity. In this paper, we contribute to the understanding of C-SR by introducing an analytical model based on Continuous Time Markov Chains (CTMCs) to characterize its throughput and spatial efficiency. Applying the proposed model to several network topologies, we show that C-SR opportunistically enables parallel high-quality transmissions and yields an average throughput gain of up to 59% in comparison to the legacy 802.11 Distributed Coordination Function (DCF) and up to 42% when compared to the 802.11ax Overlapping Basic Service Set Packet Detect (OBSS/PD) mechanism.

Federated learning is one of the most appealing alternatives to the standard centralized learning paradigm, allowing a heterogeneous set of devices to train a machine learning model without sharing their raw data. However, it requires a central server to coordinate the learning process, thus introducing potential scalability and security issues. In the literature, server-less federated learning approaches like gossip federated learning and blockchain-enabled federated learning have been proposed to mitigate these issues. In this work, we propose a complete overview of these three techniques proposing a comparison according to an integral set of performance indicators, including model accuracy, time complexity, communication overhead, convergence time, and energy consumption. An extensive simulation campaign permits to draw a quantitative analysis considering both feedforward and convolutional neural network models. Results show that gossip federated learning and standard federated solution are able to reach a similar level of accuracy, and their energy consumption is influenced by the machine learning model adopted, the software library, and the hardware used. Differently, blockchain-enabled federated learning represents a viable solution for implementing decentralized learning with a higher level of security, at the cost of an extra energy usage and data sharing. Finally, we identify open issues on the two decentralized federated learning implementations and provide insights on potential extensions and possible research directions in this new research field.

Federated learning (FL), thanks in part to the emergence of the edge computing paradigm, is expected to enable true real-time applications in production environments. However, its original dependence on a central server for orchestration raises several concerns in terms of security, privacy, and scalability. To solve some of these worries, blockchain technology is expected to bring decentralization, robustness, and enhanced trust to FL. The empowerment of FL through blockchain (also referred to as FLchain), however, has some implications in terms of ledger inconsistencies and age of information (AoI), which are naturally inherited from the blockchain's fully decentralized operation. Such issues stem from the fact that, given the temporary ledger versions in the blockchain, FL devices may use different models for training, and that, given the asynchronicity of the FL operation, stale local updates (computed using outdated models) may be generated. In this paper, we shed light on the implications of the FLchain setting and study the effect that both the AoI and ledger inconsistencies have on the FL performance. To that end, we provide a faithful simulation tool that allows capturing the decentralized and asynchronous nature of the FLchain operation.

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.

Due to the increasing interest in blockchain technology for fostering secure, auditable, decentralized applications, a set of challenges associated with this technology need to be addressed. In this letter, we focus on the delay associated with Proof-of-Work (PoW)-based blockchain networks, whereby participants validate the new information to be appended to a distributed ledger via consensus to confirm transactions. We propose a novel end-to-end latency model based on batch-service queuing theory that characterizes timers and forks for the first time. Furthermore, we derive an estimation of optimum block size analytically. Endorsed by simulation results, we show that the optimal block size approximation is a consistent method that leads to close-to-optimal performance by significantly reducing the overheads associated with blockchain applications.

Motivated by the heterogeneous nature of devices participating in large-scale Federated Learning (FL) optimization, we focus on an asynchronous server-less FL solution empowered by blockchain technology. In contrast to mostly adopted FL approaches, which assume synchronous operation, we advocate an asynchronous method whereby model aggregation is done as clients submit their local updates. The asynchronous setting fits well with the federated optimization idea in practical large-scale settings with heterogeneous clients. Thus, it potentially leads to higher efficiency in terms of communication overhead and idle periods. To evaluate the learning completion delay of BC-enabled FL, we provide an analytical model based on batch service queue theory. Furthermore, we provide simulation results to assess the performance of both synchronous and asynchronous mechanisms. Important aspects involved in the BC-enabled FL optimization, such as the network size, link capacity, or user requirements, are put together and analyzed. As our results show, the synchronous setting leads to higher prediction accuracy than the asynchronous case. Nevertheless, asynchronous federated optimization provides much lower latency in many cases, thus becoming an appealing solution for FL when dealing with large datasets, tough timing constraints (e.g., near-real-time applications), or highly varying training data.

IEEE 802.11be networks (aka Wi-Fi 7) will have to cope with new bandwidth-hungry and low-latency services such as eXtended Reality and multi-party cloud gaming. With this goal in mind, transmit opportunity (TXOP) sharing between coordinated access points (APs) may contribute to alleviating inter-AP contention, hence increasing the overall network throughput. This paper evaluates two coordinated TXOP sharing strategies: coordinated time division multiple access (c-TDMA) and coordinated-TDMA with spatial reuse (c-TDMA/SR). We show that, while c-TDMA alone does not result in any significant improvement in terms of the WLAN throughput, it lays the groundwork to implement coordinated SR (c-SR) techniques. To evaluate the performance of c-TDMA/SR, we propose a fair scheduler able to select the best subset of parallel transmissions in WLAN deployments, as well as the appropriate power levels to be used by APs and stations (STAs), leading to maximum performance. The results obtained for c-TDMA/SR show significant throughput gains compared with c-TDMA, with values higher than 140% in 90% of the considered scenarios.

The innovation provided by network virtualization in 5G, together with standardization and openness boosted by the Open Radio Access Network (O-RAN) Alliance, has paved the way to a collaborative future in cellular systems, driven by flexible network sharing. Such advents are expected to attract new players like content providers and verticals, increasing competitiveness in the telecom market. However, scalability and trust issues are expected to arise, given the criticality of ownership traceability and resource exchanging in a sharing ecosystem. To address that, we propose integrating blockchain technology for enabling mobile operators and other players to exchange RAN resources (e.g., infrastructure) in the form of virtual network functions (VNF) autonomously and dynamically. Blockchain will provide automation, robustness, trustworthiness, and reliability to mobile networks, thus bringing confidence to open RAN environments. In particular, we define a novel O-RAN-based blockchain-enabled architecture that allows automating RAN sharing procedures through either auction or marketplace-based mechanisms. The potential advantages of the proposed solution are demonstrated through simulation results. The used simulation platform is openly released.

Blockchain (BC) technology can revolutionize the future of communications by enabling decentralized and open sharing networks. In this paper, we propose the application of BC to facilitate Mobile Network Operators (MNOs) and other players such as Verticals or Over-The-Top (OTT) service providers to exchange Radio Access Network (RAN) resources (e.g., infrastructure, spectrum) in a secure, flexible and autonomous manner. In particular, we propose a BC-enabled reverse auction mechanism for RAN sharing and dynamic users' service provision in Beyond 5G networks, and we analyze its potential advantages with respect to current service provisioning and RAN sharing schemes. Moreover, we study the delay and overheads incurred by the BC in the whole process, when running over both wireless and wired interfaces.

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.

Blockchain (BC) technology can revolutionize future networks by providing a distributed, secure, and unalterable way to boost collaboration among operators, users, and other stakeholders. Its implementations have traditionally been supported by wired communications, with performance indicators like the high latency introduced by the BC being one of the key technology drawbacks. However, when applied to wireless communications, the performance of BC remains unknown, especially if running over contention-based networks. In this paper, we evaluate the latency performance of BC technology when the supporting communication platform is wireless, specifically we focus on IEEE 802.11ax, for the use case of users' radio resource provisioning. For that purpose, we propose a discrete-time Markov model to capture the expected delay incurred by the BC. Unlike other models in the literature, we consider the effect that timers and forks have on the end-to-end latency.

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.

Lots of hopes have been placed on Machine Learning (ML) as a key enabler of future wireless networks. By taking advantage of large volumes of data, ML is expected to deal with the ever-increasing complexity of networking problems. Unfortunately, current networks are not yet prepared to support the ensuing requirements of ML-based applications in terms of data collection, processing, and output distribution. This article points out the architectural requirements that are needed to pervasively include ML as part of future wireless networks operation. Specifically, we look into Wireless Local Area Networks (WLANs), which, due to their nature can be found in multiple forms, ranging from cloud-based to edge-computing-like deployments. In particular, we propose to adopt the International Telecommunications Union (ITU) unified architecture for 5G and beyond. Based on ITU's architecture, we provide insights on the main requirements and the major challenges of introducing ML to the multiple modalities of WLANs. Finally, we showcase the superiority of the architecture through an ML-enabled use case for future networks.

Dealing with massively crowded scenarios is one of the most ambitious goals of next-generation wireless networks. With this goal in mind, the IEEE 802.11ax amendment includes, among other techniques, the Spatial Reuse (SR) operation. The SR operation encompasses a set of unprecedented techniques {that are expected to significantly boost Wireless Local Area Networks (WLANs) performance in dense environments}. In particular, the main objective of the SR operation is to maximize the utilization of the medium by increasing the number of parallel transmissions. Nevertheless, due to the novelty of the operation, its performance gains remain largely unknown. In this paper, we first provide a gentle tutorial of the SR operation included in the IEEE 802.11ax. Then, we analytically model SR and delve into the new kinds of MAC-level interactions among network devices. Finally, we provide a simulation-driven analysis to showcase the potential of SR in various deployments, comprising different network densities and traffic loads. Our results show that the SR operation can significantly improve the medium utilization, especially in scenarios under high interference conditions. Moreover, our results demonstrate the non-intrusive design characteristic of SR, which allows enhancing the number of simultaneous transmissions with a low impact on the environment. We conclude the paper by giving some thoughts on the main challenges and limitations of the IEEE 802.11ax SR operation, including research gaps and future directions.

In order to dynamically adapt the transmission bandwidth in wireless local area networks (WLANs), dynamic channel bonding (DCB) was introduced in IEEE 802.11n. It has been extended since then, and it is expected to be a key element in IEEE 802.11ax and future amendments such as IEEE 802.11be. While DCB is proven to be a compelling mechanism by itself, its performance is deeply tied to the primary channel selection, especially in high-density (HD) deployments, where multiple nodes contend for the spectrum. Traditionally, this primary channel selection relied on picking the most free one without any further consideration. In this paper, in contrast, we propose dynamic-wise (DyWi), a light-weight, decentralized, online primary channel selection algorithm for DCB that maximizes the expected WLAN throughput by considering not only the occupancy of the target primary channel but also the activity of the secondary channels. Even when assuming important delay costs due to primary switching, simulation results show a significant improvement both in terms of average delay and throughput.

The Spatial Reuse (SR) operation included in the IEEE 802.11ax-2020 (11ax) amendment aims at increasing the number of parallel transmissions in an Overlapping Basic Service Set (OBSS). However, many unknowns exist about the performance gains that can be achieved through SR. In this paper, we provide a brief introduction to the SR operation described in the IEEE 802.11ax (draft D4.0). Then, a simulation-based implementation is provided in order to explore the performance gains of the SR operation. Our results show the potential of using SR in different scenarios covering multiple network densities and traffic loads. In particular, we observe significant improvements on the channel utilization when applying SR with respect to the default configuration, thus allowing to increase the throughput and reduce the delay. Interestingly, the highest improvements provided by the SR operation are observed in the most pessimistic situations in terms of network density and traffic load.

Komondor is a wireless network simulator for next-generation wireless local area networks (WLANs). The simulator has been conceived as an accessible (ready-to-use) open source tool for research on wireless networks and academia. An important advantage of Komondor over other well-known wireless simulators lies in its high event processing rate, which is furnished by the simplification of the core operation. This allows outperforming the execution time of other simulators like ns-3, thus supporting large-scale scenarios with a huge number of nodes. In this paper, we provide insights into the Komondor simulator and overview its main features, development stages and use cases. The operation of Komondor is validated in a variety of scenarios against different tools: the ns-3 simulator and two analytical tools based on Continuous Time Markov Networks (CTMNs) and the Bianchi's DCF model. Results show that Komondor captures the IEEE 802.11 operation very similarly to ns-3. Finally, we discuss the potential of Komondor for simulating complex environments -- even with machine learning support -- in next-generation WLANs by easily developing new user-defined modules of code

Spatial Reuse (SR) has recently gained attention to maximize the performance of IEEE 802.11 Wireless Local Area Networks (WLANs). Decentralized mechanisms are expected to be key in the development of SR solutions for next-generation WLANs, since many deployments are characterized by being uncoordinated by nature. However, the potential of decentralized mechanisms is limited by the significant lack of knowledge with respect to the overall wireless environment. To shed some light on this subject, we show the main considerations and possibilities of applying online learning to address the SR problem in uncoordinated WLANs. In particular, we provide a solution based on Multi-Armed Bandits (MABs) whereby independent WLANs dynamically adjust their frequency channel, transmit power and sensitivity threshold. To that purpose, we provide two different strategies, which refer to selfish and environment-aware learning. While the former stands for pure individual behavior, the second one considers the performance experienced by surrounding networks, thus taking into account the impact of individual actions on the environment. Through these two strategies we delve into practical issues of applying MABs in wireless networks, such as convergence guarantees or adversarial effects. Our simulation results illustrate the potential of the proposed solutions for enabling SR in future WLANs. We show that substantial improvements on network performance can be achieved regarding throughput and fairness.

Next generation of wireless local area networks (WLANs) will operate in dense, chaotic and highly dynamic scenarios that in a significant number of cases may result in a low user experience due to uncontrolled high interference levels. Flexible network architectures, such as the software-defined networking (SDN) paradigm, will provide WLANs with new capabilities to deal with users' demands, while achieving greater levels of efficiency and flexibility in those complex scenarios. On top of SDN, the use of machine learning (ML) techniques may improve network resource usage and management by identifying feasible configurations through learning. ML techniques can drive WLANs to reach optimal working points by means of parameter adjustment, in order to cope with different network requirements and policies, as well as with the dynamic conditions. In this paper we overview the work done in SDN for WLANs, as well as the pioneering works considering ML for WLAN optimization. Finally, in order to demonstrate the potential of ML techniques in combination with SDN to improve the network operation, we evaluate different use cases for intelligent-based spatial reuse and dynamic channel bonding operation in WLANs using Multi-Armed Bandits.

Wireless local area networks (WLANs) are the most popular kind of wireless Internet connection because of their simplicity of deployment and operation. As a result, the number of devices accessing the Internet through WLANs such as laptops, smartphones, or wearables, is increasing drastically at the same time that applications' throughput requirements do. To cope with these challenges, channel bonding (CB) techniques are used for enabling higher data rates by transmitting in wider channels, thus increasing spectrum efficiency. However, important issues like higher potential co-channel and adjacent channel interference arise when bonding channels. This may harm the performance of the carrier sense multiple access (CSMA) protocol because of recurrent backoff freezing while making nodes more sensitive to hidden node effects. In this paper, we address the following point at issue: is it convenient for high-density (HD) WLANs to use wider channels and potentially overlap in the spectrum? First, we highlight key aspects of DCB in toy scenarios through a continuous time Markov network (CTMN) model. Then, by means of extensive simulations covering a wide range of traffic loads and access point (AP) densities, we show that dynamic channel bonding (DCB) - which adapts the channel bandwidth on a per-packet transmission - significantly outperforms traditional single-channel on average. Nevertheless, results also corroborate that DCB is more prone to generate unfair situations where WLANs may starve. Contrary to most of the current thoughts pushing towards non-overlapping channels in HD deployments, we highlight the benefits of allocating channels as wider as possible to WLANs altogether with implementing adaptive access policies to cope with the unfairness situations that may appear., Comment: arXiv admin note: text overlap with arXiv:1801.00594

In this paper, we discuss the effects on throughput and fairness of dynamic channel bonding (DCB) in spatially distributed high-density wireless local area networks (WLANs). First, we present an analytical framework based on continuous-time Markov networks (CTMNs) for depicting the behavior of different DCB policies in spatially distributed scenarios, where nodes are not required to be within the carrier sense range of each other. Then, we assess the performance of DCB in high-density IEEE 802.11ac/ax WLANs by means of simulations. We show that there may be critical interrelations among nodes in the spatial domain - even if they are located outside the carrier sense range of each other - in a chain reaction manner. Results also reveal that, while always selecting the widest available channel normally maximizes the individual long-term throughput, it often generates unfair situations where other WLANs starve. Moreover, we show that there are scenarios where DCB with stochastic channel width selection improves the latter approach both in terms of individual throughput and fairness. It follows that there is not a unique optimal DCB policy for every case. Instead, smarter bandwidth adaptation is required in the challenging scenarios of next-generation WLANs.

Next-generation wireless deployments are characterized by being dense and uncoordinated, which often leads to inefficient use of resources and poor performance. To solve this, we envision the utilization of completely decentralized mechanisms to enable Spatial Reuse (SR). In particular, we focus on dynamic channel selection and Transmission Power Control (TPC). We rely on Reinforcement Learning (RL), and more specifically on Multi-Armed Bandits (MABs), to allow networks to learn their best configuration. In this work, we study the exploration-exploitation trade-off by means of the $\varepsilon$-greedy, EXP3, UCB and Thompson sampling action-selection, and compare their performance. In addition, we study the implications of selecting actions simultaneously in an adversarial setting (i.e., concurrently), and compare it with a sequential approach. Our results show that optimal proportional fairness can be achieved, even when no information about neighboring networks is available to the learners and Wireless Networks (WNs) operate selfishly. However, there is high temporal variability in the throughput experienced by the individual networks, specially for $\varepsilon$-greedy and EXP3. These strategies, contrary to UCB and Thompson sampling, base their operation on the absolute experienced reward, rather than on its distribution. We identify the cause of this variability to be the adversarial setting of our setup in which the set of most played actions provide intermittent good/poor performance depending on the neighboring decisions. We also show that learning sequentially, even if using a selfish strategy, contributes to minimize this variability. The sequential approach is therefore shown to effectively deal with the challenges posed by the adversarial settings that are typically found in decentralized WNs.

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., Comment: Conference