Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance With Machine Learning

Abstract

Wireless local area networks (WLANs) empowered by IEEE 802.11 (Wi-Fi) hold a dominant position in providing Internet access thanks to their freedom of deployment and configuration as well as the existence of affordable and highly interoperable devices. The Wi-Fi community is currently deploying Wi-Fi 6 and developing Wi-Fi 7, which will bring higher data rates, better multi-user and multi-AP support, and, most importantly, improved configuration flexibility. These technical innovations, including the plethora of configuration parameters, are making next-generation WLANs exceedingly complex as the dependencies between parameters and their joint optimization usually have a non-linear impact on network performance. The complexity is further increased in the case of dense deployments and coexistence in shared bands. While classical optimization approaches fail in such conditions, machine learning (ML) is able to handle complexity. Much research has been published on using ML to improve Wi-Fi performance and solutions are slowly being adopted in existing deployments. In this survey, we adopt a structured approach to describe the various Wi-Fi areas where ML is applied. To this end, we analyze over 250 papers in the field, providing readers with an overview of the main trends. Based on this review, we identify specific open challenges and provide general future research directions.

AI-Enabled Reliable QoS in Multi-RAT Wireless IoT Networks: Prospects, Challenges, and Future Directions

“…The Networking research community has reviewed and surveyed many works employing AI & ML in wireless networks research. There are various surveys done on application of AI & ML in wireless networks [41], [42], [43] and WiFi networks [36], [44]. These surveys are focusing on AI & ML employment in resource allocation, user association, mobility management, network security and anomaly detection etc.…”

“…CNNs have seen great progress in the field of computer vision and completely revolutionized it as they have the ability to extract complex features from underlying data for a given objective. Similarly, DRL, LSTM and GNN algorithms have seen an upward trend to solve complex optimization problems in wireless networks [29], [41], [44], [59], [60]. A brief review of AI & ML algorithms employment in CLD/CLO in wireless networks towards meeting QoS requirements is given in Table 2.…”

“…Wireless Networks have seen a massive increase in employment of AI & ML for performance enhancement in almost all domains. A number of comprehensive surveys [29], [41], [44], [59], [60] have been published to cover the AI & ML application in wireless networks. Various ML data related challenges are already identified and require research efforts to cater heterogeneity in wireless network data.…”

“…AI & ML have been employed in every layer of network protocol stack from the application layer to the physical layer [44], [41], [60]. Network researchers have mostly employed AI & ML to one or two problems at a time like channel-aware user association, load balancing, congestion control and spectrum allocation etc.…”

Improving IEEE 802.11ax UORA Performance: Comparison of Reinforcement Learning and Heuristic Approaches

“…None of the above research uses ML methods, although the application of reinforcement learning (RL) to improve UORA operation is suggested as future work by Kim et al [13]. In fact, with the proliferation of the use of ML solutions to improve Wi-Fi performance [17], extending UORA with ML is the logical next step. Thus inspired, in this paper, we present an RL-based OBO procedure (RL-OBO) to adjust the UORA random access backoff operation to the congestion level of the shared channel.…”