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.

In this survey we attempt to describe the Quality of Service (QoS) mechanisms employed by Medium Access Control (MAC) protocols designed for ad-hoc networks. We begin with background information: an overview of the related work, the definition of QoS and QoS-related metrics, a general description of contention-free and contention-based protocols for wireless networks, a discussion of issues affecting QoS provisioning in ad-hoc networks, as well as a novel classification of the QoS mechanisms. Then, each mechanism is briefly explained and implementation examples from different protocols are provided. Furthermore, a separate section is devoted to the completed and ongoing standardization work in the field. Afterwards, an extensive comparison of salient features, advantages and disadvantages of all described MAC mechanisms is given in order to guide future protocol designers. Finally, we comment on the most probable future research directions. Based on the presented survey, we observe that QoS provisioning is not only challenging but also a significant contemporary research problem. The protocol designs presented in the literature usually involve trade-offs between certain metrics, and currently there is no ideal solution which deals with all the issues affecting ad-hoc networks. Therefore, we trust that this survey will be of great help to designers of future QoS-aware protocols.

IEEE 802.11ax stations can use multi-user (MU) uplink OFDMA-based random access (UORA) to improve per-station throughput in dense deployments in comparison to legacy IEEE 802.11 single-user access. Unfortunately, UORA suffers from a high collision probability and low efficiency under high contention. In this paper, we address this problem by modifying the UORA backoff selection method. The proposed solution allows an access point to adjust the OFDMA random access backoff (OBO) countdown rate to decrease the probability of uplink transmission failures. The implemented changes considerably improve UORA performance. We show through extensive simulations, that the proposed efficient OFDMA random access backoff (E-OBO) ensures throughput, efficiency, and collision probability close to optimal and outperforms state-of-the-art solutions.

Recent advances in wireless networking technologies are leading toward the proliferation of novel home network applications. However, the landscape of emerging scenarios is fragmented due to their varying technological requirements and the heterogeneity of current wireless technologies. We argue that the development of flexible software-defined wireless architectures, including such efforts as the wireless MAC processor, coupled with SDN concepts, will enable the support of both emerging and future home applications. In this article, we first identify problems with managing current home networks composed of separate network segments governed by different technologies. Second, we point out the flaws of current approaches to provide interoperability of these technologies. Third, we present a vision of a software-defined multi-technology network architecture (SDN@home) and demonstrate how a future home gateway (SDN controller) can directly and dynamically program network devices. Finally, we define a new type of flexibility enabled by SDN@home. Wireless protocols and features are no longer tied to specific technologies but can be used by general-purpose wireless SDN devices. This permits satisfaction of the requirements demanded by home owners and service providers under heterogeneous network conditions.