The potential applications of deep learning (DL) to the media access control (MAC) layer of wireless local area networks (WLANs) have already been progressively acknowledged due to their novel features for future communications. Their new features challenge conventional communications theories with more sophisticated artificial intelligence (AI)-based theories. DL has been extensively proposed for the MAC layer of WLANs in various research areas, such as deployment of cognitive radio and communications networks. Deep reinforcement learning (DRL) is one DL technique that is motivated by the behaviorist sensibility and control philosophy, where a learner can achieve an objective by interacting with the environment. Next-generation dense WLANs like the IEEE 802.11ax high-efficiency WLAN (HEW) are expected to confront ultra-dense diverse user environments and radically new applications. To satisfy the diverse requirements of such dense WLANs, it is anticipated that prospective WLANs will freely access the best channel resources with the assistance of self-scrutinized wireless channel condition inference. Such intelligence is only possible with the introduction of DL techniques in future WLANs. Therefore, in this paper, we propose reinforcement learning (RL) as an intelligent paradigm for MAC layer resource allocation in dense WLANs. One of the RL models, Q-learning (QL), is used to optimize the performance of channel observation–based MAC protocols in dense wireless networks. An intelligent QL-based resource allocation (iQRA) mechanism is proposed for MAC layer channel access in dense WLANs. Simulation results indicate that the proposed intelligent paradigm learns diverse WLAN environments and optimizes performance, compared to conventional non-intelligent MAC protocols. The performance of the proposed iQRA mechanism is evaluated in diverse WLAN network environments with throughput, channel access delay, and fairness as performance metrics.

Recently, the Wi-Fi Alliance announced a new Wi-Fi standard known as IEEE 802.11ah (or Wi-Fi HaLow) to efficiently support Internet of Things (IoT) applications. However, the existing registration method under IEEE 802.11ah, based on carrier-sense multiple access with collision avoidance (CSMA/CA), was analyzed as not efficient enough for registration of large-scale machine-to-machine (M2M) communications where massive numbers of devices try to access a single, centralized access point (AP). In this paper, we propose a hybrid slotted-CSMA/CA–time-division multiple access (TDMA) (HSCT) medium access control (MAC) protocol for efficient massive registration of IoT devices (up to 8000) in M2M networks. We focus on situations where large numbers of M2M devices simultaneously try to register at a single, centralized AP. In the proposed HSCT, contention-based slotted-CSMA/CA allows devices to send an authentication request via randomly selected backoff slots, whereas contention-free TDMA permits those devices to send/receive the subsequent association request/association response via an individually allocated TDMA slot. In addition, a centralized authentication control (CAC)-based mechanism with modified algorithms for optimal selection of CAC parameters and the slotted fixed-window CSMA protocol with Sift geometric probability distribution are used to mitigate severe contention between massive registrations upon network (re-)initialization from an AP reboot. This paper also analyzes the performance of the proposed scheme and determines the optimal configuration to enhance registration performance. Simulation results demonstrate that the proposed HSCT MAC protocol achieves substantial improvement, compared to contention-free transmission, a combined authentication/association scheme, and the conventional IEEE 802.11ah with CSMA/CA.

The IEEE 802.11ax high-efficiency wireless local area network (HEW) is promising as a foundation for evolving the fifth-generation (5G) radio access network on unlicensed bands (5G-U). 5G-U is a continued effort toward rich ubiquitous communication infrastructures, promising faster and reliable services for the end user. HEW is likely to provide four times higher network efficiency even in highly dense network deployments. However, the current wireless local area network (WLAN) itself faces huge challenge of efficient radio access due to its contention-based nature. WLAN uses a carrier sense multiple access with collision avoidance (CSMA/CA) procedure in medium access control (MAC) protocols, which is based on a binary exponential backoff (BEB) mechanism. Blind increase and decrease of the contention window in BEB limits the performance of WLAN to a limited number of contenders, thus affecting end-user quality of experience. In this paper, we identify future use cases of HEW proposed for 5G-U networks. We use a self-scrutinized channel observation-based scaled backoff (COSB) mechanism to handle the high-density contention challenges. Furthermore, a recursive discrete-time Markov chain model (R-DTMC) is formulated to analyze the performance efficiency of the proposed solution. The analytical and simulation results show that the proposed mechanism can improve user experience in 5G-U networks.

Carrier sense multiple access with collision avoidance(CSMA/CA) in current IEEE 802.11 wireless local area networks (WLANs) uses a uniformly distributed binary exponential backoff (BEB) mechanism that is mainly based upon exponential increases of the contention window (CW) to avoid repeated collisions. After each consecutive collision, the CW is doubled until it reaches the maximum value. Under dense conditions, however, the blind selection of the CW greatly reduces throughput, whereas under sparse conditions with smaller number of contending stations, the blind exponential increase of the CW for collision avoidance causes unnecessarily long delays. Therefore, it fails to achieve high efficiency in both dense and sparse environments with the current BEB mechanism. In this paper, we propose a cognitive backoff (CB) mechanism that adaptively determines the CW to provide efficient collision avoidance with high throughput and low delay under both dense and sparse conditions. In the proposed CB mechanism, the measured conditional collision probability and the number of backoff stages determine the CW. A performance analysis with an event-driven simulator, NS3, reveals that the proposed CB can achieve higher throughput and lower delay than the BEB, without much implementation complexity while preserving fairness.

The IEEE 802.11ah Wi-Fi HaLow allows thousands of devices being connected to a single access point (AP) with several improved functionalities compared to existing WiFi, such as restricted access window (RAW), target wake time (TWT), and traffic indication map (TIM). However, such functionalities are applicable only after successful registration process (exchanges of authentication and association information). In the registration process, a large number IoT devices are simultaneously trying to connect to a single centralized AP and inevitably imports severe contentions that bring a long registration time. In IEEE 802.11ah standards, the problems have been addressed through Centralized Authentication Control (CAC) and Distributed Authentication Control (DAC) protocols. Both CAC and DAC are proposed to reduce severe contentions by allowing an optimal number of devices requests for the registrations. However, the standard does not define the way to select the optimal operational parameters. In this paper, we evaluate and compare the performances of CAC and DAC protocols and provide two modified CAC-based algorithms that achieve substantial improvement overall existing IEEE 802.11ah schemes to reduce the registration time. ¹