English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The exponential increase of wireless devices with highly demanding servicessuch as streaming video, gaming and others has imposed several challenges toWireless Local Area Networks (WLANs). In the context of Wi-Fi, IEEE 802.11axbrings high-data rates in dense user deployments. Additionally, it comes withnew flexible features in the physical layer as dynamic Clear-Channel-Assessment(CCA) threshold with the goal of improving spatial reuse (SR) in response toradio spectrum scarcity in dense scenarios. In this paper, we formulate theTransmission Power (TP) and CCA configuration problem with an objective ofmaximizing fairness and minimizing station starvation. We present four maincontributions into distributed SR optimization using Multi-Agent Multi-ArmedBandits (MAMABs). First, we propose to reduce the action space given the largecardinality of action combination of TP and CCA threshold values per AccessPoint (AP). Second, we present two deep Multi-Agent Contextual MABs (MA-CMABs),named Sample Average Uncertainty (SAU)-Coop and SAU-NonCoop as cooperative andnon-cooperative versions to improve SR. In addition, we present an analysiswhether cooperation is beneficial using MA-MABs solutions based on thee-greedy, Upper Bound Confidence (UCB) and Thompson techniques. Finally, wepropose a deep reinforcement transfer learning technique to improveadaptability in dynamic environments. Simulation results show that cooperationvia SAU-Coop algorithm contributes to an improvement of 14.7% in cumulativethroughput, and 32.5% improvement of PLR when compared with no cooperationapproaches. Finally, under dynamic scenarios, transfer learning contributes tomitigation of service drops for at least 60% of the total of users.

Cooperate or not Cooperate: Transfer Learning with Multi-Armed Bandit for Spatial Reuse in Wi-Fi