Enhancing WiFi Multiple Access Performance with Federated Deep Reinforcement Learning

TL;DR

This paper introduces a federated deep reinforcement learning-based MAC protocol that significantly improves WiFi network throughput and fairness in dense user scenarios compared to traditional methods.

Contribution

It proposes a novel federated deep reinforcement learning approach with a Monte Carlo reward update for enhanced WiFi access performance.

Findings

20% throughput improvement over DCF

5% throughput gain over RTS/CTS-based DCF

Ensures fairness among users in dense scenarios

Abstract

Carrier sensing multiple access/collision avoidance (CSMA/CA) is the backbone MAC protocol for IEEE 802.11 networks. However, tuning the binary exponential back-off (BEB) mechanism of CSMA/CA in user-dense scenarios so as to maximize aggregate throughput still remains a practically essential and challenging problem. In this paper, we propose a new and enhanced multiple access mechanism based on the application of deep reinforcement learning (DRL) and Federated learning (FL). A new Monte Carlo (MC) reward updating method for DRL training is proposed and the access history of each station is used to derive a DRL-based MAC protocol that improves the network throughput vis-a-vis the traditional distributed coordination function (DCF). Further, federated learning (FL) is applied to achieve fairness among users. The simulation results showcase that the proposed federated reinforcement multiple access (FRMA) performs better than basic DCF by 20% and DCF with request-to-send/clear-to-send (RTS/CTS) by 5% while guaranteeing the fairness in user-dense scenarios.