ReinWiFi: A Reinforcement-Learning-Based Framework for the Application-Layer QoS Optimization of WiFi Networks

Qianren Li, Bojie Lv, Yuncong Hong, and Rui Wang*
Southern University of Technology and Science
*Corresponding author: Prof. Rui Wang (wang.r@sustech.edu.cn)
Paper Code arXiv

This is an example of the proposed ReinWiFi framework's performance. The left graph visualizes the transmission latency, while the right plots the change in RTT and actions. Each UE initially follows the standard EDCA, with the scheduling parameters rate and CW denoted as 0. The proposed ReinWiFi framework is activated to optimize the QoS in the vision of a significant RTT increase.

Abstract

In this paper, a reinforcement-learning-based scheduling framework is proposed and implemented to optimize the application-layer quality-of-service (QoS) of a practical wireless local area network (WLAN) suffering from unknown interference. Particularly, application-layer tasks of file delivery and delay-sensitive communication, e.g., screen projection, in a WLAN with enhanced distributed channel access (EDCA) mechanism, are jointly scheduled by adjusting the contention window sizes and application-layer throughput limitation, such that their QoS, including the throughput of file delivery and the round trip time of the delay-sensitive communication, can be optimized. Due to the unknown interference and vendor-dependent implementation of the network interface card, the relation between the scheduling policy and the system QoS is unknown. Hence, a reinforcement learning method is proposed, in which a novel Q-network is trained to map from the historical scheduling parameters and QoS observations to the current scheduling action. It is demonstrated on a testbed that the proposed framework can achieve a significantly better QoS than the conventional EDCA mechanism.

BibTeX

@misc{li2024reinwifi,
        title={ReinWiFi: A Reinforcement-Learning-Based Framework for the Application-Layer QoS Optimization of WiFi Networks}, 
        author={Qianren Li and Bojie Lv and Yuncong Hong and Rui Wang},
        year={2024},
        eprint={2405.03526},
        archivePrefix={arXiv},
        primaryClass={cs.NI}
  }