基于双向强化学习与动态码率调节的无线mesh网络协议

摘要

针对现有无线mesh网络协议的用户体验质量(QoE)较差的问题,提出一种基于双向强化学习与动态码率调节的无线mesh网络协议.设计了兼容不同服务类型的无线mesh网络QoE度量框架和基于双向强化学习的无线mesh网络路由协议,并结合QoE感知的差异化报文调度策略与数据流源节点码率动态调节算法进一步优化终端用户的QoE质量.基于NS-2仿真平台的对比实验结果显示,协议可明显地提高无线mesh网络的QoE指标,同时具有较低的控制开销.%Concerned the problem that the existing wireless mesh network(WMN) protocols show pool performance in quality of experience(QoE),this paper proposed a bidirectional reinforcement learning and dynamic data rate adjustment based wireless WMN protocol.Firstly,it designed different types of services compatible QoE measure framework of WMN.Then,it designed bidirectional reinforcement learning based WMN routing protocol.Lastly,it combined QoE aware differential packets scheduling strategy and dynamic adjustment for data rate in source nodes of data flow to optimize the QoE quality of terminal user further.NS-2 simulation platform based compared experimental results show that the proposed protocol improves the QoE quality of wireless mesh network obviously,at the same time realizes a lower control overhead.