应用科学学报 ›› 2017, Vol. 35 ›› Issue (3): 317-325.doi: 10.3969/j.issn.0255-8297.2017.03.005

• 通信工程 • 上一篇    下一篇

基于强化学习的M2M网络自适应媒体接入控制协议

徐昶, 王聪, 刘灵雅, 李宁   

  1. 解放军理工大学 通信工程学院, 南京 210007
  • 收稿日期:2016-01-19 修回日期:2016-11-19 出版日期:2017-05-30 发布日期:2017-05-30
  • 通信作者: 王聪,副教授,研究方向:计算机网络,E-mail:dolphin6488@163.com E-mail:dolphin6488@163.com
  • 基金资助:

    国家自然科学基金(No.61371123)资助

Self-Adaption MAC Protocol for M2M Network Based on Q-Learning

XU Chang, WANG Cong, LIU Ling-ya, LI Ning   

  1. Institute of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China
  • Received:2016-01-19 Revised:2016-11-19 Online:2017-05-30 Published:2017-05-30

摘要:

提出了一种针对机器与机器通信网络中数据收集业务的自适应媒体接入控制(medium access control,MAC)层协议,即强化学习混合MAC(Q-learning hybrid MAC,QH-MAC)。这种协议在混合分组MAC(hybrid group MAC,HG-MAC)的基础上增加了基于Q-learning的自适应学习机制,其中心节点可以根据网络状况动态调节竞争时段的时长,因此提高了网络的灵活性和适应性。通过OPNET仿真,将QH-MAC与HG-MAC、多时分址、载波监听多路访问/冲突避免性能进行了比较,结果表明QH-MAC在数据传输速率、能量效率和信道利用率上具有优势。

关键词: 强化学习, M2M网络, 媒体接入控制, 能量效率

Abstract:

An adaptive medium access control (MAC) protocol Q-learning hybrid MAC (QH-MAC) is proposed for data collection application in machine-to-machine (M2M) networks. The QH-MAC enhances hybrid group MAC (HG-MAC) with an adaptive Q-learning based mechanism, in which the central node dynamically adjusts the COP duration according to the network load. The adaptive learning mechanism improves flexibility and the adaptability of the MAC protocol. QH-MAC is compared with carrier sense multiple access with collision avoidance (CSMA/CA), time division multiple address (TDMA) and HG-MAC by optimized network engineering tool (OPNET) simulations. The results show that HG-MAC is better than the others in terms of data rate, energy efciency and channel utilization.

Key words: medium access control (MAC), energy efciency, Q-learning, machine-tomachine (M2M) network

中图分类号: