7. Reinforcement Learning for Distributed Power Control and Channel Access in Cognitive Wireless Mesh Networks

  1. David Grace1 and
  2. Honggang Zhang2
  1. Xianfu Chen,
  2. Zhifeng Zhao and
  3. Honggang Zhang

Published Online: 24 JUL 2012

DOI: 10.1002/9781118360316.ch7

Cognitive Communications: Distributed Artificial Intelligence (DAI), Regulatory Policy & Economics, Implementation

Cognitive Communications: Distributed Artificial Intelligence (DAI), Regulatory Policy & Economics, Implementation

How to Cite

Chen, X., Zhao, Z. and Zhang, H. (2012) Reinforcement Learning for Distributed Power Control and Channel Access in Cognitive Wireless Mesh Networks, in Cognitive Communications: Distributed Artificial Intelligence (DAI), Regulatory Policy & Economics, Implementation (eds D. Grace and H. Zhang), John Wiley & Sons, Ltd, Chichester, UK. doi: 10.1002/9781118360316.ch7

Editor Information

  1. 1

    Department of Electronics, University of York, UK

  2. 2

    Department of Information Science and Electronic Engineering, Zhejiang University, China

Author Information

  1. Department of Information Science and Electronic Engineering, Zhejiang University, China

Publication History

  1. Published Online: 24 JUL 2012
  2. Published Print: 31 AUG 2012

ISBN Information

Print ISBN: 9781119951506

Online ISBN: 9781118360316

SEARCH

Keywords:

  • RL for distributed power control, in CogMesh;
  • CogMesh, self-organized/self-configured network architecture;
  • CogMesh framework, two major technical issues;
  • resource allocation in CogMesh, stochastic learning process;
  • stochastic power allocation, performance balancing competing objectives;
  • conjecture-based multi-agent Q-learning algorithm;
  • CogMesh, and problem of opportunistic spectrum access;
  • distributed learning algorithms and dynamic conjectures, OSA in CogMesh;
  • e-greedy method, single-/multi-agent learning algorithms for balancing

Summary

This chapter contains sections titled:

  • Introduction

  • Applying Reinforcement Learning to Distributed Power Control and Channel Access

  • Future Challenges

  • Conclusions

  • References