J4 ›› 2015, Vol. 42 ›› Issue (6): 179-183.doi: 10.3969/j.issn.1001-2400.2015.06.030

• Original Articles • Previous Articles     Next Articles

Optimization algorithm for dynamic spectrum access based on Q-learning in cognitive radio networks

HUANG Ying1;YAN Dingyu2;LI Nan2   

  1. (1. School of Mathematics and Computer Engineering, Xi'an Univ. of Arts and Science, Xi'an  710068, China;
    2. State Key Lab. of Integrated Service Networks, Xidian Univ., Xi'an  710071, China)
  • Received:2014-07-16 Online:2015-12-20 Published:2016-01-25
  • Contact: HUANG Ying E-mail:yhuang@xidian.edu.cn

Abstract:

Under the centralized cognitive radio network architecture, considering the network performance and users' demands. We propose an optimized dynamic spectrum access algorithm based on Q-learning. The proposed algorithm has two steps, which consist of user request according to Q-learning and the application process according to the overall system performance. Simulation results show that the proposed scheme can improve the overall system performance obviously, and that the user requirements could be satisfied at the same time.

Key words: cognitive radio networks, dynamic spectrum access, Q-learning