Dynamic Spectrum Access Based on Improved SARSA Algorithm
Xiaofei Liao, Dequan Wu, Yang Wang · IOP Conference Series Materials Science and Engineering · 2020
Abstract Dynamic spectrum access is the core technology of cognitive radio, accurate spectrum access can effectively alleviate the shortage of spectrum resources and realize the "secondary utilization"of spectrum resources. For this reason, this paper proposes a dynamic spectrum access based on improved Sarsa algorithm. The algorithm uses a simulated annealing strategy instead of the ε-greedy strategy in action selection, which can effectively overcome the problem of the traditional Sarsa algorithm falling into a local optimum. Simulation experiments show that the algorithm proposed in this paper can effectively improve the throughput of cognitive users and reduce the probability of collision with the main user, what’s more, it also has a significant increase in speed.