Dynamic Spectrum Access Scheme of Joint Power Control in Underlay Mode Based on Deep Reinforcement Learning
Xiping Chen, Xianzhong Xie, Zhaoyuan Shi, Zishen Fan · 2020
With the increasing complexity of wireless networks and the increasing shortage of spectrum resources, a novel dynamic spectrum access (DSA) solution is urgently needed. For complex and dynamic cognitive radio networks (CRN), this paper proposes a joint DSA and power control scheme based on deep reinforcement learning (DRL). In order to improve the convergence speed of the algorithm, the DRL is improved to a hierarchical DRL, centralized DSA is implemented through CBS, and distributed power control is implemented at each secondary user (SU). Sufficient simulation experiments show that the proposed algorithm has faster convergence speed and lower packet loss.