Proximal Policy Optimization Based Continuous Intelligent Power Control in Cognitive Radio Network
Fan Zishen, Xie Xianzhong, Zhaoyuan Shi, Xiping Chen · 2020
The purpose of this paper is to develop a learning-based power control method for the secondary user (SU) in order to effectively share the common spectrum with the primary users (PUs). However, deep reinforcement learning (DRL) methods applied to cognitive radio (CR) are mostly value-based and they can only deal with discrete action spaces, while full search for optimal actions in continuous action spaces is usually not feasible. We propose a novel proximal policy optimization (PPO) based algorithm that allows the SU to realize continuous power control. Simulation results show that the proposed algorithm can effectively control the SU's power to share the spectrum resources of PUs without affecting the normal communication of the PUs.