Deep Deterministic Policy Gradient for Relay Selection and Power Allocation in Cooperative Communication Network
share
Cooperative communication is an effective approach to improve spectrum utilization. In this letter, we study the outage probability minimizing problem in a two-hop cooperative communication scenario, to improve the Quality-of-Service of the system through appropriate relay selection and power allocation. We propose a deep deterministic policy gradient based learning framework, which can find an optimal solution for the problem without any assumption or prior knowledge of channel state information. The proposed method can deal with continuous action space, which is more advanced than other existing reinforcement learning (RL) based approaches. Simulation results reveal that the proposed method outperforms traditional RL method, which can improve the communication success rate by about 5
READ FULL TEXT