Performance Analysis of DRL-Based IRS-Aided Short Packet Communication With Practical Phase Shift Model and Statistical CSI
Xiaoliang Gao, Lei Yuan, Yi Guo, Jianbin Chen · IEEE Wireless Communications Letters · 2025
Most works on reflecting-only intelligent reflecting surface (IRS) are based on the ideal phase shift model (IPSM), which assumes that the reflection amplitude is independent of the phase shift. However, due to hardware limitations, practical IRS generally follows the practical phase shift model (PPSM), where the reflection amplitude is related to the phase shift. This paper analyzes the average block error rate (BLER) of PPSM-based IRS aided short-packet communication (SPC) using statistical channel state information (CSI) over Rician fading. Because the optimal continuous phase shifts at the PPSM-based IRS are difficult to be explicitly solved, we first propose a deep deterministic policy gradient (DDPG) based algorithm to optimize the phase shift design. Then, we derive the average BLER of the considered system. Finally, numerical results verify the effectiveness of the proposed DDPG-based phase shift design. They also show that, different from the IPSM-based IRS, the optimal phase shifts at the PPSM-based IRS are related to the Rician factors.