Deep Reinforcement Learning for Practical Phase Shift Optimization in RIS-aided MISO URLLC Systems

TL;DR

This paper introduces a deep reinforcement learning approach using TD3 to optimize phase shifts, beamforming, and channel blocklength in RIS-aided URLLC systems, significantly enhancing data rates in practical non-ideal conditions.

Contribution

It presents a novel DRL-based method for joint optimization in RIS-aided URLLC systems considering non-ideal RIS characteristics, outperforming traditional approaches.

Findings

Optimizing RIS phase shifts and beamforming improves total FBL rate.

The TD3-based method outperforms conventional optimization techniques.

Non-ideal RIS with non-linear amplitude response causes performance loss, but optimization mitigates this.

Abstract

We study the joint active/passive beamforming and channel blocklength (CBL) allocation in a non-ideal reconfigurable intelligent surface (RIS)-aided ultra-reliable and low-latency communication (URLLC) system. The considered scenario is a finite blocklength (FBL) regime and the problem is solved by leveraging a novel deep reinforcement learning (DRL) algorithm named twin-delayed deep deterministic policy gradient (TD3). First, assuming an industrial automation system with multiple actuators, the signal-to-interference-plus-noise ratio and achievable rate in the FBL regime are identified for each actuator in terms of the phase shift configuration matrix at the RIS. Next, the joint active/passive beamforming and CBL optimization problem is formulated where the objective is to maximize the total achievable FBL rate in all actuators, subject to non-linear amplitude response at the RIS elements, BS transmit power budget, and total available CBL. Since the amplitude response equality constraint is highly non-convex and non-linear, we resort to employing an actor-critic policy gradient DRL algorithm based on TD3. The considered method relies on interacting RIS with the industrial automation environment by taking actions which are the phase shifts at the RIS elements, CBL variables, and BS beamforming to maximize the expected observed reward, i.e., the total FBL rate. We assess the performance loss of the system when the RIS is non-ideal, i.e., with non-linear amplitude response, and compare it with ideal RIS without impairments. The numerical results show that optimizing the RIS phase shifts, BS beamforming, and CBL variables via the proposed TD3 method is highly beneficial to improving the network total FBL rate as the proposed method with deterministic policy outperforms conventional methods.