Millimeter Wave Communications with an Intelligent Reflector: Performance Optimization and Distributional Reinforcement Learning

TL;DR

This paper introduces a novel framework for optimizing millimeter wave multi-user communication using an intelligent reflector, employing channel estimation and distributional reinforcement learning to enhance downlink capacity.

Contribution

It develops a real-time channel estimation method and a distributional reinforcement learning approach for IR reflection optimization, improving downlink rates under perfect and imperfect CSI conditions.

Findings

Over 30% increase in downlink sum-rate with the proposed method.

Doubling of downlink sum-rate compared to fixed IR schemes.

QR-DRL improves rate prediction accuracy and increases downlink rate by 10%.

Abstract

In this paper, a novel framework is proposed to optimize the downlink multi-user communication of a millimeter wave base station, which is assisted by a reconfigurable intelligent reflector (IR). In particular, a channel estimation approach is developed to measure the channel state information (CSI) in real-time. First, for a perfect CSI scenario, the precoding transmission of the BS and the reflection coefficient of the IR are jointly optimized, via an iterative approach, so as to maximize the sum of downlink rates towards multiple users. Next, in the imperfect CSI scenario, a distributional reinforcement learning (DRL) approach is proposed to learn the optimal IR reflection and maximize the expectation of downlink capacity. In order to model the transmission rate's probability distribution, a learning algorithm, based on quantile regression (QR), is developed, and the proposed QR-DRL method is proved to converge to a stable distribution of downlink transmission rate. Simulation results show that, in the error-free CSI scenario, the proposed approach yields over 30% and 2-fold increase in the downlink sum-rate, compared with a fixed IR reflection scheme and direct transmission scheme, respectively. Simulation results also show that by deploying more IR elements, the downlink sum-rate can be significantly improved. However, as the number of IR components increases, more time is required for channel estimation, and the slope of increase in the IR-aided transmission rate will become smaller. Furthermore, under limited knowledge of CSI, simulation results show that the proposed QR-DRL method, which learns a full distribution of the downlink rate, yields a better prediction accuracy and improves the downlink rate by 10% for online deployments, compared with a Q-learning baseline.