Machine learning-inspired hybrid precoding with low-resolution phase shifters for intelligent reflecting surface (IRS) massive MIMO systems with limited RF chains

Abstract

The number of bits required in phase shifters (PS) in hybrid precoding (HP) has a significant impact on sum-rate, spectral efficiency (SE), and energy efficiency (EE). The space and cost constraints of a realistic massive multiple-input multiple-output (MIMO) system limit the number of antennas at the base station (BS), limiting the throughput gain promised by theoretical analysis. This paper demonstrates the effectiveness of employing an intelligent reflecting surface (IRS) to enhance efficiency, reduce costs, and conserve energy. Particularly, an IRS consists of an extensive number of reflecting elements, wherein every individual element has a distinct phase shift. Adjusting each phase shift and then jointly optimizing the source precoder at BS and selecting the optimal phase-shift values at IRS will allow us to modify the direction of signal propagation. Additionally, we can improve sum-rate, EE, and SE performance. Furthermore, we proposed an energy-efficient HP at BS in which the analog component is implemented using a low-resolution PS rather than a high-resolution PS. Our analysis reveals that the performance gets better as the number of bits increases. We formulate the problem of jointly optimizing the source precoder at BS and the reflection coefficient at IRS to improve the system performance. However, because of the non-convexity and high complexity of the formulated problem. Inspired by the cross-entropy (CE) optimization technique used in machine learning, we proposed an adaptive cross-entropy (ACE) 1-3-bit PS-based optimization HP approach for this new architecture. Moreover, our analysis of energy consumption revealed that increasing the low-resolution bits can significantly reduce power consumption while also improving performance parameters such as SE, EE, and sum-rate. The simulation results are presented to validate the proposed algorithm, which highlights the IRS efficiency gains to boost sum-rate, SE, and EE compared to previously reported methods.