Joint Optimization of UAV-Carried IRS for Urban Low Altitude mmWave Communications with Deep Reinforcement Learning

TL;DR

This paper proposes a deep reinforcement learning approach to optimize UAV-carried IRS for enhancing low altitude mmWave communications in urban environments, improving signal robustness and energy efficiency.

Contribution

It introduces a novel joint optimization framework for UAV trajectory and IRS phase shifts using deep reinforcement learning in urban low altitude mmWave scenarios.

Findings

The proposed method outperforms benchmark algorithms in simulation.

It effectively maximizes transmission rates and reduces UAV energy consumption.

The approach enhances communication robustness in obstacle-rich urban environments.

Abstract

Emerging technologies in sixth generation (6G) of wireless communications, such as terahertz communication and ultra-massive multiple-input multiple-output, present promising prospects. Despite the high data rate potential of millimeter wave communications, millimeter wave (mmWave) communications in urban low altitude economy (LAE) environments are constrained by challenges such as signal attenuation and multipath interference. Specially, in urban environments, mmWave communication experiences significant attenuation due to buildings, owing to its short wavelength, which necessitates developing innovative approaches to improve the robustness of such communications in LAE networking. In this paper, we explore the use of an unmanned aerial vehicle (UAV)-carried intelligent reflecting surface (IRS) to support low altitude mmWave communication. Specifically, we consider a typical urban low altitude communication scenario where a UAV-carried IRS establishes a line-of-sight (LoS) channel between the mobile users and a source user (SU) despite the presence of obstacles. Subsequently, we formulate an optimization problem aimed at maximizing the transmission rates and minimizing the energy consumption of the UAV by jointly optimizing phase shifts of the IRS and UAV trajectory. Given the non-convex nature of the problem and its high dynamics, we propose a deep reinforcement learning-based approach incorporating neural episodic control, long short-term memory, and an IRS phase shift control method to enhance the stability and accelerate the convergence. Simulation results show that the proposed algorithm effectively resolves the problem and surpasses other benchmark algorithms in various performances.