Reinforcement Learning-Based Spectral Performance Optimization for UAV-Assisted MIMO Communication System

Authors:
Publisher website
Google Scholar
Abstract
Dear Editor, This letter is concerned with the problem of stable high-quality signal transmission of unmanned aerial vehicle (UAV)-assisted multiple-input multiple-output (MIMO) communication system. The particle swarm optimization (PSO) algorithm is used to achieve optimal beamforming and power allocation for this system. Additionally, sensitive particle (SP) and parameter adaptive adjustment are introduced into the traditional PSO algorithm, aiming to improve the performance of the PSO algorithm in dynamic environments with real-time changes in the UAV position. A reinforcement learning (RL)-based approach is proposed to obtain optimal UAV trajectory and adaptive adjustment strategy for PSO parameters, which combine with a specific obstacle avoidance scheme to achieve accurate UAV navigation while satisfying high-quality signal transmission. Simulation experiments show that our scheme provides higher and more stable spectral efficiency as well as more efficient UAV navigation than the currently commonly used scheme with a single RL approach.
Funding Information
  • National Natural Science Foundation of China (62173251,62203113)
  • Fundamental Research Funds for the Central Universities (2242023K30034)

This publication has 12 references indexed in Scilit: