Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks

arXiv:2404.16920v1 Announce Type: cross
Abstract: We study the data packet transmission problem (mmDPT) in dense cell-free millimeter wave (mmWave) networks, i.e., users sending data packet requests to access points (APs) via uplinks and APs transmitting requested data packets to users via downlinks. Our objective is to minimize the average delay in the system due to APs' limited service capacity and unreliable wireless channels between APs and users. This problem can be formulated as a restless multi-armed bandits problem with fairness …

abstract access arxiv cs.it cs.lg cs.ni data delay eess.sp free math.it millimeter wave networks reinforcement reinforcement learning study type via