17th AIAI 2021, 25 - 27 June 2021, Greece

Power Control in 5G Heterogeneous Cells considering User Demands using Deep Reinforcement Learning

Anastasios Giannopoulos, Sotirios Spantideas, Christos Tsinos, Panagiotis Trakadas


  Heterogeneous cells have been emerged as the dominant design approach for the deployment of 5G wireless networks. In this context, inter-cell interferences are expected to drastically affect the 5G targets, especially in terms of through-put experienced by the mobile users. This work proposes a novel Deep Rein-forcement Learning (DRL) scheme, targeting at minimizing the difference be-tween the allocated and requested user throughput through power regulation. The developed algorithm is employed in heterogeneous cells that are controlled in a centralized manner and validated for 5G-compliant channel models. First, the proposed learning framework of the DRL method is presented, mainly in-cluding the stabilization of the learning-related hyperparameters. Then, the DRL method is evaluated for several simulation scenarios and compared to well-established optimization methods for power allocation, namely the Water-filling and Weighted Minimum Mean Squared Error (WMMSE) algorithms, as well as a fixed power control scheme. The evaluation outcomes demonstrate the ability of the DRL framework in accurately approaching the user requirements, where-as the Water-filling and WMMSE solutions present large deviations from the user demands since they aim at the total network-wide throughput maximiza-tion.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.