Cellular Network Capacity and Coverage Enhancement with MDT Data and Deep Reinforcement Learning

Abstract

Recent years witnessed a remarkable increase in the availability of data and computing resources in communication networks. This contributed to the rise of data-driven over model-driven algorithms for network automation. This paper investigates a Minimization of Drive Tests (MDT)-driven Deep Reinforcement Learning (DRL) algorithm to optimize coverage and capacity by tuning antennas tilts on a cluster of cells from TIM's cellular network. We jointly utilize MDT data, electromagnetic simulations, and network Key Performance indicators (KPIs) to define a simulated network environment for the training of a Deep Q-Network (DQN) agent. Some tweaks have been introduced to the classical DQN formulation to improve the agent's sample efficiency, stability and performance. In particular, a custom exploration policy is designed to introduce soft constraints at training time. Results show that the proposed algorithm outperforms baseline approaches like DQN and best-first search in terms of long-term reward and sample efficiency. Our results indicate that MDT-driven approaches constitute a valuable tool for autonomous coverage and capacity optimization of mobile radio networks.

Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approach

“…For the first method, an reinforcement learning (RL)-based solution for coverage and capacity optimization using base station antenna electrical tilt in mobile networks was proposed in [8]. For the second method, in [9], a minimization of drive tests-driven deep RL algorithm was investigated to optimize coverage and capacity with fixed weights. For the third method, the authors in [10] developed and compared two RL-based approaches for maximizing coverage and capacity.…”