Cellular Network Capacity and Coverage Enhancement with MDT Data and Deep Reinforcement Learning
This work addresses autonomous optimization for mobile radio networks, but it is incremental as it builds on existing DRL methods with tweaks for a specific domain.
The paper tackled optimizing cellular network coverage and capacity by tuning antenna tilts using MDT data and deep reinforcement learning, achieving better long-term reward and sample efficiency compared to baselines like DQN and best-first search.
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-fist 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.