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

TL;DR

This paper presents a novel MDT-driven deep reinforcement learning approach to optimize cellular network coverage and capacity by tuning antenna tilts, demonstrating improved performance over traditional methods.

Contribution

It introduces a customized Deep Q-Network with a specialized exploration policy for efficient network optimization using MDT data.

Findings

Outperforms baseline DQN and best-first search in reward and efficiency

Enhances network coverage and capacity through autonomous antenna tilt tuning

Shows MDT data as a valuable resource for network automation

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-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.