A Safe Reinforcement Learning Architecture for Antenna Tilt Optimisation

TL;DR

This paper introduces a modular Safe Reinforcement Learning architecture for antenna tilt optimization in cellular networks, ensuring safety during exploration while improving network performance.

Contribution

The paper presents a novel SRL architecture with a safety shield that benchmarks and ensures safe actions in RET optimization tasks.

Findings

SRL outperforms baseline in network performance

Safety shield effectively prevents unsafe actions

Improved reliability in antenna tilt adjustments

Abstract

Safe interaction with the environment is one of the most challenging aspects of Reinforcement Learning (RL) when applied to real-world problems. This is particularly important when unsafe actions have a high or irreversible negative impact on the environment. In the context of network management operations, Remote Electrical Tilt (RET) optimisation is a safety-critical application in which exploratory modifications of antenna tilt angles of base stations can cause significant performance degradation in the network. In this paper, we propose a modular Safe Reinforcement Learning (SRL) architecture which is then used to address the RET optimisation in cellular networks. In this approach, a safety shield continuously benchmarks the performance of RL agents against safe baselines, and determines safe antenna tilt updates to be performed on the network. Our results demonstrate improved performance of the SRL agent over the baseline while ensuring the safety of the performed actions.