Application of Reinforcement Learning for 5G Scheduling Parameter Optimization

TL;DR

This paper explores using reinforcement learning to optimize 5G network parameters, aiming to automate and improve the tuning process amidst complex air interface features like massive MIMO and beamforming.

Contribution

It introduces a reinforcement learning approach for automatic 5G parameter tuning, comparing it with expert recommendations to enhance network performance.

Findings

Reinforcement learning effectively learns optimal scheduling parameters.

The method outperforms traditional expert-based tuning.

Automation reduces manual effort and improves network efficiency.

Abstract

RF Network parametric optimization requires a wealth of experience and knowledge to achieve the optimal balance between coverage, capacity, system efficiency and customer experience from the telecom sites serving the users. With 5G, the complications of Air interface scheduling have increased due to the usage of massive MIMO, beamforming and introduction of higher modulation schemes with varying numerologies. In this work, we tune a machine learning model to "learn" the best combination of parameters for a given traffic profile using Cross Entropy Method Reinforcement Learning and compare these with RF Subject Matter Expert "SME" recommendations. This work is aimed towards automatic parameter tuning and feature optimization by acting as a Self Organizing Network module