Green O-RAN Operation: a Modern ML-Driven Network Energy Consumption Optimisation

TL;DR

This paper presents a machine learning approach using TD3 to optimize energy consumption in O-RAN networks by intelligently controlling base station components, achieving significant energy savings and improved stability over traditional methods.

Contribution

Introduces a TD3-based control strategy for energy efficiency in O-RAN, overcoming discrete action limitations and demonstrating superior performance in simulations.

Findings

Over 50% energy savings compared to baseline

TD3 outperforms DQN by up to 6%

Faster convergence and better stability

Abstract

The increasing energy demand of next-generation mobile networks, especially 6G, is becoming a major concern, particularly due to the high power usage of base station components RU, which often remain active even during low traffic periods. To tackle this challenge, our study focuses on improving energy efficiency in O-RAN systems using intelligent control strategies. TD3 leverages a continuous action space to overcome the limitations of traditional discrete-action methods like DQN. By avoiding exponential growth in action space, TD3 enables more precise control of RU sleep modes in dense and large radio environments. Simulation results show that our approach consistently achieves over 50% energy savings compared to the always-on baseline, with TD3 outperforming DQN-based methods by up to 6%, while also offering better stability and faster convergence.