BESS Aided Reconfigurable Energy Supply using Deep Reinforcement Learning for 5G and Beyond

TL;DR

This paper presents a deep reinforcement learning-based reconfigurable energy storage system to supply renewable energy to 5G base stations, significantly reducing energy costs and consumption.

Contribution

It introduces a novel RL-based policy for dynamic reconfiguration of energy storage, optimizing renewable energy use for 5G base stations.

Findings

Achieves 74.8% energy saving ratio compared to traditional grid supply.

Effectively adapts to fluctuating renewable energy and power demands.

Demonstrates practical benefits using real-world data.

Abstract

The year of 2020 has witnessed the unprecedented development of 5G networks, along with the widespread deployment of 5G base stations (BSs). Nevertheless, the enormous energy consumption of BSs and the incurred huge energy cost have become significant concerns for the mobile operators. As the continuous decline of the renewable energy cost, equipping the power-hungry BSs with renewable energy generators could be a sustainable solution. In this work, we propose an energy storage aided reconfigurable renewable energy supply solution for the BS, which could supply clean energy to the BS and store surplus energy for backup usage. Specifically, to flexibly reconfigure the battery's discharging/charging operations, we propose a deep reinforcement learning based reconfiguring policy, which can adapt to the dynamical renewable energy generations as well as the varying power demands. Our experiments using the real-world data on renewable energy generations and power demands demonstrate that, our reconfigurable power supply solution can achieve an energy saving ratio of 74.8%, compared to the case with traditional power grid supply.