A special lecture seminar was held on July 4, 2024. Details are as follows.

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

Lecturer： Dr. Xun Shao（Associate Professor in the Department of Electrical and Electronic Information Engineering at Toyohashi University of Technology, Japan.）

Date： 15:10～16:50, July 4 (Thu), 2024

Place： Room M-4 (W4032), the 4th floor, West Building, Koganei Campus

Abstract： The unprecedented development of 5G networks and the widespread deployment of 5G base stations (BSs) have highlighted significant concerns about their energy consumption and costs. With the declining cost of renewable energy, equipping power-hungry BSs with renewable energy generators offers a sustainable solution. This work proposes an energy storage-aided reconfigurable renewable energy supply solution for BSs, providing clean energy and storing surplus energy. The proposed system leverages a deep reinforcement learning-based reconfiguring policy to adapt to dynamic renewable energy generation and varying power demands. This policy optimizes the discharging and charging operations of the batteries, ensuring efficient energy use. Experiments utilizing real-world data on renewable energy generation and power demands demonstrate the effectiveness of this solution. The results show an impressive energy saving ratio of 74.8% compared to traditional power grid supply. Furthermore, the proposed system enhances the stability and reliability of the energy supply to BSs, thereby supporting the sustainable expansion of 5G networks. This innovative approach not only reduces operational costs for mobile operators but also contributes to environmental sustainability by minimizing the reliance on non-renewable energy sources.