What is it about?
Aggregating distributed energy resources (DERs) on the demand side plays a crucial role in achieving high renewable energy penetration rates and reaching a sustainable future. This paper mainly focuses on batteries among DERs, which are controllable and have large energy capacity, but whose capacity degradation is a severe issue. By aggregating the prosumer’s battery, we attempt to exploit demand-side flexibility and stabilize the power grid. Moreover, we also try to minimize the degradation of the prosumer’s battery. In other words, we have realized the aggregation method of exploiting the demand-side flexibility and extending the battery lifetimes.
Featured Image
Photo by Riccardo Annandale on Unsplash
Why is it important?
We incorporated the battery degradation model into the aggregation problem to quantitatively evaluate and control the battery degradation. Moreover, we formulated the battery aggregation problem as a Markov Decision Process (MDP) and solved it using deep reinforcement learning. The experimental result shows that the proposed method can improve the battery lifetime. In particular, the average battery lifetime was improved by 11.2%. The results of our proposed method will contribute to stabilizing the power grid while extending the battery lifetime.
Perspectives
I am grateful for the opportunity to write this article about the paper which is my first publication in international conferences. I hope that this article will stimulate research on the aggregation methodology in energy systems and help to realize the sustainable society.
Shotaro Nonaka
Osaka University
Read the Original
This page is a summary of: Deep reinforcement learning-based SOH-aware battery management for DER aggregation, November 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3563357.3566166.
You can read the full text:
Contributors
The following have contributed to this page
