A Proximal Policy Optimization based Control Framework for Flexible Battery Energy Storage System
IEEE Transactions on Energy Conversion(2023)
Abstract
Battery energy storage system with a fixed connection lacks the ability to meet various power and energy demands of the power grid. In this thread, Flexible Battery Energy Storage Systems (FBESS) with a highly controllable structure is proposed as a new path for future energy storage. With the increasing complexity of the battery system, an advanced strategy is needed from the control side to tune the multi-terminal of the FBESS. Especially, the FBESS, with a large number of switches, increases the dimension of the decision space, while the traditional control method can not well handle such a task. In addition, the control of the FBESS should consider both the working performance and the balance requirement of the cells. Thus, a Proximal Policy Optimization (PPO) based framework is proposed in this paper to dynamically learn an optimal control strategy for FBESS. Utilizing the clipped surrogate objective, PPO can stably update the policy online through gradient descent. By utilizing its easy implementable property, the proposed method can efficiently control the high dimensional action space and synchronously improve the working time and the balancing performance. Experimental results with data collected from a real battery system prove the validation of the proposed framework.
MoreTranslated text
Key words
Control framework,Proximal policy optimization,Reinforcement learning,Flexible battery energy storage system
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined