解耦(概率)
控制工程
计算机科学
非线性系统
储能
工程类
可再生能源
控制理论(社会学)
智能控制
网格
电力系统
电子稳定控制
理论(学习稳定性)
间歇性
功率(物理)
非线性控制
钥匙(锁)
控制(管理)
控制系统
Lyapunov稳定性
电力电子
功率控制
联轴节(管道)
动态需求
协同仿真
多智能体系统
接口(物质)
微电网
对偶(语法数字)
能量(信号处理)
智能电网
路径(计算)
作者
wang yiying,Dongyi Zhang,Lifen Ma,Xiaoling Li,Mingxian Liu,Chen Liu,Jie Wu
标识
DOI:10.1088/2631-8695/ae3220
摘要
Abstract The penetration rate of renewable energy in the power system continues to increase, and the intermittency and volatility pose severe challenges to the stability of the power grid. The integration of energy storage systems with the power grid has become a research focus. The three-port converter (TAB) serves as a key interface device, boasting high power density and flexible control. However, it faces difficulties such as multi-port strong coupling and complex nonlinear dynamic characteristics. Traditional control methods are unable to achieve optimal performance, thereby restricting its application. To address this issue, this paper proposes a TAB cooperative control strategy based on dual intelligent agents DDQN. This strategy enables intelligent agent collaboration for learning, reducing cross-port coupling and computational complexity, and improving the dynamic response performance and system stability of TAB. Compared with existing methods, it not only accelerates the dynamic response speed but also achieves decoupling control of TAB, providing a new theoretical framework and engineering path for the control of high-dimensional nonlinear power electronic systems, and helping to promote the development of the collaborative technology of renewable energy and energy storage systems.
科研通智能强力驱动
Strongly Powered by AbleSci AI