基于智能体的电力系统分布式自适应抗干扰控制  

Distributed adaptive anti-disturbance control for power systems based on multi-agents

作　　者：石童昕 陈龙胜[1] 李统帅 金飞宇 SHI Tongxin;CHEN Longsheng;LI Tongshuai;JIN Feiyu(School of Aircraft Engineering,Nanchang Hangkong University,Nanchang 330063,China)

机构地区：[1]南昌航空大学飞行器工程学院,南昌330063

出　　处：《北京航空航天大学学报》2024年第5期1685-1692,共8页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(61963029);江西省教育厅科学技术研究项目(GJJ2201124)。

摘　　要：针对多机电力系统中不可避免存在非线性、不确定特性和动态干扰等问题,基于径向基神经网络(RBFNN)和非线性干扰观测器(NDO)提出一种分布式自适应抗干扰控制器,以增强多机电力系统的暂态稳定性和鲁棒性。采用RBFNN处理系统中的未知非线性问题,并基于神经网络的输出设计NDO以实现对复合扰动的在线估计;在多智能体框架下为多机电力系统提出一种分布式自适应抗干扰控制策略,实时接收通信网络测量的数据并控制储能装置动作,在外部扰动下实现各电机转速的快速同步与跟踪,并利用Lyapunov稳定性理论证明闭环系统信号的收敛性。仿真实验表明:所提策略有效可行。In response to problems like the inevitable nonlinearities,uncertainties and dynamic external disturbances in multi-machine power systems,a distributed adaptive anti-disturbance control scheme is proposed based on radial basis function neural networks(RBFNN)and nonlinear disturbance observers(NDO)to enhance transient stability and robustness.The unknown nonlinearities of the system are approximated by RBFNN,and NDO are designed based on the output of RBFNNs to estimate the compounded disturbances on-line.A novel distributed adaptive anti-disturbance control scheme for multi-machine power systems is developed with multi-agents'framework,which can receive real-time data measured by communication networks,and control the action of energy storage devices.The speed synchronization of each motor is guaranteed in the presence of external disturbances,and the stability of the closed-loop system is proven based on the Lyapunov stability theory.The simulation results verify the effectiveness of the proposed scheme.

关 键 词：暂态电力系统 神经网络 非线性干扰观测器 多智能体 暂态稳定性 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]