基于情感自学习神经网络的电力系统分布式复合学习控制

Distributed composite learning control for power systems based on emotional self-structuring neural network

中文关键词  电力系统  多智能体  情感自学习神经网络  复合学习控制

英文关键词  power system  multi-agent  emotional self-structuring neural network  composite learning control

中文摘要

      针对非线性多智能体电力系统(NMAPSs)的非线性、强耦合、不确定特性和未知扰动等问题, 本文基于连续情感自学习神经网络(CESSNNs)提出一种分布式复合学习控制方法. 首先, 采用CESSNNs逼近NMAPSs中的非线性不确定项, 并设计对应的串–并行辨识模型以获取模型辨识误差; 其次, 基于CESSNNs的输出和模型辨识误差为NMAPSs设计复合学习控制策略, 并基于Lyapunov稳定性理论分析了闭环系统的稳定性; 最后, 仿真实验表明所设计的控制策略的有效性.

英文摘要

      To solve the control problem of nonlinear multi-agent power systems (NMAPSs) with inevitable nonlinearities, uncertainties and dynamic disturbances, a distributed composite learning control is proposed based on the continuous emotional self-structuring neural networks (CESSNNs). Firstly, the unknown nonlinearities of the system are approximated by CESSNNs. Furthermore, a series-parallel identification model is designed to obtain the model identification error of the power system. Moreover, a distributed composite learning control methodology for NMAPSs is proposed based on the outputs of CESSNNs and model identification errors. The closed-loop system signal converges to zero which is proved based on the Lyapunov stability theory. Finally, the simulation results verify the effectiveness of control strategy, and the power system has good robustness and stability.