使用直接神经动态规划方法的SVC附加阻尼控制

电力系统具有的规模巨大、强非线性和不确定性等因素一直是动态稳定控制中难以解决的问题，而直接神经动态规划方法是一种基于测量的不依赖于系统模型的在线控制方法，文中用于实现4机2区系统中SVC的附加阻尼控制器的设计，主要由两部分组成：执行网络和评价网络，这两部分均为神经网络，前者用于产生控制信号，后者用于评价当前的系统状态，并据此调整控制律。文中还通过在MATLAB环境下的仿真，分析了其学习能力、控制效果和适应能力，与使用传统方法设计的控制器的比较结果显示了其在适应性上的优越性。

SVC SUPPLEMENTARY DAMPING CONTROL USING DIRECT NEURAL DYNAMIC PROGRAMMING

The great scales, nonlinearities and uncertainties in modern power system are the most intractable problems for dynamic controls. However, direct neural dynamic programming (direct NDP) approach based on on-line measurements can be employed in this situation, which is independent of models. In this paper, a supplementary SVC damping control in a 4-generator 2-area system was implemented using direct NDP method. Two neural networks, action network (AN) and critic network (CN), make up this controller. AN is used to control SVC, and CN is used to evaluate current system states and update AN. The self-learning and adaptive abilities are analyzed in the MATLAB environment, and the simulation results demonstrate the advantages compared to conventional control.