基于直接神经动态规划的电力系统协调控制  

Coordinated Control of Power System Based on Direct Neural Dynamic Programming Method

作　　者：于淼[1,2] 尚伟鹏 卢宁[1,2] Yu Miao Shang Weipeng Lu Ning(School of Mechanical-electronic and Automobile Engineering, Beijing University of Civil Engineering and Architecture,Beijing 100044,China Beijing Key Laboratory of Service Performance of Urban Rail Transit Vehicles, Beijing University of Civil Engineering and Architecture, Beijing 100044, China.)

机构地区：[1]北京建筑大学机电与车辆工程学院,北京100044 [2]城市轨道交通车辆服役性能保障北京市重点实验室,北京100044

出　　处：《系统仿真学报》2017年第4期699-707,共9页Journal of System Simulation

基　　金：国家自然科学基金(51407201);北京建筑大学博士启动基金(00331614032);北京市教委科研计划(SQKM201610016017)

摘　　要：区域间弱阻尼低频振荡是影响电网安全稳定运行的关键问题。目前广域直流和发电机控制的实施已成为提高电网区域间低频振荡阻尼的重要手段之一,但是在发电机、HVDC、FACTS等装置控制器之间的协调方面还需进一步的深入研究。提出直接神经动态规划方法在电力系统稳定控制中的应用结构,基于一般超前-滞后环节的移相式神经网络形式,将直接神经动态规划方法嵌入到传统的电力系统稳定控制器中。将上述提出的方法应用到典型电网结构以及南方电网中实现了控制器的协调设计。仿真结果表明使用该方法进行控制器协调设计后,可以实现很好的协调控制效果。Inter-area low frequency oscillation with weak damping is a key issue affecting the security and stability operation of power grid. Currently, the implementation of wide-area DC and generator control has become one of the important means to improve inter-area low frequency oscillation damping. But the coordination among the controllers of generator, HVDC and FACTS needs to further studying. The application structure of direct neural dynamic programming method in power system stability control was proposed, and based on phase-shift neural network of general lead-lag link, the proposed method was embedded in the traditional power system stability controller It was applied to a typical grid structure as well as in the South China power grid to achieve a coordinated controller design. Simulation results show that this method can realize the coordinated controller design, and the coordinated control effect is very good.

关 键 词：低频振荡 直接神经动态规划 移相式神经网络 协调控制 电力系统稳定 

分 类 号：TM712[电气工程—电力系统及自动化]