基于人工神经网络预测虚拟注入电流的暂态稳定快速算法  

Fast algorithm for transient stability simulations based on predicting fictitious injection current with artificial neural network

作　　者：朱翎 童伟林[1] 王建全[1] ZHU Ling;TONG Wei-lin;WANG Jian-quan(School of Electrical Engineering, Zhejiang University, Hangzhou 310027, China)

机构地区：[1]浙江大学电气工程学院

出　　处：《能源工程》2019年第4期28-34,共7页Energy Engineering

摘　　要：提出了一种基于神经网络预测虚拟注入电流的暂态稳定快速算法,使用并行计算的方法可提高该算法的执行效率。该算法通过使用人工神经网络来预测虚拟注入电流,可以有效减少暂态稳定数值积分中网络方程与微分方程的交替求解次数,减少暂态稳定计算时间。在3机9节点算例和新英格兰10机39节点算例上进行了验证,证明了该方法的可靠性与有效性。由于神经网络的训练能够离线完成,因此本算法有利于实现暂态稳定计算的在线化应用。A fast algorithm for transient stability based on predicting virtual injection current with artificial neural network was proposed and parallel algorithm was used to improve efficiency of the method. The reliability and effectiveness were proved with 10-generator New England test system and example which consisted of 3 generators and 9 buses. The number of iterations of the network equation and differential equation could be significantly reduced. As a result, the time cost of transient stability calculation was reduced. The training of the artificial neural networks could be processed off-line, so the method proposed was useful for the application of online calculation of transient stability.

关 键 词：人工神经网络 虚拟注入电流 并行计算 暂态稳定数值积分算法 

分 类 号：TM727[电气工程—电力系统及自动化]