Power system transient stability assessment based on the multiple paralleled convolutional neural network and gated recurrent unit

作     者：Shan Cheng Zihao Yu Ye Liu Xianwang Zuo 

作者机构：College of Electrical Engineering and New EnergyChina Three Gorges UniversityYichang 443002HubeiChina 

出 版 物：《Protection and Control of Modern Power Systems》 (现代电力系统保护与控制（英文）)

年 卷 期：2022年第7卷第1期

页      面：586-601页

核心收录：

学科分类：0401[教育学-教育学] 04[教育学] 

基　　金：funded by the National Natural Science Foundation of China under Grant No.51607105 

主　　题：Transient stability assessment MP CNN+GRU Sample misclassification Improved focal loss function 

摘      要：In order to accurately evaluate power system stability in a timely manner after faults,and further improve the feature extraction ability of the model,this paper presents an improved transient stability assessment(TSA)method of CNN+*** comprises a convolutional neural network(CNN)and gated recurrent unit(GRU).CNN has the feature extraction capability for a micro short-term time sequence,while GRU can extract characteristics contained in a macro long-term time *** two are integrated to comprehensively extract the high-order features that are contained in a transient *** overcome the difficulty of sample misclassification,a multiple parallel(MP)CNN+GRU,with multiple CNN+GRU connected in parallel,is ***,an improved focal loss(FL)func-tion which can implement self-adaptive adjustment according to the neural network training is introduced to guide model ***,the proposed methods are verified on the IEEE 39 and 145-bus *** simulation results indicate that the proposed methods have better TSA performance than other existing methods.