{"title":"基于随机森林算法的电力系统电压动态时空分布特征研究","authors":"Jiaqi Fan, Tongjun Shang, Tianyu Yang","doi":"10.1002/adc2.132","DOIUrl":null,"url":null,"abstract":"<p>The theme of this study is to find a method that can more accurately classify the spatiotemporal distribution characteristics of power system voltage dynamics. As more and more new energy power generation devices are added to the power network, the accuracy of traditional methods for classifying the spatiotemporal distribution characteristics of power system voltage dynamics has gradually decreased. It is significant to reduce the power loss caused by error in identifying voltage dynamic spatiotemporal distribution characteristics. Hence it is necessary to design methods that can more accurately classify power system voltage dynamic spatiotemporal distribution characteristics data. This study proposes a method for studying the spatiotemporal distribution characteristics of power system voltage dynamics based on an improved random forest algorithm. The information entropy calculation method of decision tree in random forest algorithm is improved. According to the experimental results, the classification accuracy of the method for voltage dynamic spatiotemporal distribution characteristics is 99.55%. It can effectively achieve the dynamic spatiotemporal distribution of power system voltage.</p>","PeriodicalId":100030,"journal":{"name":"Advanced Control for Applications","volume":"6 2","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/adc2.132","citationCount":"0","resultStr":"{\"title\":\"Research on dynamic temporal and spatial distribution characteristics of electrical power system voltage based on random forest algorithm\",\"authors\":\"Jiaqi Fan, Tongjun Shang, Tianyu Yang\",\"doi\":\"10.1002/adc2.132\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The theme of this study is to find a method that can more accurately classify the spatiotemporal distribution characteristics of power system voltage dynamics. As more and more new energy power generation devices are added to the power network, the accuracy of traditional methods for classifying the spatiotemporal distribution characteristics of power system voltage dynamics has gradually decreased. It is significant to reduce the power loss caused by error in identifying voltage dynamic spatiotemporal distribution characteristics. Hence it is necessary to design methods that can more accurately classify power system voltage dynamic spatiotemporal distribution characteristics data. This study proposes a method for studying the spatiotemporal distribution characteristics of power system voltage dynamics based on an improved random forest algorithm. The information entropy calculation method of decision tree in random forest algorithm is improved. According to the experimental results, the classification accuracy of the method for voltage dynamic spatiotemporal distribution characteristics is 99.55%. It can effectively achieve the dynamic spatiotemporal distribution of power system voltage.</p>\",\"PeriodicalId\":100030,\"journal\":{\"name\":\"Advanced Control for Applications\",\"volume\":\"6 2\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/adc2.132\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advanced Control for Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/adc2.132\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced Control for Applications","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/adc2.132","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Research on dynamic temporal and spatial distribution characteristics of electrical power system voltage based on random forest algorithm
The theme of this study is to find a method that can more accurately classify the spatiotemporal distribution characteristics of power system voltage dynamics. As more and more new energy power generation devices are added to the power network, the accuracy of traditional methods for classifying the spatiotemporal distribution characteristics of power system voltage dynamics has gradually decreased. It is significant to reduce the power loss caused by error in identifying voltage dynamic spatiotemporal distribution characteristics. Hence it is necessary to design methods that can more accurately classify power system voltage dynamic spatiotemporal distribution characteristics data. This study proposes a method for studying the spatiotemporal distribution characteristics of power system voltage dynamics based on an improved random forest algorithm. The information entropy calculation method of decision tree in random forest algorithm is improved. According to the experimental results, the classification accuracy of the method for voltage dynamic spatiotemporal distribution characteristics is 99.55%. It can effectively achieve the dynamic spatiotemporal distribution of power system voltage.