{"title":"电力大数据需求侧管理的聚类抽样","authors":"Yongxin Zhang, Shi Shen","doi":"10.17781/P002208","DOIUrl":null,"url":null,"abstract":"In view of the DSM (Demand Side Management) under the big data environment, an improved FCM (Fuzzy C-Mean) clustering with Gauss data preprocessing is proposed, and the daily load curve of the whole study area was obtained with the electricity data. According to the formulation of the TOU (Time of Use) price, which is consistent with the characteristics of local users is given. The electricity suggestions based on the specific user load curve is provided, including the return of the DR (Demand Response). Subsequently, the sampling division is put forward to expand the improved model. Finally, the method is tested by the actual data, and the results show that it has a processing speed 10 times of the direct processing when the data is more","PeriodicalId":211757,"journal":{"name":"International journal of new computer architectures and their applications","volume":"103 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"CLUSTER SAMPLING FOR THE DEMAND SIDE MANAGEMENT OF POWER BIG DATA\",\"authors\":\"Yongxin Zhang, Shi Shen\",\"doi\":\"10.17781/P002208\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In view of the DSM (Demand Side Management) under the big data environment, an improved FCM (Fuzzy C-Mean) clustering with Gauss data preprocessing is proposed, and the daily load curve of the whole study area was obtained with the electricity data. According to the formulation of the TOU (Time of Use) price, which is consistent with the characteristics of local users is given. The electricity suggestions based on the specific user load curve is provided, including the return of the DR (Demand Response). Subsequently, the sampling division is put forward to expand the improved model. Finally, the method is tested by the actual data, and the results show that it has a processing speed 10 times of the direct processing when the data is more\",\"PeriodicalId\":211757,\"journal\":{\"name\":\"International journal of new computer architectures and their applications\",\"volume\":\"103 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International journal of new computer architectures and their applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.17781/P002208\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of new computer architectures and their applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.17781/P002208","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
摘要
针对大数据环境下的需求侧管理(Demand Side Management, DSM),提出了一种基于高斯数据预处理的改进FCM (Fuzzy C-Mean)聚类方法,利用用电数据得到整个研究区域的日负荷曲线。根据制定的TOU (Time of Use)价格,给出符合当地用户特点的价格。根据具体的用户负荷曲线给出用电建议,包括返回DR (Demand Response)。随后,提出了抽样划分,对改进模型进行了扩展。最后,通过实际数据对该方法进行了测试,结果表明,当数据量较大时,该方法的处理速度是直接处理的10倍
CLUSTER SAMPLING FOR THE DEMAND SIDE MANAGEMENT OF POWER BIG DATA
In view of the DSM (Demand Side Management) under the big data environment, an improved FCM (Fuzzy C-Mean) clustering with Gauss data preprocessing is proposed, and the daily load curve of the whole study area was obtained with the electricity data. According to the formulation of the TOU (Time of Use) price, which is consistent with the characteristics of local users is given. The electricity suggestions based on the specific user load curve is provided, including the return of the DR (Demand Response). Subsequently, the sampling division is put forward to expand the improved model. Finally, the method is tested by the actual data, and the results show that it has a processing speed 10 times of the direct processing when the data is more