Hua Ye, Xuegang Lu, Wei Zhang, Fei Cheng, Ying Zhao
{"title":"基于时间序列数据采集的分布式光伏集群产量监测方法","authors":"Hua Ye, Xuegang Lu, Wei Zhang, Fei Cheng, Ying Zhao","doi":"10.1186/s42162-025-00480-1","DOIUrl":null,"url":null,"abstract":"<div><p>The data processing efficiency of distributed photovoltaic cluster output monitoring needs to be improved, improving the prediction effect of distributed photovoltaic power station cluster can effectively improve the security of power system operation and reduce the difficulty of power grid management. In order to obtain a reliable distributed photovoltaic cluster output monitoring method, this paper analyzes the output relationship of cluster power stations, combining time series data analysis methods for distributed cluster processing and monitoring data processing, a combined model of ceemdan and Bayesian neural network is proposed, the representative power plant prediction values obtained by establishing a combination model are weighted to obtain the cluster output prediction values. Compared with the simple superposition of the predicted values of cluster power stations, the average absolute error of this method is reduced by 3.3%, and the root mean square error is reduced by 5.86%. It is concluded that this model can effectively predict the power stations in the cluster. According to the experimental analysis, the output monitoring method of distributed photovoltaic clusters based on time series data collection proposed in this paper has certain effects and can provide theoretical support for the further development of distributed photovoltaic clusters.</p></div>","PeriodicalId":538,"journal":{"name":"Energy Informatics","volume":"8 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://energyinformatics.springeropen.com/counter/pdf/10.1186/s42162-025-00480-1","citationCount":"0","resultStr":"{\"title\":\"Distributed photovoltaic cluster output monitoring method based on time series data acquisition\",\"authors\":\"Hua Ye, Xuegang Lu, Wei Zhang, Fei Cheng, Ying Zhao\",\"doi\":\"10.1186/s42162-025-00480-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The data processing efficiency of distributed photovoltaic cluster output monitoring needs to be improved, improving the prediction effect of distributed photovoltaic power station cluster can effectively improve the security of power system operation and reduce the difficulty of power grid management. In order to obtain a reliable distributed photovoltaic cluster output monitoring method, this paper analyzes the output relationship of cluster power stations, combining time series data analysis methods for distributed cluster processing and monitoring data processing, a combined model of ceemdan and Bayesian neural network is proposed, the representative power plant prediction values obtained by establishing a combination model are weighted to obtain the cluster output prediction values. Compared with the simple superposition of the predicted values of cluster power stations, the average absolute error of this method is reduced by 3.3%, and the root mean square error is reduced by 5.86%. It is concluded that this model can effectively predict the power stations in the cluster. According to the experimental analysis, the output monitoring method of distributed photovoltaic clusters based on time series data collection proposed in this paper has certain effects and can provide theoretical support for the further development of distributed photovoltaic clusters.</p></div>\",\"PeriodicalId\":538,\"journal\":{\"name\":\"Energy Informatics\",\"volume\":\"8 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-02-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://energyinformatics.springeropen.com/counter/pdf/10.1186/s42162-025-00480-1\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Energy Informatics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://link.springer.com/article/10.1186/s42162-025-00480-1\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Energy\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy Informatics","FirstCategoryId":"1085","ListUrlMain":"https://link.springer.com/article/10.1186/s42162-025-00480-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Energy","Score":null,"Total":0}
Distributed photovoltaic cluster output monitoring method based on time series data acquisition
The data processing efficiency of distributed photovoltaic cluster output monitoring needs to be improved, improving the prediction effect of distributed photovoltaic power station cluster can effectively improve the security of power system operation and reduce the difficulty of power grid management. In order to obtain a reliable distributed photovoltaic cluster output monitoring method, this paper analyzes the output relationship of cluster power stations, combining time series data analysis methods for distributed cluster processing and monitoring data processing, a combined model of ceemdan and Bayesian neural network is proposed, the representative power plant prediction values obtained by establishing a combination model are weighted to obtain the cluster output prediction values. Compared with the simple superposition of the predicted values of cluster power stations, the average absolute error of this method is reduced by 3.3%, and the root mean square error is reduced by 5.86%. It is concluded that this model can effectively predict the power stations in the cluster. According to the experimental analysis, the output monitoring method of distributed photovoltaic clusters based on time series data collection proposed in this paper has certain effects and can provide theoretical support for the further development of distributed photovoltaic clusters.