Pengcheng Li, Haitao Zhang, Haohan Hu, Wanlong Liu, Li Zhang
{"title":"Application research of massive power data prediction based on combinatorial model","authors":"Pengcheng Li, Haitao Zhang, Haohan Hu, Wanlong Liu, Li Zhang","doi":"10.1109/ICCEAI52939.2021.00052","DOIUrl":null,"url":null,"abstract":"Based on the massive data of Shanghai Pudong Electric Power Co., Ltd., this paper studies the load data prediction. Based on the theoretical support of KNN, linear regression and ARIMA algorithm, the local optimal decomposition prediction model was established. In this paper, the million-magnitude load control data are used for model training and experiments. The traditional prediction method is a single day dimension model, while the research method in this paper is time-divided optimal model prediction. For different periods of each day, according to the data characteristics, match and train the best local optimal prediction model for each period. The experimental results show that the accuracy of the local optimal decomposition model is higher than that of the single model, which can fully meet the business needs of the current energy data prediction, and also provide support for the subsequent prediction of other energy data.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCEAI52939.2021.00052","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Based on the massive data of Shanghai Pudong Electric Power Co., Ltd., this paper studies the load data prediction. Based on the theoretical support of KNN, linear regression and ARIMA algorithm, the local optimal decomposition prediction model was established. In this paper, the million-magnitude load control data are used for model training and experiments. The traditional prediction method is a single day dimension model, while the research method in this paper is time-divided optimal model prediction. For different periods of each day, according to the data characteristics, match and train the best local optimal prediction model for each period. The experimental results show that the accuracy of the local optimal decomposition model is higher than that of the single model, which can fully meet the business needs of the current energy data prediction, and also provide support for the subsequent prediction of other energy data.