New energy big data classification and suspicious data processing method

• Main Authors: YUAN JIAN, YUAN LONG, XI XINKUI, ZHOU CHAO, XU JUNJIE, WANG NING, MA BIN, KONG XIANGYU
• Format: Patent
• Language: Chinese; English
• Published: 14.06.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to a new energy big data classification and suspicious data processing method. The method comprises the following steps: (1) data preprocessing; (2) classification: load classification based on users comprises multi-user classification and single-user multi-period classification, and a clustering effectiveness index is obtained; (3) performing FCM clustering analysis, calculating the change of a clustering result according to the determined clustering effectiveness index to obtain an optimal classification result, and calculating to obtain a typical daily load curve corresponding to the optimal classification result; (4) performing weighted FCM clustering analysis to obtain new energy data characteristic indexes; (5) abnormal value processing; (6) missing value processing; and (7) performing normalization processing. According to the method, the classification result is obtained by utilizing FCM clustering, and meanwhile, the effectiveness of the clustering result is checked, so that the