Transformer area data missing value completion method and device based on machine learning

• Main Authors: YANG SHIHAI, WU WEIJIANG, SUN GUOQIANG, CUI GAOYING, LI XINRAN, LIN HE, LU XIAOQUAN, YI YONGXIAN, XIA QIANQIAN, ZHOU YU
• Format: Patent
• Language: Chinese; English
• Published: 10.04.2020
• 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; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a transformer area data missing value completion method and device, and the method comprises the steps: obtaining a to-be-completed original data set which comprises an original data sequence of a plurality of data indexes; screening out an original data sequence of data indexes needing to be completed from the original data set according to a predetermined index type needing to be completed; and for each to-be-completed data index, taking the original data sequence and the time information of the data in the sequence as the input of a pre-constructed missing value completion model to obtain the output of the missing value completion model, i.e., the data sequence after the completion of the corresponding data index. According to the method, the data factors havinglarge influence on the line loss rate are considered, the related data missing values are complemented by using the machine learning technology, and reliable data support can be provided for calculation and line loss manageme