Intelligent power grid abnormal data cleaning method based on artificial intelligence

• Main Authors: XU XIHAI, WANG GUOHUA
• Format: Patent
• Language: Chinese; English
• Published: 17.10.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to the field of data processing, in particular to an intelligent power grid abnormal data cleaning method based on artificial intelligence, and the method comprises the steps: obtaining the peak-valley characteristic coefficient of each power utilization load curve through combining the extreme value and extreme point on each power utilization load curve; according to the peak-valley characteristic coefficient and the kurtosis, obtaining a peak-valley change characteristic value of each electrical load curve; calculating a load fluctuation characteristic value of each electrical load curve; calculating a load stable characteristic value of each electrical load curve; taking the peak-valley change characteristic value, the load fluctuation characteristic value and the load stability characteristic value of the electrical load curve as electrical load characteristic vectors, and obtaining an abnormal electrical load curve according to the LOF value of each electrical load characteristic ve