Short-term electric quantity load accurate prediction method

• Main Authors: WANG PING, LIANG LING, HUANG YUSONG, XIA TIAN, SHI SHI, MA JIANWEI, CHEN SHENG, LIU XIAOFANG, ZHOU ZHONGQIANG, ZHANG HONGLUE
• Format: Patent
• Language: Chinese; English
• Published: 18.08.2020
• Subjects: CALCULATING; 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 relates to the field of electric power engineering, in particular to a short-term electric quantity load accurate prediction method, which comprises the steps of collecting electric quantity, load data, historical meteorological information and holiday data; cleaning data exception or data missing by adopting a replacement method and a difference method, and cleaning data asynchronization by adopting an average value method and a forced synchronization method; acquiring cleaned temperature and electric quantity load data, calculating to obtain an average electric quantity load under each temperature gear, drawing a temperature and electric quantity load influence curve, and taking a temperature interval with gentle electric quantity load trend as a reference electric quantityload temperature interval; classifying the electric quantity load in each temperature interval and calculating an average value, and considering a time-sharing characteristic for a load model to obtain an electric quantity t