Distribution network planning method, system and device based on residual neural network and medium

• Main Authors: ZENG SHAOHUANG, XU YAO, HUANG YUPENG, YANG YUBIN, HUANG WEIQIONG, LI DEQIONG, YAN LEI, CHEN XIAOXIONG, CHEN GUORUI
• Format: Patent
• Language: Chinese; English
• Published: 14.06.2024
• Subjects: CALCULATING; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; GENERATION; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to a distribution network planning method, system and equipment based on a residual neural network and a medium, and the method comprises the specific steps: based on the land use property of each land in a planning region, respectively extracting attributes influencing various land use load densities, and extracting the load densities of similar regions and historical data of the influence attributes thereof, pre-training a load density prediction model based on a residual neural network through the load density and historical data of the influence attributes of the load density, predicting the load density of each land by using the load density prediction model, and further calculating the land load; extracting related feature data influencing substation site selection in each land in the planning area; and extracting historical data of the site and related characteristics of the existing transformer substation in areas similar to the lands in the planning area, pre-training a transfor