Power Supply Zonal Loads Prediction Considering Matching of Contact Line Characteristics Based on Deep Transfer Learning

To address the problems that the current power supply partitioning method relies heavily on the selection of load simultaneous rate parameters and does not consider the matching of inter-station contact lines, and the accuracy of the load learning prediction method still needs further improvement, a deep transfer learning prediction method for power supply partitioning considering the matching of contact line characteristics is proposed. Firstly, the overall technical framework of power supply partitioning and load prediction was constructed. Secondly, a model of power supply partitioning considering the matching characteristics of contact line loads was constructed and the corresponding solution method was proposed. On this basis, a partitioned load prediction method based on deep transfer learning and an integrated process of power supply partitioning and load prediction were proposed. Finally, the validity and applicability of the theoretical method proposed in this paper were verified through the simulation analysis of practical cases.