|
Abstract
|
Power flow calculation is the basis of power system operation and control. In order to solve the uncertainty of voltage fluctuation at load point caused by the increasing penetration of renewable energy in distribution network, moreover, the development of power system automation technology has overcome the problems of insufficient power flow data collection capacity of traditional power system. In this paper, a data-driven power flow analysis model is proposed, and a power flow calculation method based on BPNN combined with GA and Adam optimization algorithm (GA-BPNN) is constructed to analyze the distribution network under randomness, the whole process is divided into two stages: training and calculation; The initial value information of power flow, topology characteristics and power factor index are introduced for model training; GA-Adam algorithm is used to optimize the initial value and weight parameters of the model, making the model more stable and the power flow calculation results more accurate. Finally, based on the IEEE-33 bus distribution model, the model in this paper is verified, and the power flow is calculated. The maximum error, average absolute error and root mean square error evaluation indicators are compared with other methods. The results show that the model built in this paper has small error indicators and high accuracy, which improves the efficiency and accuracy of power flow calculation..
|