Reactive power coordination optimization technology for source-network-load-storage in new distribution network based on adaptive learning rate convolutional neural network
With the promotion of the"dual carbon"goal,the capacity of distributed new energy connected to the power grid has significantly increased.The use of distribution network source network load storage coordination optimization strategy is an important method to achieve distributed new energy consumption,among which reactive power optimization can ensure the safe and stable operation of the power grid.This article proposes an adaptive learning rate convolutional neural network based optimization technique for load storage and reactive power coordination in distribution networks.Firstly,a reactive power optimization model is constructed with the goal of minimizing network loss and voltage offset.Secondly,utilizing the powerful nonlinear fitting ability of convolutional neural networks,the mapping relationship between power grid operation scenarios,reactive power regulation equipment,and energy storage charging and discharging strategies is excavated.Adaptive learning rate is introduced to update network parameters and improve network training efficiency.Finally,by controlling the charging and discharging conditions of reactive power regulation equipment and energy storage devices to coordinate the output of distributed power sources,active optimization control of reactive power and voltage in new distribution network is achieved.After simulation verification of the IEEE33 node power grid model,the results show that the proposed optimization method for load storage and reactive power coordination in the distribution network source network improves the voltage regulation ability of the power system,laying a good foundation for the safe and reliable operation of the distribution network.
distributed new energyoptimization of source network load storage coordinationreactive power optimizationadaptive learning rateconvolutional neural network
万方数据
维普
