Abstract:Power load forecasting commonly uses neural network method.The training time of the method is longer,and the meteorological factors can affect load,so the prediction accuracy of the algorithm is not very high.In order to overcome the current problems,particle swarm algorithm is used for optimizing the weight and threshold of BP neural network,then meteorological factors are processed by normalization method and forecasting short-term power load through neural network.The experimental results show that this method has obvious advantages over mere BP neural network.