Accurate power load forecasting is an important basis for realizing economic dispatch of power systems.Considering the good fitting and generalization ability of radial basis function neural network（RBF-NN） for time series

RBF-NN is used as the research model to predict power load.The K-means algorithm is used to preprocess the load data

and the particle swarm optimization（PSO） algorithm is used to optimize the parameters of the RBF-NN to overcome the effects of parameter uncertainty

gradient descent and local optimization on the prediction effect of the model.Based on the Australian power load data set

the simulation verifies the higher accuracy and generalization ability of the proposed power load forecasting model.