Combining Wavelet Transformed and Improved SSA Optimizing Wavelet Neural Network for Power Load Prediction
Power load forecasting is a key means for transmission network expansion,planning and reasonable power dispatch.Aimed at the nonlinear and complex characteristics of power load time series,a power load prediction model for combing improved sparrow search algorithm and wavelet neural network(ISSA-WNN)is proposed to optimize wavelet neural network.The improved sparrow search algorithm is designed to optimize the initial value of the key parameters of the wavelet neural network,which can ef-fectively solve the problem that it is easy for the gradient parameter adjustment to fall into the shortage of local optimum.The Logis-tic-Tent hybrid chaotic population initialization,discoverer or watcher adaptive update,follower variable logarithm spiral update and Gauss-Cauchy hybrid mutation strategy are introduced to improve the optimization ability of the standard sparrow search algorithm.The wavelet transform is used to decompose and reconstruct the power load sample to reduce the disorder and volatility of the load time sequence.On this basis,a new power load prediction model ISSA-WNN is constructed.The experimental results show that com-pared with the standard WNN model and optimizing SSA-WNN model,the average absolute percentage error and root mean square er-ror index values of the prediction model ISSA-WNN are averagely reduced by 18.42％and 21.21％,respectinely,with a stronger fit-ting ability and more stable prediction performance.
power load predictionWNNwavelet transformSSAGaussian-Cauchy mutation
万方数据
维普
