A Novel Wavelet Neural Network Load Forecasting Algorithm with Adaptive Momentum Factor

Power load forecasting is an important component of modern power system project which is the foundation of economic operation. In order to effectively improve the precision of short period load forecasting, traditional neural network has slow convergence and easily falling into local optimum in the practical application. This paper proposes a novel neural network load forecasting algorithm with wavelet neural network and self-adaptive momentum factor. This algorithm combines the characteristics in the wavelet transform’s time domain and frequency domain. By adding an adaptive momentum factor, the new algorithm has better stability and higher convergence rate. By comparing three different prediction models, the simulation results show that the improved algorithm model has higher convergence accuracy.