Short-Term Gas Load Forecasting Based on Wavelet BP Neural Network Optimized by Genetic Algorithm

摘要: Aiming at the limitations of a single neural network for effective gas load forecasting, combinational model based on wavelet BP optimized by genetic algorithm is proposed. The problems that traditional converges slowly and easily falls into local minimum are overcame. strengthens function approximation capacity combining well time-frequency feature transform with self-learning ability network. And real coded algorithm, more quick than non-optimized one. This proposed applied to daily forecasting Shanghai simulation results indicate this has excellent prediction effect.