Electric power consumption forecast of life energy sources based on fuzzy neural network

A fuzzy neural network(FNN) with five layers is proposed in this article. Aim at the structure optimization of network, a new node selection method and corresponding back propagation learning algorithm are presented. We use real history data to train the network model at the same time and to forecast the result after the train finished. Test results illustrate its good practicability to power consumption forecast of life energy sources.