The prediction of Energy Consumption in Henan Based on Genetic Neural Network

摘要

In order to avoid the standard BP network shortcomings, the forecast model of energy consumption in henan was constructed based on genetic neural network. Involving the advantages of GA and BP, the algorithm can simultaneously complete genetic selection within a solution space to find the optimal points. Then the BP algorithm searchs the best optimal result from those points by the direction of negative gradient. Simulation indicates the MAPE in GA-BP is 8.45%, lower than that of 19.44% in standard BP. Finally it predicts the total energy consumptions with the 23350 million tons of coal in 2011, an annual growth rate of 3.8%, which is slightly slower than the average rate in the past decade.