Artificial Neural Network (ANN) is competent for non-linear proceeding for its excellent non-linear character, predicting methods based on ANN are good for non-linear problem. In the process of the informational construction of electric power industry, there are a great deal of historical data which cry for decision supporting of electric power enterprise. According to the experience of practice in many electric power corporations, this paper introduce a new method of using ANN in electric power marketing. Intelligence decision tree classification algorithm is used in data preprocessing to ensure data optimization, the algorithm about hidden nodes of ANN is improving and ANN computational complexity is reduced. In network training, period of time is partitioned by seasons and taking a conjugate gradient algorithm to raise the speed of network convergence. The experiment result indicates that ANN model has good predicting effect in electric power distribution. |