The Study of Power Customer Classification Based on Principal Component Analysis and Improved Back Propagation Neural Network

According to the characteristics of the power industry, an index system of power customer classification was designed in this thesis, and all the initial indexes included were screened through the Principal Component Analysis (PCA). Using the Back Propagation Neural Network (BPNN) which was optimized by the Genetic Algorithm (GA) to establish the customer classification model. The combination of the GA and the BPNN can effectively solve the problems of trapping into local minimum and low convergence speed which exist in the BPNN. Finally, we give an example to prove the validity of the model.