Application of Elman Neural Network and MATLAB to Load Forecasting

In order to improve the load-forecast precision and availability of power system, a method based on Elman neural network and MATLAB is presented to create a load forecast model, which according to the Elman neural network model having the characteristics of approach to arbitrary nonlinear functions and having the ability of reflecting the dynamic behavior of the system and for the practicability and high efficiency of using neural network tool-box in MATLAB to program. Then using actual load data to train the model, the emulation results show that the model is of quickly convergence speed and high forecasting precision, which can meet the needs of running and scheduling in power system, and using neural network tool-box in MATLAB to program can make the worker won free of elaborate program and make the working efficiency improved effectively. The example is of proof that the method is feasible and effective.