Abstract: In this study, the use of neural networks to study the design of Short-Term Load Forecasting (STLF) Systems for the west of Iran was explored. The three important architectures of neural networks named Multi Layer Perceptron (MLP), Elman Recurrent Neural Network (ERNN) and Radial Basis Function Network (RBFN) to model STLF systems were used. The results show that RBFN networks have the minimum forecasting error and are the best method to model the STLF systems.