Efficient Short-Term Electricity Load Forecasting Using Recurrent Neural Networks

Short term load forecasting (STLF) plays an important role in the economic and reliable operation of power systems. Electric load demand has a complex profile with many multivariable and nonlinear dependencies. In this study, recurrent neural network (RNN) architecture is presented for STLF. The proposed model is capable of forecasting next 24-hour load profile. The main feature in this network is internal feedback to highlight the effect of past load data for efficient load forecasting results. Testing results on the three year demand profile shows higher performance with respect to common feed forward back propagation architecture.