Artificial Neural Network and ANFIS Based Short Term Load Forecasting in Real Time Electrical Load Environment

An efficient and accurate electrical power Short Term Load forecasting plays a vital role for economic operational planning of both the electricity markets as well as regulated power systems. Till date many techniques and approaches have been presented for STLF in the literature. However there is still an essential need to develop more efficient and accurate load forecast model. This paper uses hourly load data of three years from 2005-2007, and weather data such as temperature, wind speed and humidity for the same years. Forecasting will be of load demand for coming hour based on input parameters at that hour. In regard to the influence of real-time electricity market on short-term load, a model to forecast short term load is established by combining the artificial neural network (ANN) with the adaptive neural fuzzy inference system (ANFIS). The model first makes use of the nonlinear approaching capacity of the FFBP network to forecast the load on the prediction day with no account of the factor of electric load, and then, based on the recent changes of the real-time load, it uses the ANFIS system to adjust the results of load forecasting obtained by ANN network. This system integration will improve forecasting accuracy and overcome the defects of the ANN network.