Short-Term Load Forecasting in Power Systems Using Adaptive Fuzzy Critic Based Neural Network

Load forecasting constitutes an important tool for efficient planning and operation of power systems and its significance has been intensifying particularly, because of the recent movement towards open energy markets and the need to assure high standards on reliability. Accurate load forecasting is of great importance for power system operation. It is the basis of economic dispatch, hydrothermal coordination, unit commitment, and system security analysis among other functions. Short-term load forecasting (STLF) is for hour to hour forecasting and important to daily maintaining of power plant. Most important factors in load forecasting includes past load history, calendar information (weekday, weekend, holiday, season, etc.) and weather information (instant temperature, average temperature, peak temperature, wind speed, etc.). The forecaster will treat past data as a time series and many kinds of approaches have been applied on this problem. This paper presents a new intelligent approach for short term load forecasting which can model the valuable experiences of the expert operator. This technique is based on emotional critic based fuzzy logic. Emotional learning is a family of intelligent algorithms which can be used for time series prediction, classification, control and identification. This approach is relatively simple and can accurately forecast the hourly loads of weekdays, as well as the weekends and public holidays. It is shown that the proposed method can provide more accurate results than the conventional techniques such as artificial neural networks or ARMA models. Obtained results from extensive testing on power system networks confirm the validity of the developed approach. Key-Words: Short-Term load forecasting, Neural network, Fuzzy logic, Power System, Adaptive Critic