SHORT-TERM LOAD FORECASTING.

The authors discuss the state of the art in short-term load forecasting (STLF), that is, the prediction of the system load over intervals ranging from one hour to one week. The role of STLF in the online scheduling and security functions of an energy management system (EMS) is reviewed. The nature of the load and the different factors influencing its behavior are considered. A classification of the types of load modeling and forecasting techniques is presented, accompanied by recommendations and by references to the literature which support or expand the discussion. Practical aspects for the development and usage of STLF models and packages are outlined.