Real time load forecast in power system

Abstract

This paper presents an overview of different practical techniques to forecast the load for real time applications. The accuracy of load forecast often determines the amount of energy to be procured in the imbalance market. Therefore to reduce exposures to real-time risks and obtain economic, reliable and secure operations of power system, an accurate real-time forecast is required. It can be used by vertically integrated utilities as well as the ISOs in restructured power system. In this paper, we discuss different approaches based on time series and artificial neural network (ANN). The ISO New England market data are used to illustrate and compare the models.