On-Line Algorithms for Forecasting Hourly Loads of an Electric Utility

Abstract

A method which lends itself to online forecasting of hourly electric loads is presented and the results of its use are compared to models developed using the Box-Jenkins method. The method consits of processing the historical hourly loads with a sequential least-squares estimator to identify a finite order autoregressive model which in turn is used to obtain a parsimnious autoregressive-moving average model.