On-line algorithms for forecasting hourly loads of an electric utility
A method that lends itself to on-line 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 parsimonious autoregressive-moving average model. The method presented has several advantages in comparison with the Box-Jenkins method including much-less human intervention, improved model identification, and better results. The method is also more robust in that greater confidence can be placed in the accuracy of models based upon the various measures available at the identification stage.
- Research Organization:
- Harris Corp., Melbourne, FL
- OSTI ID:
- 5485982
- Journal Information:
- IEEE Trans. Power Appar. Syst.; (United States), Journal Name: IEEE Trans. Power Appar. Syst.; (United States) Vol. 100:8; ISSN IEPSA
- Country of Publication:
- United States
- Language:
- English
Similar Records
System load forecasts for an electric utility. [Hourly loads using Box-Jenkins method]
Short-term forecasts gain in accuracy. [Regression technique using ''Box-Jenkins'' analysis]