On-line algorithms for forecasting hourly loads of an electric utility

Journal Article · Sat Aug 01 04:00:00 EDT 1981 · IEEE Trans. Power Appar. Syst.; (United States)

DOI:https://doi.org/10.1109/TPAS.1981.317020· OSTI ID:5485982

Vemuri, S; Huang, W L; Nelson, D J

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

Related Subjects

29 ENERGY PLANNING, POLICY, AND ECONOMY
296001* -- Energy Planning & Policy-- Electric Power Generation-- (-1989)
ALGORITHMS
ELECTRIC UTILITIES
FORECASTING
HOURLY VARIATIONS
LOAD MANAGEMENT
MANAGEMENT
MATHEMATICAL LOGIC
ON-LINE SYSTEMS
PUBLIC UTILITIES
STOCHASTIC PROCESSES
VARIATIONS