Abstract #301228


The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.


Back to main JSM 2002 Program page



JSM 2002 Abstract #301228
Activity Number: 355
Type: Contributed
Date/Time: Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
Sponsor: Business & Economics Statistics Section*
Abstract - #301228
Title: Bayesian Modeling and Forecasting of Intra-day Electricity Load
Author(s): Remy Cottet*+ and Michael Smith+
Affiliation(s): University of Sydney and University of Sydney
Address: Merewether Building H04, University of Sydney, Sydney, NSW, , 2006, Australia Merewether Building H04, Sydney, NSW, , 2006, Australia
Keywords: Peak load forecasting ; Electricity Demand ; Seemingly Unrelated Regression
Abstract:

This paper employs a multi-equation regression model and a first-order vector autoregressive error process with a parsimonious disturbance for modeling and forecasting electricity load data. The model is flexible and can be applied to several years of data, or a running window of several weeks. Long-term load, short-term load, time-of-peak load, and peak load-level forecasts can all be obtained from the one model, and meteorological effects can be included or excluded, depending on the availability of reliable forecasts. The model is estimated using Bayesian Markov chain Monte Carlo methods, and full finite sample posterior and predictive distributions are obtained. This is challenging, because the models employed can have thousands of parameters, and the number of intra-day observations can number in the tens of thousands.


  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2002 program

JSM 2002

For information, contact meetings@amstat.org or phone (703) 684-1221.

If you have questions about the Continuing Education program, please contact the Education Department.

Revised March 2002