skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Hourly thermal load prediction for the next 24 hours by ARIMA, EWMA, LR and an artificial neural network

Abstract

Predicting the thermal load for the next 24 hours is essential for optimal control of heating, ventilating, and air conditioning (HVAC) systems that use thermal cool storage. It can be useful in minimizing costs and energy in nonstorage systems. A cooperative research project between a US. university and a Japanese corporation investigated four generally used prediction methods to examine the basic models with variations and to compare the accuracy of each model. A cooling and heating seasonal data set with known next-day weather was used to evaluate the accuracy of each prediction method. The results indicate that an artificial neural network (ANN) model produces the most accurate thermal load predictions. After the initial comparisons with a computer-generated data set, the ANN model was applied to two measured building loads from another research project. These sets included typical measurement noise related to continuous field monitoring. The predictions of the next-day cooling load using the ANN prediction model were close to the actual data, even when the next-day weather was forecast. This confirms that the ANN model has sufficient accuracy and is the correct method for practical utilization in HVAC system control, thermal storage optimal control, and load/demand management.

Authors:
 [1];  [2];  [3]
  1. Shimizu Corp., Tokyo (Japan)
  2. Dorgan Associates Inc., Madison, WI (United States)
  3. Univ. of Wisconsin, Madison, WI (United States)
Publication Date:
OSTI Identifier:
87390
Report Number(s):
CONF-950104-
TRN: IM9535%%21
Resource Type:
Conference
Resource Relation:
Conference: American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) winter meeting and exhibition, Chicago, IL (United States), 28 Jan - 1 Feb 1995; Other Information: PBD: 1995; Related Information: Is Part Of ASHRAE transactions 1995. Volume 101, Part 1; PB: 1517 p.
Country of Publication:
United States
Language:
English
Subject:
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; SPACE HVAC SYSTEMS; COLD STORAGE; COOLING LOAD; FORECASTING; COMPUTER CALCULATIONS; A CODES; E CODES; L CODES; ARTIFICIAL INTELLIGENCE; NEURAL NETWORKS

Citation Formats

Kawashima, Minoru, Dorgan, C E, and Mitchell, J W. Hourly thermal load prediction for the next 24 hours by ARIMA, EWMA, LR and an artificial neural network. United States: N. p., 1995. Web.
Kawashima, Minoru, Dorgan, C E, & Mitchell, J W. Hourly thermal load prediction for the next 24 hours by ARIMA, EWMA, LR and an artificial neural network. United States.
Kawashima, Minoru, Dorgan, C E, and Mitchell, J W. 1995. "Hourly thermal load prediction for the next 24 hours by ARIMA, EWMA, LR and an artificial neural network". United States.
@article{osti_87390,
title = {Hourly thermal load prediction for the next 24 hours by ARIMA, EWMA, LR and an artificial neural network},
author = {Kawashima, Minoru and Dorgan, C E and Mitchell, J W},
abstractNote = {Predicting the thermal load for the next 24 hours is essential for optimal control of heating, ventilating, and air conditioning (HVAC) systems that use thermal cool storage. It can be useful in minimizing costs and energy in nonstorage systems. A cooperative research project between a US. university and a Japanese corporation investigated four generally used prediction methods to examine the basic models with variations and to compare the accuracy of each model. A cooling and heating seasonal data set with known next-day weather was used to evaluate the accuracy of each prediction method. The results indicate that an artificial neural network (ANN) model produces the most accurate thermal load predictions. After the initial comparisons with a computer-generated data set, the ANN model was applied to two measured building loads from another research project. These sets included typical measurement noise related to continuous field monitoring. The predictions of the next-day cooling load using the ANN prediction model were close to the actual data, even when the next-day weather was forecast. This confirms that the ANN model has sufficient accuracy and is the correct method for practical utilization in HVAC system control, thermal storage optimal control, and load/demand management.},
doi = {},
url = {https://www.osti.gov/biblio/87390}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Aug 01 00:00:00 EDT 1995},
month = {Tue Aug 01 00:00:00 EDT 1995}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: