Share

Hourly thermal load prediction for the next 24 hours by autoregressive integrated moving average (ARIMA), exponential weighted moving average (EWWA), recursive linear regressive (LR), and an artificial neural network.

Author(s) : KAWASHIMA M., DORGAN C. E., MITCHELL J. W.

Summary

Predicting the thermal load for the next 24 hours is essential for optimal control of 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. The results indicate that an artificial neural network model produces the most accurate thermal load predictions.

Details

  • Original title: Hourly thermal load prediction for the next 24 hours by autoregressive integrated moving average (ARIMA), exponential weighted moving average (EWWA), recursive linear regressive (LR), and an artificial neural network.
  • Record ID : 1996-1720
  • Languages: English
  • Source: ASHRAE Transactions.
  • Publication date: 1995/01
  • Document available for consultation in the library of the IIR headquarters only.

Links


See other articles from the proceedings (70)
See the conference proceedings

Indexing