Hourly thermal load prediction for the next 24 hours by ARIMA, EWMA, LR and an artificial neural network
- Shimizu Corp., Tokyo (Japan)
- Dorgan Associates Inc., Madison, WI (United States)
- Univ. of Wisconsin, Madison, WI (United States)
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.
- OSTI ID:
- 87390
- Report Number(s):
- CONF-950104-; TRN: IM9535%%21
- 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
Similar Records
Comparative Analysis of ANN and LSTM Prediction Accuracy and Cooling Energy Savings through AHU-DAT Control in an Office Building
Hourly load forecasting using artificial neural networks. Final report