The Comparison of Holt-Winters Method and Multiple Regression Method: A Case Study
Keywords:
District heating,
Heat load forecasting,
Multiple regression,
Holt-Winters methods.
Author(s):
Liljana Ferbar Tratar, PhD, University of Ljubljana, Faculty of Economics;
Ervin Strmčnik, MSc, University of Ljubljana, Faculty of Mechanical Engineering.
Abstract:
The European Union approach towards a low-carbon society in EU provides many measures. Appropriate heat load forecasting techniques offer opportunity for more effective schedule operations and cost minimization. The Company Energetika Ljubljanaclaims the largest district heating network in the Republic of Slovenia. Although the company has a 150-year tradition, the company has not implemented any of the advanced heat load forecasting methods. Especially long-term heat load forecasting methods offer many opportunities for the strategic planning and the optimal scheduling of heating resources, whereas short-term forecasting approach would help to reach the optimal daily operations and the maximum utilization of the company’s resources. This paper presents forecasting approach for short- and long-term heat load forecasting on the three levels: monthly, weekly and daily forecasting bases. The comparison of the forecasting performances of Multiple regression and Exponential smoothing methods has been analysed. Based on chosen accuracy measures, Multiple regression was recognized as the best forecasting method for daily and weekly short-term heat load forecasting, whereas Holt–Winters methods ensured the best forecasting values in purpose of long-term heat load forecasting and monthly short-term heat load forecasting.
Journal:
Energy, ISSN 0360-5442. [Print ed.], 2016, vol. 109, p. 266-276.
Indexing:
JCR(2014): 4,844
Related news
Publish your comment:
Upcoming events
