Modelling and Forecasting Energy Demand: Principles and Difficulties
We give a brief description of how energy demand can be modelled as a function of calendar data, meteorological data and economic variables. The principles of energy demand models are presented and a brief overview of commonly used mathematical methods is given. For each method advantages and disadvantages are described. Some examples illustrate difficulties that may be encountered when using meteorological data in energy models. These difficulties are discussed and we propose some steps weather services could take to facilitate the use of meteorological data in the energy sector.
KeywordsEnergy demand forecast modeling non-linear
Unable to display preview. Download preview PDF.
- Dutton JA. 2009: Chapter 1, This volume.Google Scholar
- ECMWF home page 23 March 2009: www.ecmwf.int/research/demeter
- Friedman J.H. 1991: Multivariate adaptive regression splines (with discussion). Annals of Statistics, 19.Google Scholar
- Hastie T., Tibshirani R., and Friedman J.H. 2001: The Elements of Statistical Learning, Springer, New York, ISBN 978-0387952840.Google Scholar
- Smola A.J. and Schoelkopf B. 1998: A Tutorial on Support Vector Regression.Google Scholar
- NeuroCOLT2 Technical Report Series, NC2-TR-1998-030, www.neurocolt.com
- Smola A.J. and Schoelkopf B. 2003: A Tutorial on Support Vector Regression, http://eprints.pascal-network.org/archive/00002057/01/SmoSch03b.pdf
- Tendances Carbon 2009: No 33, February 2009. The Monthly Bulletin on the European Carbon Market. In collaboration between Caisse des Dépôts-Mission Climat and Bluenext SA. May.firstname.lastname@example.org, email@example.comGoogle Scholar
- Vapnik V.N. 1995: The Nature of Statistical Learning Theory, Springer, New York.Google Scholar
- Vapnik V.N., Golowich S.E., and Smola A.J. 1996: Support vector method for function approximation, regression estimation, and signal processing. Advances in Neural Information Processing Systems, 9, 281–287.Google Scholar