Electric Power Forecasting in Inner Mongolia by Random Forest

Zhi-jun Wei ()
Additional contact information
Zhi-jun Wei: Tianjin University

Chapter Chapter 66 in Proceedings of 2012 3rd International Asia Conference on Industrial Engineering and Management Innovation (IEMI2012), 2013, pp 665-673 from Springer

Abstract: Abstract Demand forecasting is the foundation of planning for electricity power. Time, gross national product and population in Inner Mongolia can be viewed as three important factors influencing power demand. Rank correlation coefficients between them and demand are calculated respectively. The results display strong dependence. The function among them is fitted by Random Forest, a matured algorithm in machine learning. Relative errors of three reserved samples are 5.6, −0.4 and 3.6%. All of them are less than 6%. It is showed that Random Forest is suitable for power demand forecasting. Future gross national product and population are predicted by ARMA time series model. Substituting those values into the fitted function, power demand of 2015 in Inner Mongolia is predicted to be 236,768.07 million kilowatt-hours. The predicted value is helpful to planning development strategy.

Keywords: Forecasting; Power demand; Random Forest (search for similar items in EconPapers)
Date: 2013
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-33012-4_66

Ordering information: This item can be ordered from
http://www.springer.com/9783642330124

DOI: 10.1007/978-3-642-33012-4_66

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().