A Hidden Markov Model for a Day-Ahead Prediction of Half-Hourly Energy Demand in Romanian Electricity Market

Anatoli Paul Ulmeanu ()
Additional contact information
Anatoli Paul Ulmeanu: Polytechnic University of Bucharest

A chapter in Advances in Reliability Analysis and its Applications, 2020, pp 307-317 from Springer

Abstract: Abstract In this chapter we introduce an original approach to predict a day-ahead energy demand, based on machine learning and pattern recognition. Our Hidden Markov Model (HMM) is a simple and explainable model that uses integer sequences to define emission probability distributions attached to states. We develop a Mathematica code which relies on the maximum likelihood principle in HMM environment. Based on these exploratory results, we conclude that the HMM approach is an efficient way in modeling short-term/day-ahead energy demand prediction, especially during peak period(s) and in accounting for the inherent stochastic nature of demand conditions. The model can be easily extended to predict energy demand values for more than one day in the future. However, the accuracy of such predictions would decrease as we expect.

Keywords: Forecasting; Hidden Markov Model; Energy demand; Pattern recognition (search for similar items in EconPapers)
Date: 2020
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:ssrchp:978-3-030-31375-3_9

Ordering information: This item can be ordered from
http://www.springer.com/9783030313753

DOI: 10.1007/978-3-030-31375-3_9

Access Statistics for this chapter

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