Modeling real-time balancing power market prices using combined SARIMA and Markov processes
2008 (English)In: IEEE Transactions on Power Systems, ISSN 0885-8950, Vol. 23, no 2, 443-450 p.Article in journal (Refereed) Published
This paper describes modeling of real-time balancingpower market prices by using combined seasonal auto regressiveintegrated moving average (SARIMA) and discrete Markovprocesses. The combination of such processes allows generationof price series with periods where no demand for balancingpower exists. The purpose of the model is simulation of prices toconstruct scenario trees representing possible realization of thestochastic prices. Such scenario trees can be used in planningmodels based on stochastic optimization to generate bid sequencesto the balancing market. The spread of the prices in the treeand the shape of the scenarios are of central importance. Modelparameter estimation methods reflecting the demands on scenariotrees have therefore been used. The proposed model is also appliedto data from the Nordic power market. The conclusion of thispaper is that the developed model is appropriate for modelingreal-time balancing power prices.
Place, publisher, year, edition, pages
2008. Vol. 23, no 2, 443-450 p.
Markov processes, power prices, SARIMA processes, scenario generation, time series analysis
Other Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:kth:diva-10262DOI: 10.1109/TPWRS.2008.920046ISI: 000258765900021ScopusID: 2-s2.0-43849104117OAI: oai:DiVA.org:kth-10262DiVA: diva2:213670
QC 201008042009-04-282009-04-282012-09-17Bibliographically approved