Title: Modelling power spot prices in deregulated European energy markets: a dual long memory approach

Authors: Najeh Chaâbane; Foued Saâdaoui; Saloua Benammou

Addresses: Faculty of Economic Sciences and Management, Erriadh City, 4023 Sousse, Tunisia. ' Computational Mathematics Laboratory, Faculty of Sciences, Avenue de l'Environnement, 5019 Monastir, Tunisia. ' Faculty of Economic Sciences and Management, Erriadh City, 4023 Sousse, Tunisia

Abstract: In the last decade, with deregulation and introduction of competition in power markets, prices forecasting have become a real challenge for all market participants. However, forecasting is a rather complex task since electricity prices involve many features comparably with financial ones. Electricity markets have a highly volatile nature. They are indeed a more unpredictable than that of other commodities referred to as extreme volatile. In this paper, the two most emerging European electricity markets are considered. A preliminary analysis of the time series attests to the presence of a long range dependance behaviour. Therefore, prices processes are modelled using ARFIMA-FIGARCH under Gaussian and non-Gaussian distributions. Such models are sufficiently flexible to handle the long memory phenomena often encountered in both conditional mean and conditional variance in electricity spot prices. Forecasting is subsequently performed on the basis of adequate models.

Keywords: electricity spot prices; European electricity markets; long memory; ARFIMA-FIGARCH model; non-Gaussian distributions; forecasting; modelling; power spot prices; deregulated markets; European energy markets.

DOI: 10.1504/GBER.2012.049870

Global Business and Economics Review, 2012 Vol.14 No.4, pp.338 - 361

Received: 26 Aug 2011
Accepted: 07 Jul 2012

Published online: 29 Jul 2014 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article