Time series data mining for energy prices forecasting: An application to real data

Eliana Costa e Silva, Ana Borges, M. Filomena Teodoro, Marina A.P. Andrade, Ricardo Covas

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Recently, at the 119th European Study Group with Industry, the Energy Solutions Operator EDP proposed a challenge concerning electricity prices simulation, not only for risk measures purposes but also for scenario analysis in terms of pricing and strategy. The main purpose was short-term Electricity Price Forecasting (EPF). This analysis is contextualized in the study of time series behavior, in particular multivariate time series, which is considered one of the current challenges in data mining. In this work a short-term EPF analysis making use of vector autoregressive models (VAR) with exogenous variables is proposed. The results show that the multivariate approach using VAR, with the season of the year and the type of day as exogenous variables, yield a model that explains the intra-day and intra-hour dynamics of the hourly prices.

Original languageEnglish
Title of host publicationIntelligent Systems Design and Applications - 16th International Conference on Intelligent Systems Design and Applications, ISDA 2016
EditorsPaulo Novais, Ana Maria Madureira, Ajith Abraham, Dorabela Gamboa
PublisherSpringer Verlag
Pages649-658
Number of pages10
ISBN (Print)9783319534794
DOIs
Publication statusPublished - 1 Jan 2017
Event16th International Conference on Intelligent Systems Design and Applications, ISDA 2016 - Porto, Portugal
Duration: 16 Dec 201618 Dec 2016

Publication series

NameAdvances in Intelligent Systems and Computing
Volume557
ISSN (Print)2194-5357

Conference

Conference16th International Conference on Intelligent Systems Design and Applications, ISDA 2016
CountryPortugal
CityPorto
Period16/12/1618/12/16

Keywords

  • Data mining
  • Electricity prices forecasting
  • Multivariate time series
  • Vector autoregressive models

Fingerprint Dive into the research topics of 'Time series data mining for energy prices forecasting: An application to real data'. Together they form a unique fingerprint.

Cite this