Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural Breaks
This paper develops a new approach to short-term electricity forecasting by focusing upon the dynamic specification of an appropriate calibration dataset prior to model specification. It challenges the conventional forecasting principles which argue that adaptive methods should place most emphasis u...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/13/20/5452 |
id |
doaj-e64f27c48d1b4499b44aa848e01a716a |
---|---|
record_format |
Article |
spelling |
doaj-e64f27c48d1b4499b44aa848e01a716a2020-11-25T03:45:18ZengMDPI AGEnergies1996-10732020-10-01135452545210.3390/en13205452Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural BreaksRodrigo A. de Marcos0Derek W. Bunn1Antonio Bello2Javier Reneses3Institute for Research in Technology, Technical School of Engineering (ICAI), Universidad Pontificia Comillas, 28015 Madrid, SpainManagement Science and Operations, London Business School, London NW1 4SA, UKInstitute for Research in Technology, Technical School of Engineering (ICAI), Universidad Pontificia Comillas, 28015 Madrid, SpainInstitute for Research in Technology, Technical School of Engineering (ICAI), Universidad Pontificia Comillas, 28015 Madrid, SpainThis paper develops a new approach to short-term electricity forecasting by focusing upon the dynamic specification of an appropriate calibration dataset prior to model specification. It challenges the conventional forecasting principles which argue that adaptive methods should place most emphasis upon recent data and that regime-switching should likewise model transitions from the latest regime. The approach in this paper recognises that the most relevant dataset in the episodic, recurrent nature of electricity dynamics may not be the most recent. This methodology provides a dynamic calibration dataset approach that is based on cluster analysis applied to fundamental market regime indicators, as well as structural time series breakpoint analyses. Forecasting is based upon applying a hybrid fundamental optimisation model with a neural network to the appropriate calibration data. The results outperform other benchmark models in backtesting on data from the Iberian electricity market of 2017, which presents a considerable number of market structural breaks and evolving market price drivers.https://www.mdpi.com/1996-1073/13/20/5452day-ahead electricity marketselectricity price forecastingfundamental-econometric modelsmarket structural breaks |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rodrigo A. de Marcos Derek W. Bunn Antonio Bello Javier Reneses |
spellingShingle |
Rodrigo A. de Marcos Derek W. Bunn Antonio Bello Javier Reneses Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural Breaks Energies day-ahead electricity markets electricity price forecasting fundamental-econometric models market structural breaks |
author_facet |
Rodrigo A. de Marcos Derek W. Bunn Antonio Bello Javier Reneses |
author_sort |
Rodrigo A. de Marcos |
title |
Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural Breaks |
title_short |
Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural Breaks |
title_full |
Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural Breaks |
title_fullStr |
Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural Breaks |
title_full_unstemmed |
Short-Term Electricity Price Forecasting with Recurrent Regimes and Structural Breaks |
title_sort |
short-term electricity price forecasting with recurrent regimes and structural breaks |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2020-10-01 |
description |
This paper develops a new approach to short-term electricity forecasting by focusing upon the dynamic specification of an appropriate calibration dataset prior to model specification. It challenges the conventional forecasting principles which argue that adaptive methods should place most emphasis upon recent data and that regime-switching should likewise model transitions from the latest regime. The approach in this paper recognises that the most relevant dataset in the episodic, recurrent nature of electricity dynamics may not be the most recent. This methodology provides a dynamic calibration dataset approach that is based on cluster analysis applied to fundamental market regime indicators, as well as structural time series breakpoint analyses. Forecasting is based upon applying a hybrid fundamental optimisation model with a neural network to the appropriate calibration data. The results outperform other benchmark models in backtesting on data from the Iberian electricity market of 2017, which presents a considerable number of market structural breaks and evolving market price drivers. |
topic |
day-ahead electricity markets electricity price forecasting fundamental-econometric models market structural breaks |
url |
https://www.mdpi.com/1996-1073/13/20/5452 |
work_keys_str_mv |
AT rodrigoademarcos shorttermelectricitypriceforecastingwithrecurrentregimesandstructuralbreaks AT derekwbunn shorttermelectricitypriceforecastingwithrecurrentregimesandstructuralbreaks AT antoniobello shorttermelectricitypriceforecastingwithrecurrentregimesandstructuralbreaks AT javierreneses shorttermelectricitypriceforecastingwithrecurrentregimesandstructuralbreaks |
_version_ |
1724510254944747520 |