Energy forward price prediction with a hybrid adaptive model

Hang T. Nguyen; Ian T. Nabney

doi:10.1109/CIFER.2009.4937504

Energy forward price prediction with a hybrid adaptive model

Hang T. Nguyen, Ian T. Nabney

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Chapter

Abstract

This paper presents a forecasting technique for forward electricity/gas prices, one day ahead. This technique combines a Kalman filter (KF) and a generalised autoregressive conditional heteroschedasticity (GARCH) model (often used in financial forecasting). The GARCH model is used to compute next value of a time series. The KF updates parameters of the GARCH model when the new observation is available. This technique is applied to real data from the UK energy markets to evaluate its performance. The results show that the forecasting accuracy is improved significantly by using this hybrid model. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

Original language	English
Title of host publication	IEEE Symposium on Computational Intelligence for Financial Engineering, 2009. CIFEr '09
Publisher	IEEE
Pages	66-71
Number of pages	6
ISBN (Print)	9781424427741
DOIs	https://doi.org/10.1109/CIFER.2009.4937504
Publication status	Published - 30 Mar 2009

Bibliographical note

Computational Intelligence for Financial Engineering, CIFEr 2009, Nashville (TN)

Keywords

Kalman filters
autoregressive processes
load forecasting
power markets
GARCH model
Kalman filter
UK energy markets
energy forward price prediction
forecasting technique
forward electricity/gas prices
generalised autoregressive conditional heteroschedasticity model
hybrid adaptive model

Access to Document

10.1109/CIFER.2009.4937504

CIFEr2009.pdf
Computational Intelligence for Financial Engineering, CIFEr 2009, Nashville (TN)

http://ieeexplore.ieee.org/search/srchabstract.jsp?tp=&arnumber=4937504&queryText%3DEnergy+forward+price+prediction+with+a+hybrid+adaptive+model%26openedRefinements%3D*%26searchField%3DSearch+All

Cite this

@inbook{1b06569aa9dd427db4ec205907addd93,

title = "Energy forward price prediction with a hybrid adaptive model",

abstract = "This paper presents a forecasting technique for forward electricity/gas prices, one day ahead. This technique combines a Kalman filter (KF) and a generalised autoregressive conditional heteroschedasticity (GARCH) model (often used in financial forecasting). The GARCH model is used to compute next value of a time series. The KF updates parameters of the GARCH model when the new observation is available. This technique is applied to real data from the UK energy markets to evaluate its performance. The results show that the forecasting accuracy is improved significantly by using this hybrid model. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.",

keywords = "Kalman filters, autoregressive processes, load forecasting, power markets, GARCH model, Kalman filter, UK energy markets, energy forward price prediction, forecasting technique, forward electricity/gas prices, generalised autoregressive conditional heteroschedasticity model, hybrid adaptive model",

author = "Nguyen, {Hang T.} and Nabney, {Ian T.}",

note = "Computational Intelligence for Financial Engineering, CIFEr 2009, Nashville (TN)",

year = "2009",

month = mar,

day = "30",

doi = "10.1109/CIFER.2009.4937504",

language = "English",

isbn = "9781424427741",

pages = "66--71",

booktitle = "IEEE Symposium on Computational Intelligence for Financial Engineering, 2009. CIFEr '09",

publisher = "IEEE",

address = "United States",

}

TY - CHAP

T1 - Energy forward price prediction with a hybrid adaptive model

AU - Nguyen, Hang T.

AU - Nabney, Ian T.

N1 - Computational Intelligence for Financial Engineering, CIFEr 2009, Nashville (TN)

PY - 2009/3/30

Y1 - 2009/3/30

N2 - This paper presents a forecasting technique for forward electricity/gas prices, one day ahead. This technique combines a Kalman filter (KF) and a generalised autoregressive conditional heteroschedasticity (GARCH) model (often used in financial forecasting). The GARCH model is used to compute next value of a time series. The KF updates parameters of the GARCH model when the new observation is available. This technique is applied to real data from the UK energy markets to evaluate its performance. The results show that the forecasting accuracy is improved significantly by using this hybrid model. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

AB - This paper presents a forecasting technique for forward electricity/gas prices, one day ahead. This technique combines a Kalman filter (KF) and a generalised autoregressive conditional heteroschedasticity (GARCH) model (often used in financial forecasting). The GARCH model is used to compute next value of a time series. The KF updates parameters of the GARCH model when the new observation is available. This technique is applied to real data from the UK energy markets to evaluate its performance. The results show that the forecasting accuracy is improved significantly by using this hybrid model. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

KW - Kalman filters

KW - autoregressive processes

KW - load forecasting

KW - power markets

KW - GARCH model

KW - Kalman filter

KW - UK energy markets

KW - energy forward price prediction

KW - forecasting technique

KW - forward electricity/gas prices

KW - generalised autoregressive conditional heteroschedasticity model

KW - hybrid adaptive model

UR - http://www.scopus.com/inward/record.url?scp=69849087908&partnerID=8YFLogxK

U2 - 10.1109/CIFER.2009.4937504

DO - 10.1109/CIFER.2009.4937504

M3 - Chapter

SN - 9781424427741

SP - 66

EP - 71

BT - IEEE Symposium on Computational Intelligence for Financial Engineering, 2009. CIFEr '09

PB - IEEE

ER -

Energy forward price prediction with a hybrid adaptive model

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this