Combining the wavelet transform and forecasting models to predict gas forward prices

Hang T. Nguyen; Ian T. Nabney

doi:10.1109/ICMLA.2008.37

Combining the wavelet transform and forecasting models to predict gas forward prices

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 energy prices, one day ahead. This technique combines a wavelet transform and forecasting models such as multi- layer perceptron, linear regression or GARCH. These techniques are applied to real data from the UK gas markets to evaluate their performance. The results show that the forecasting accuracy is improved significantly by using the wavelet transform. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

Original language	English
Title of host publication	Seventh International Conference on Machine Learning and Applications, 2008. ICMLA '08
Publisher	IEEE
Pages	311-317
Number of pages	7
ISBN (Print)	9780769534954
DOIs	https://doi.org/10.1109/ICMLA.2008.37
Publication status	Published - 11 Dec 2008

Bibliographical note

Seventh International Conference on Machine Learning and Applications, San Diego (US)

Keywords

forecasting theory
natural gas technology
power markets
power system economics
pricing
wavelet transforms
UK gas market
electricity load
forecasting model
forward energy price
gas forward price prediction
gas load
market clearing price forecasting
wavelet transform
GARCH
linear regression
multi-layer perceptron

Access to Document

10.1109/ICMLA.2008.37

ICMLA08final.pdf
Seventh International Conference on Machine Learning and Applications, San Diego (US)

http://ieeexplore.ieee.org/search/srchabstract.jsp?tp=&arnumber=4724991&queryText%3DCombining+the+wavelet+transform+and+forecasting+models+to+predict+gas+forward+prices%26openedRefinements%3D*%26searchField%3DSearch+All

Cite this

@inbook{d19a1abbd2e644729c1cce4e0c346c07,

title = "Combining the wavelet transform and forecasting models to predict gas forward prices",

abstract = "This paper presents a forecasting technique for forward energy prices, one day ahead. This technique combines a wavelet transform and forecasting models such as multi- layer perceptron, linear regression or GARCH. These techniques are applied to real data from the UK gas markets to evaluate their performance. The results show that the forecasting accuracy is improved significantly by using the wavelet transform. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.",

keywords = "forecasting theory, natural gas technology, power markets, power system economics, pricing, wavelet transforms, UK gas market, electricity load, forecasting model, forward energy price, gas forward price prediction, gas load, market clearing price forecasting, wavelet transform, GARCH, linear regression, multi-layer perceptron",

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

note = "Seventh International Conference on Machine Learning and Applications, San Diego (US)",

year = "2008",

month = dec,

day = "11",

doi = "10.1109/ICMLA.2008.37",

language = "English",

isbn = "9780769534954",

pages = "311--317",

booktitle = "Seventh International Conference on Machine Learning and Applications, 2008. ICMLA '08",

publisher = "IEEE",

address = "United States",

}

TY - CHAP

T1 - Combining the wavelet transform and forecasting models to predict gas forward prices

AU - Nguyen, Hang T.

AU - Nabney, Ian T.

N1 - Seventh International Conference on Machine Learning and Applications, San Diego (US)

PY - 2008/12/11

Y1 - 2008/12/11

N2 - This paper presents a forecasting technique for forward energy prices, one day ahead. This technique combines a wavelet transform and forecasting models such as multi- layer perceptron, linear regression or GARCH. These techniques are applied to real data from the UK gas markets to evaluate their performance. The results show that the forecasting accuracy is improved significantly by using the wavelet transform. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

AB - This paper presents a forecasting technique for forward energy prices, one day ahead. This technique combines a wavelet transform and forecasting models such as multi- layer perceptron, linear regression or GARCH. These techniques are applied to real data from the UK gas markets to evaluate their performance. The results show that the forecasting accuracy is improved significantly by using the wavelet transform. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

KW - forecasting theory

KW - natural gas technology

KW - power markets

KW - power system economics

KW - pricing

KW - wavelet transforms

KW - UK gas market

KW - electricity load

KW - forecasting model

KW - forward energy price

KW - gas forward price prediction

KW - gas load

KW - market clearing price forecasting

KW - wavelet transform

KW - GARCH

KW - linear regression

KW - multi-layer perceptron

UR - http://www.scopus.com/inward/record.url?scp=60649103358&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2008.37

DO - 10.1109/ICMLA.2008.37

M3 - Chapter

SN - 9780769534954

SP - 311

EP - 317

BT - Seventh International Conference on Machine Learning and Applications, 2008. ICMLA '08

PB - IEEE

ER -

Combining the wavelet transform and forecasting models to predict gas forward prices

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this