Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market

Djamel Benaouda, Fionn Murtagh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Electricity supply industry is in the process of deregulation in many countries including Australia. The purpose of deregulation is to give consumers free choices of their electricity supply. Thus, accurate electricity pool price forecasting can provide a set of vital predicted information that helps generation, transmission and retailer participating companies to bid strategically into a deregulated electricity market in order to maximize their profits. In this article, we propose a wavelet multiscale decomposition based autoregressive approach for the prediction of one-hour ahead and one-day ahead pool price based on historical electricity pool price and predicted electricity load data. This approach is based on a multiple resolution decomposition of the signal using the non-decimated or redundant Haar à trous wavelet transform whose advantage is taking into account the asymmetric nature of the time-varying data. There is an additional computational advantage in that there is no need to re-compute the wavelet transform (wavelet coefficients) of the full signal if the electricity pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive (MAR) method, in both linear and non-linear variants, with single resolution autoregressive (AR), and multilayer perceptron (MLP) model. Experimental results are based on the New South Wales (Australia) electricity load and pool price data that is provided by the National Electricity Market Management Company (NEMMCO).

Original languageEnglish
Title of host publicationIEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006
Number of pages6
DOIs
Publication statusPublished - 18 Sep 2006
Externally publishedYes
EventIEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006 - Islamabad, Pakistan
Duration: 22 Apr 200623 Apr 2006

Conference

ConferenceIEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006
CountryPakistan
CityIslamabad
Period22/04/0623/04/06

Fingerprint

Electricity
Deregulation
Wavelet transforms
Wavelet decomposition
Electric utilities
Multilayer neural networks
Power markets
Time series
Industry
Profitability

Cite this

Benaouda, D., & Murtagh, F. (2006). Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market. In IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006 [1703198] https://doi.org/10.1109/ICEIS.2006.1703198
Benaouda, Djamel ; Murtagh, Fionn. / Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market. IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006. 2006.
@inproceedings{5e33b379cbc6432dae3b138d3a3a6091,
title = "Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market",
abstract = "Electricity supply industry is in the process of deregulation in many countries including Australia. The purpose of deregulation is to give consumers free choices of their electricity supply. Thus, accurate electricity pool price forecasting can provide a set of vital predicted information that helps generation, transmission and retailer participating companies to bid strategically into a deregulated electricity market in order to maximize their profits. In this article, we propose a wavelet multiscale decomposition based autoregressive approach for the prediction of one-hour ahead and one-day ahead pool price based on historical electricity pool price and predicted electricity load data. This approach is based on a multiple resolution decomposition of the signal using the non-decimated or redundant Haar {\`a} trous wavelet transform whose advantage is taking into account the asymmetric nature of the time-varying data. There is an additional computational advantage in that there is no need to re-compute the wavelet transform (wavelet coefficients) of the full signal if the electricity pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive (MAR) method, in both linear and non-linear variants, with single resolution autoregressive (AR), and multilayer perceptron (MLP) model. Experimental results are based on the New South Wales (Australia) electricity load and pool price data that is provided by the National Electricity Market Management Company (NEMMCO).",
keywords = "Autoregression, Multi-layer perceptron, Resolution scale, Time-series, Wavelet transform",
author = "Djamel Benaouda and Fionn Murtagh",
year = "2006",
month = "9",
day = "18",
doi = "10.1109/ICEIS.2006.1703198",
language = "English",
isbn = "1424404568",
booktitle = "IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006",

}

Benaouda, D & Murtagh, F 2006, Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market. in IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006., 1703198, IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006, Islamabad, Pakistan, 22/04/06. https://doi.org/10.1109/ICEIS.2006.1703198

Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market. / Benaouda, Djamel; Murtagh, Fionn.

IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006. 2006. 1703198.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market

AU - Benaouda, Djamel

AU - Murtagh, Fionn

PY - 2006/9/18

Y1 - 2006/9/18

N2 - Electricity supply industry is in the process of deregulation in many countries including Australia. The purpose of deregulation is to give consumers free choices of their electricity supply. Thus, accurate electricity pool price forecasting can provide a set of vital predicted information that helps generation, transmission and retailer participating companies to bid strategically into a deregulated electricity market in order to maximize their profits. In this article, we propose a wavelet multiscale decomposition based autoregressive approach for the prediction of one-hour ahead and one-day ahead pool price based on historical electricity pool price and predicted electricity load data. This approach is based on a multiple resolution decomposition of the signal using the non-decimated or redundant Haar à trous wavelet transform whose advantage is taking into account the asymmetric nature of the time-varying data. There is an additional computational advantage in that there is no need to re-compute the wavelet transform (wavelet coefficients) of the full signal if the electricity pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive (MAR) method, in both linear and non-linear variants, with single resolution autoregressive (AR), and multilayer perceptron (MLP) model. Experimental results are based on the New South Wales (Australia) electricity load and pool price data that is provided by the National Electricity Market Management Company (NEMMCO).

AB - Electricity supply industry is in the process of deregulation in many countries including Australia. The purpose of deregulation is to give consumers free choices of their electricity supply. Thus, accurate electricity pool price forecasting can provide a set of vital predicted information that helps generation, transmission and retailer participating companies to bid strategically into a deregulated electricity market in order to maximize their profits. In this article, we propose a wavelet multiscale decomposition based autoregressive approach for the prediction of one-hour ahead and one-day ahead pool price based on historical electricity pool price and predicted electricity load data. This approach is based on a multiple resolution decomposition of the signal using the non-decimated or redundant Haar à trous wavelet transform whose advantage is taking into account the asymmetric nature of the time-varying data. There is an additional computational advantage in that there is no need to re-compute the wavelet transform (wavelet coefficients) of the full signal if the electricity pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive (MAR) method, in both linear and non-linear variants, with single resolution autoregressive (AR), and multilayer perceptron (MLP) model. Experimental results are based on the New South Wales (Australia) electricity load and pool price data that is provided by the National Electricity Market Management Company (NEMMCO).

KW - Autoregression

KW - Multi-layer perceptron

KW - Resolution scale

KW - Time-series

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=40849092833&partnerID=8YFLogxK

U2 - 10.1109/ICEIS.2006.1703198

DO - 10.1109/ICEIS.2006.1703198

M3 - Conference contribution

SN - 1424404568

SN - 9781424404568

BT - IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006

ER -

Benaouda D, Murtagh F. Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market. In IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006. 2006. 1703198 https://doi.org/10.1109/ICEIS.2006.1703198