Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting

D. Benaouda, F. Murtagh, J. L. Starck, O. Renaud

Research output: Contribution to journalArticle

74 Citations (Scopus)

Abstract

We propose a wavelet multiscale decomposition-based autoregressive approach for the prediction of 1-h ahead load based on historical 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 recompute the wavelet transform (wavelet coefficients) of the full signal if the electricity 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 autoregression (AR), multilayer perceptron (MLP), Elman recurrent neural network (ERN) and the general regression neural network (GRNN) models. Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).

Original languageEnglish
Pages (from-to)139-154
Number of pages16
JournalNeurocomputing
Volume70
Issue number1-3
Early online date6 Jun 2006
DOIs
Publication statusPublished - 1 Dec 2006
Externally publishedYes

Fingerprint

Electricity
Wavelet Analysis
Wavelet transforms
Neural Networks (Computer)
Wavelet decomposition
Recurrent neural networks
Multilayer neural networks
South Australia
New South Wales
Time series
Neural networks
Industry

Cite this

Benaouda, D. ; Murtagh, F. ; Starck, J. L. ; Renaud, O. / Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting. In: Neurocomputing. 2006 ; Vol. 70, No. 1-3. pp. 139-154.
@article{e76fd09f4bf345a8a29c8834b115f66f,
title = "Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting",
abstract = "We propose a wavelet multiscale decomposition-based autoregressive approach for the prediction of 1-h ahead load based on historical 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 recompute the wavelet transform (wavelet coefficients) of the full signal if the electricity 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 autoregression (AR), multilayer perceptron (MLP), Elman recurrent neural network (ERN) and the general regression neural network (GRNN) models. Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).",
keywords = "Autoregression, General regression neural network, Load forecast, Multi-layer perceptron, Recurrent neural network, Resolution, Scale, Time series, Wavelet transform",
author = "D. Benaouda and F. Murtagh and Starck, {J. L.} and O. Renaud",
year = "2006",
month = "12",
day = "1",
doi = "10.1016/j.neucom.2006.04.005",
language = "English",
volume = "70",
pages = "139--154",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "1-3",

}

Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting. / Benaouda, D.; Murtagh, F.; Starck, J. L.; Renaud, O.

In: Neurocomputing, Vol. 70, No. 1-3, 01.12.2006, p. 139-154.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting

AU - Benaouda, D.

AU - Murtagh, F.

AU - Starck, J. L.

AU - Renaud, O.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - We propose a wavelet multiscale decomposition-based autoregressive approach for the prediction of 1-h ahead load based on historical 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 recompute the wavelet transform (wavelet coefficients) of the full signal if the electricity 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 autoregression (AR), multilayer perceptron (MLP), Elman recurrent neural network (ERN) and the general regression neural network (GRNN) models. Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).

AB - We propose a wavelet multiscale decomposition-based autoregressive approach for the prediction of 1-h ahead load based on historical 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 recompute the wavelet transform (wavelet coefficients) of the full signal if the electricity 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 autoregression (AR), multilayer perceptron (MLP), Elman recurrent neural network (ERN) and the general regression neural network (GRNN) models. Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).

KW - Autoregression

KW - General regression neural network

KW - Load forecast

KW - Multi-layer perceptron

KW - Recurrent neural network

KW - Resolution

KW - Scale

KW - Time series

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=33750417685&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2006.04.005

DO - 10.1016/j.neucom.2006.04.005

M3 - Article

VL - 70

SP - 139

EP - 154

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 1-3

ER -