Neuro-Wavelet Approach to Time-Series Signals Prediction

An Example of Electricity Load and Pool-Price Data

Djamel Benaouda, Fionn Murtagh

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Accurate electricity load and 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 and increase returns to their stakeholders. Although a number of forecasting methods have been proposed to solve the shortterm and long-term electricity load forecast, pool-price forecasting is a relatively new research area. In this article, we propose an autoregressive approach, based on a wavelet multiscale decomposition, for the prediction of one-hour ahead load and pool price based respectively on historical electricity load, and pool-price data. This approach is based on a multiple resolution decomposition of the signal using the 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 and pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive method, in both linear and nonlinear variants, with single resolution autoregressive, multilayer perceptron, Elman recurrent neural network and the general regression neural network models. The input data consists of historical load and pool price data, which is collected over a period of 3 years (1999-2001), used for training, and 1 year (2002) used for testing. 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.

Original languageEnglish
Article number5
JournalInternational Journal of Emerging Electric Power Systems
Volume8
Issue number2
DOIs
Publication statusPublished - 2007
Externally publishedYes

Fingerprint

Time series
Electricity
Wavelet transforms
Wavelet decomposition
Recurrent neural networks
Multilayer neural networks
Industry
Profitability
Neural networks
Testing
Power markets

Cite this

@article{b825cb6f22d448fbba3ef5b63dffee6d,
title = "Neuro-Wavelet Approach to Time-Series Signals Prediction: An Example of Electricity Load and Pool-Price Data",
abstract = "Accurate electricity load and 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 and increase returns to their stakeholders. Although a number of forecasting methods have been proposed to solve the shortterm and long-term electricity load forecast, pool-price forecasting is a relatively new research area. In this article, we propose an autoregressive approach, based on a wavelet multiscale decomposition, for the prediction of one-hour ahead load and pool price based respectively on historical electricity load, and pool-price data. This approach is based on a multiple resolution decomposition of the signal using the 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 and pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive method, in both linear and nonlinear variants, with single resolution autoregressive, multilayer perceptron, Elman recurrent neural network and the general regression neural network models. The input data consists of historical load and pool price data, which is collected over a period of 3 years (1999-2001), used for training, and 1 year (2002) used for testing. 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.",
keywords = "Artificial neural networks, Autoregression, Load forecast, Pool-price forecast, Resolution, Scale, Time-series, Wavelet transform",
author = "Djamel Benaouda and Fionn Murtagh",
year = "2007",
doi = "10.2202/1553-779X.1404",
language = "English",
volume = "8",
journal = "International Journal of Emerging Electric Power Systems",
issn = "1553-779X",
publisher = "Walter de Gruyter GmbH",
number = "2",

}

TY - JOUR

T1 - Neuro-Wavelet Approach to Time-Series Signals Prediction

T2 - An Example of Electricity Load and Pool-Price Data

AU - Benaouda, Djamel

AU - Murtagh, Fionn

PY - 2007

Y1 - 2007

N2 - Accurate electricity load and 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 and increase returns to their stakeholders. Although a number of forecasting methods have been proposed to solve the shortterm and long-term electricity load forecast, pool-price forecasting is a relatively new research area. In this article, we propose an autoregressive approach, based on a wavelet multiscale decomposition, for the prediction of one-hour ahead load and pool price based respectively on historical electricity load, and pool-price data. This approach is based on a multiple resolution decomposition of the signal using the 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 and pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive method, in both linear and nonlinear variants, with single resolution autoregressive, multilayer perceptron, Elman recurrent neural network and the general regression neural network models. The input data consists of historical load and pool price data, which is collected over a period of 3 years (1999-2001), used for training, and 1 year (2002) used for testing. 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.

AB - Accurate electricity load and 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 and increase returns to their stakeholders. Although a number of forecasting methods have been proposed to solve the shortterm and long-term electricity load forecast, pool-price forecasting is a relatively new research area. In this article, we propose an autoregressive approach, based on a wavelet multiscale decomposition, for the prediction of one-hour ahead load and pool price based respectively on historical electricity load, and pool-price data. This approach is based on a multiple resolution decomposition of the signal using the 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 and pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive method, in both linear and nonlinear variants, with single resolution autoregressive, multilayer perceptron, Elman recurrent neural network and the general regression neural network models. The input data consists of historical load and pool price data, which is collected over a period of 3 years (1999-2001), used for training, and 1 year (2002) used for testing. 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.

KW - Artificial neural networks

KW - Autoregression

KW - Load forecast

KW - Pool-price forecast

KW - Resolution

KW - Scale

KW - Time-series

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=33846986013&partnerID=8YFLogxK

U2 - 10.2202/1553-779X.1404

DO - 10.2202/1553-779X.1404

M3 - Article

VL - 8

JO - International Journal of Emerging Electric Power Systems

JF - International Journal of Emerging Electric Power Systems

SN - 1553-779X

IS - 2

M1 - 5

ER -