Electricity Load Forecast using Neural Network Trained from Wavelet-Transformed Data

Djamel Benaouda; Fionn Murtagh

doi:10.1109/ICEIS.2006.1703163

Electricity Load Forecast using Neural Network Trained from Wavelet-Transformed Data

Djamel Benaouda, Fionn Murtagh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

9 Citations (Scopus)

Abstract

With accurate electricity load forecasting important information is provided that helps to build up cost effective risk management plans for any electric utility such as electricity generators and retailers in the electricity market. In this article, we propose a wavelet based multilayer perceptron (MLPw) approach for the prediction of one-hour and one-day ahead load trained from Haar à trous wavelet-transformed historical electricity load data. We assess results produced by the MLPw method, with multiple resolution autoregressive (MAR), single resolution autoregressive (AR), multilayer perceptron (MLP), and the general regression neural network (GRNN) model. Experimental Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).

Original language	English
Title of host publication	2006 IEEE International Conference on Engineering of Intelligent Systems (ICEIS 2006)
Publisher	IEEE
Number of pages	6
ISBN (Print)	1424404568, 9781424404568
DOIs	https://doi.org/10.1109/ICEIS.2006.1703163
Publication status	Published - 18 Sep 2006
Externally published	Yes
Event	IEEE International Conference on Engineering of Intelligent Systems - Islamabad, Pakistan Duration: 22 Apr 2006 → 23 Apr 2006

Conference

Conference	IEEE International Conference on Engineering of Intelligent Systems
Abbreviated title	ICEIS 2006
Country/Territory	Pakistan
City	Islamabad
Period	22/04/06 → 23/04/06

Access to Document

10.1109/ICEIS.2006.1703163Licence: Unspecified

Cite this

@inproceedings{0482722987e24248951fe253d934e111,

title = "Electricity Load Forecast using Neural Network Trained from Wavelet-Transformed Data",

abstract = "With accurate electricity load forecasting important information is provided that helps to build up cost effective risk management plans for any electric utility such as electricity generators and retailers in the electricity market. In this article, we propose a wavelet based multilayer perceptron (MLPw) approach for the prediction of one-hour and one-day ahead load trained from Haar {\`a} trous wavelet-transformed historical electricity load data. We assess results produced by the MLPw method, with multiple resolution autoregressive (MAR), single resolution autoregressive (AR), multilayer perceptron (MLP), and the general regression neural network (GRNN) model. Experimental Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).",

keywords = "Multi-layer perceptron, Resolution scale, Wavelet transforms",

author = "Djamel Benaouda and Fionn Murtagh",

year = "2006",

month = sep,

day = "18",

doi = "10.1109/ICEIS.2006.1703163",

language = "English",

isbn = "1424404568",

booktitle = "2006 IEEE International Conference on Engineering of Intelligent Systems (ICEIS 2006)",

publisher = "IEEE",

address = "United States",

note = "IEEE International Conference on Engineering of Intelligent Systems, ICEIS 2006 ; Conference date: 22-04-2006 Through 23-04-2006",

}

TY - GEN

T1 - Electricity Load Forecast using Neural Network Trained from Wavelet-Transformed Data

AU - Benaouda, Djamel

AU - Murtagh, Fionn

PY - 2006/9/18

Y1 - 2006/9/18

N2 - With accurate electricity load forecasting important information is provided that helps to build up cost effective risk management plans for any electric utility such as electricity generators and retailers in the electricity market. In this article, we propose a wavelet based multilayer perceptron (MLPw) approach for the prediction of one-hour and one-day ahead load trained from Haar à trous wavelet-transformed historical electricity load data. We assess results produced by the MLPw method, with multiple resolution autoregressive (MAR), single resolution autoregressive (AR), multilayer perceptron (MLP), and the general regression neural network (GRNN) model. Experimental Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).

AB - With accurate electricity load forecasting important information is provided that helps to build up cost effective risk management plans for any electric utility such as electricity generators and retailers in the electricity market. In this article, we propose a wavelet based multilayer perceptron (MLPw) approach for the prediction of one-hour and one-day ahead load trained from Haar à trous wavelet-transformed historical electricity load data. We assess results produced by the MLPw method, with multiple resolution autoregressive (MAR), single resolution autoregressive (AR), multilayer perceptron (MLP), and the general regression neural network (GRNN) model. Experimental Results are based on the New South Wales (Australia) electricity load data that is provided by the National Electricity Market Management Company (NEMMCO).

KW - Multi-layer perceptron

KW - Resolution scale

KW - Wavelet transforms

UR - http://www.scopus.com/inward/record.url?scp=40849113353&partnerID=8YFLogxK

U2 - 10.1109/ICEIS.2006.1703163

DO - 10.1109/ICEIS.2006.1703163

M3 - Conference contribution

AN - SCOPUS:40849113353

SN - 1424404568

SN - 9781424404568

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

PB - IEEE

T2 - IEEE International Conference on Engineering of Intelligent Systems

Y2 - 22 April 2006 through 23 April 2006

ER -

Electricity Load Forecast using Neural Network Trained from Wavelet-Transformed Data

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this