Short term load forecasting using a hybrid neural network

Keem Siah Yap, Izham Zainal Abidin, Chee Peng Lim, Mohd Suhairi Shah

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

5 Citations (Scopus)

Abstract

Short Term Load Forecasting (STLF) is very important from the power systems grid operation point of view. STLF involves forecasting load demand in a short term time frame. The short term time frame may consist of half hourly prediction up to weekly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the STLF using a novel hybrid online learning neural network, known as the Gaussian Regression (GR). This new hybrid neural network is a combination of two existing online learning neural networks which are the Gaussian Adaptive Resonance Theory (GA) and the Generalized Regression Neural Network (GRNN). Both GA and GRNN implemented online learning, but each of them suffers from limitation. Originally GA is used for unsupervised clustering by compressing the training samples into several categories. A supervised version of GA is available, namely Gaussian ARTMAP (GAM). However, the GAM is still not capable on solving regression problem. On the other hand, GRNN is designed for solving real value estimation (regression) problem, but the learning process would involve of memorizing all training samples, hence high computational cost. The hybrid GR is considered an enhanced version of GRNN with compression ability while still maintains online learning properties. Simulation results show that GR has comparable prediction accuracy and has less prototype as compared to the original GRNN as well as the Support Vector Regression.

Original languageEnglish
Title of host publicationFirst International Power and Energy Conference, (PECon 2006) Proceedings
Pages123-128
Number of pages6
DOIs
Publication statusPublished - 01 Dec 2006
Event1st International Power and Energy Conference, PECon 2006 - Putrajaya, Malaysia
Duration: 28 Nov 200629 Nov 2006

Other

Other1st International Power and Energy Conference, PECon 2006
CountryMalaysia
CityPutrajaya
Period28/11/0629/11/06

Fingerprint

Neural networks
Costs
Industry

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology

Cite this

Yap, K. S., Zainal Abidin, I., Lim, C. P., & Shah, M. S. (2006). Short term load forecasting using a hybrid neural network. In First International Power and Energy Conference, (PECon 2006) Proceedings (pp. 123-128). [4154476] https://doi.org/10.1109/PECON.2006.346632
Yap, Keem Siah ; Zainal Abidin, Izham ; Lim, Chee Peng ; Shah, Mohd Suhairi. / Short term load forecasting using a hybrid neural network. First International Power and Energy Conference, (PECon 2006) Proceedings. 2006. pp. 123-128
@inproceedings{39f42fade59e4951abbf101a6b835428,
title = "Short term load forecasting using a hybrid neural network",
abstract = "Short Term Load Forecasting (STLF) is very important from the power systems grid operation point of view. STLF involves forecasting load demand in a short term time frame. The short term time frame may consist of half hourly prediction up to weekly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the STLF using a novel hybrid online learning neural network, known as the Gaussian Regression (GR). This new hybrid neural network is a combination of two existing online learning neural networks which are the Gaussian Adaptive Resonance Theory (GA) and the Generalized Regression Neural Network (GRNN). Both GA and GRNN implemented online learning, but each of them suffers from limitation. Originally GA is used for unsupervised clustering by compressing the training samples into several categories. A supervised version of GA is available, namely Gaussian ARTMAP (GAM). However, the GAM is still not capable on solving regression problem. On the other hand, GRNN is designed for solving real value estimation (regression) problem, but the learning process would involve of memorizing all training samples, hence high computational cost. The hybrid GR is considered an enhanced version of GRNN with compression ability while still maintains online learning properties. Simulation results show that GR has comparable prediction accuracy and has less prototype as compared to the original GRNN as well as the Support Vector Regression.",
author = "Yap, {Keem Siah} and {Zainal Abidin}, Izham and Lim, {Chee Peng} and Shah, {Mohd Suhairi}",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/PECON.2006.346632",
language = "English",
isbn = "1424402735",
pages = "123--128",
booktitle = "First International Power and Energy Conference, (PECon 2006) Proceedings",

}

Yap, KS, Zainal Abidin, I, Lim, CP & Shah, MS 2006, Short term load forecasting using a hybrid neural network. in First International Power and Energy Conference, (PECon 2006) Proceedings., 4154476, pp. 123-128, 1st International Power and Energy Conference, PECon 2006, Putrajaya, Malaysia, 28/11/06. https://doi.org/10.1109/PECON.2006.346632

Short term load forecasting using a hybrid neural network. / Yap, Keem Siah; Zainal Abidin, Izham; Lim, Chee Peng; Shah, Mohd Suhairi.

First International Power and Energy Conference, (PECon 2006) Proceedings. 2006. p. 123-128 4154476.

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

TY - GEN

T1 - Short term load forecasting using a hybrid neural network

AU - Yap, Keem Siah

AU - Zainal Abidin, Izham

AU - Lim, Chee Peng

AU - Shah, Mohd Suhairi

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Short Term Load Forecasting (STLF) is very important from the power systems grid operation point of view. STLF involves forecasting load demand in a short term time frame. The short term time frame may consist of half hourly prediction up to weekly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the STLF using a novel hybrid online learning neural network, known as the Gaussian Regression (GR). This new hybrid neural network is a combination of two existing online learning neural networks which are the Gaussian Adaptive Resonance Theory (GA) and the Generalized Regression Neural Network (GRNN). Both GA and GRNN implemented online learning, but each of them suffers from limitation. Originally GA is used for unsupervised clustering by compressing the training samples into several categories. A supervised version of GA is available, namely Gaussian ARTMAP (GAM). However, the GAM is still not capable on solving regression problem. On the other hand, GRNN is designed for solving real value estimation (regression) problem, but the learning process would involve of memorizing all training samples, hence high computational cost. The hybrid GR is considered an enhanced version of GRNN with compression ability while still maintains online learning properties. Simulation results show that GR has comparable prediction accuracy and has less prototype as compared to the original GRNN as well as the Support Vector Regression.

AB - Short Term Load Forecasting (STLF) is very important from the power systems grid operation point of view. STLF involves forecasting load demand in a short term time frame. The short term time frame may consist of half hourly prediction up to weekly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the STLF using a novel hybrid online learning neural network, known as the Gaussian Regression (GR). This new hybrid neural network is a combination of two existing online learning neural networks which are the Gaussian Adaptive Resonance Theory (GA) and the Generalized Regression Neural Network (GRNN). Both GA and GRNN implemented online learning, but each of them suffers from limitation. Originally GA is used for unsupervised clustering by compressing the training samples into several categories. A supervised version of GA is available, namely Gaussian ARTMAP (GAM). However, the GAM is still not capable on solving regression problem. On the other hand, GRNN is designed for solving real value estimation (regression) problem, but the learning process would involve of memorizing all training samples, hence high computational cost. The hybrid GR is considered an enhanced version of GRNN with compression ability while still maintains online learning properties. Simulation results show that GR has comparable prediction accuracy and has less prototype as compared to the original GRNN as well as the Support Vector Regression.

UR - http://www.scopus.com/inward/record.url?scp=46249091355&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46249091355&partnerID=8YFLogxK

U2 - 10.1109/PECON.2006.346632

DO - 10.1109/PECON.2006.346632

M3 - Conference contribution

SN - 1424402735

SN - 9781424402731

SP - 123

EP - 128

BT - First International Power and Energy Conference, (PECon 2006) Proceedings

ER -

Yap KS, Zainal Abidin I, Lim CP, Shah MS. Short term load forecasting using a hybrid neural network. In First International Power and Energy Conference, (PECon 2006) Proceedings. 2006. p. 123-128. 4154476 https://doi.org/10.1109/PECON.2006.346632