A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting

Intan Azmira Wan Abdul Razak, Izham Zainal Abidin, Keem Siah Yap, Aidil Azwin Zainul Abidin, Titik Khawa Abdul Rahman, Mohd Naim Mohd Nasir

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

5 Citations (Scopus)

Abstract

Predicting price has now become an important task in the operation of electrical power system. Day-ahead prediction provides forecast prices for a day ahead that is useful for daily operation and decision-making. The main challenge for day ahead price forecasting is the accuracy and efficiency. Lower accuracy is produced due to the nature of electricity price that is highly volatile compared to load series. Hence, some researchers have developed complex procedures to produce accurate forecast while considering significant features and optimum parameters. Therefore, a multistage optimization for hybrid Least Square Support Vector Machine (LSSVM) and Genetic Algorithm (GA) model is developed in this study to provide an accurate price forecast with optimized parameters and input features. So far, no literature has been found on multistage feature and parameter selections using the methods of LSSVM-GA for day-ahead price prediction. All the models are examined on the Ontario power market; which is reported as among the most volatile market worldwide. A huge number of features are selected by two stages of optimization to avoid from missing any important features. The developed LSSVM-GA shows higher forecast accuracy with lower complexity than the existing models.

Original languageEnglish
Title of host publicationPECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages390-395
Number of pages6
ISBN (Electronic)9781509025473
DOIs
Publication statusPublished - 16 Jun 2017
Event6th IEEE International Conference on Power and Energy, PECON 2016 - Melaka, Malaysia
Duration: 28 Nov 201629 Nov 2016

Publication series

NamePECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding

Other

Other6th IEEE International Conference on Power and Energy, PECON 2016
CountryMalaysia
CityMelaka
Period28/11/1629/11/16

Fingerprint

Support vector machines
Electricity
Genetic algorithms
Decision making
Power markets

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Fuel Technology

Cite this

Razak, I. A. W. A., Zainal Abidin, I., Yap, K. S., Zainul Abidin, A. A., Rahman, T. K. A., & Nasir, M. N. M. (2017). A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting. In PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding (pp. 390-395). [7951593] (PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PECON.2016.7951593
Razak, Intan Azmira Wan Abdul ; Zainal Abidin, Izham ; Yap, Keem Siah ; Zainul Abidin, Aidil Azwin ; Rahman, Titik Khawa Abdul ; Nasir, Mohd Naim Mohd. / A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting. PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 390-395 (PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding).
@inproceedings{d5b1704f665442c79839fe430a3ff4d1,
title = "A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting",
abstract = "Predicting price has now become an important task in the operation of electrical power system. Day-ahead prediction provides forecast prices for a day ahead that is useful for daily operation and decision-making. The main challenge for day ahead price forecasting is the accuracy and efficiency. Lower accuracy is produced due to the nature of electricity price that is highly volatile compared to load series. Hence, some researchers have developed complex procedures to produce accurate forecast while considering significant features and optimum parameters. Therefore, a multistage optimization for hybrid Least Square Support Vector Machine (LSSVM) and Genetic Algorithm (GA) model is developed in this study to provide an accurate price forecast with optimized parameters and input features. So far, no literature has been found on multistage feature and parameter selections using the methods of LSSVM-GA for day-ahead price prediction. All the models are examined on the Ontario power market; which is reported as among the most volatile market worldwide. A huge number of features are selected by two stages of optimization to avoid from missing any important features. The developed LSSVM-GA shows higher forecast accuracy with lower complexity than the existing models.",
author = "Razak, {Intan Azmira Wan Abdul} and {Zainal Abidin}, Izham and Yap, {Keem Siah} and {Zainul Abidin}, {Aidil Azwin} and Rahman, {Titik Khawa Abdul} and Nasir, {Mohd Naim Mohd}",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/PECON.2016.7951593",
language = "English",
series = "PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "390--395",
booktitle = "PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding",
address = "United States",

}

Razak, IAWA, Zainal Abidin, I, Yap, KS, Zainul Abidin, AA, Rahman, TKA & Nasir, MNM 2017, A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting. in PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding., 7951593, PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding, Institute of Electrical and Electronics Engineers Inc., pp. 390-395, 6th IEEE International Conference on Power and Energy, PECON 2016, Melaka, Malaysia, 28/11/16. https://doi.org/10.1109/PECON.2016.7951593

A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting. / Razak, Intan Azmira Wan Abdul; Zainal Abidin, Izham; Yap, Keem Siah; Zainul Abidin, Aidil Azwin; Rahman, Titik Khawa Abdul; Nasir, Mohd Naim Mohd.

PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding. Institute of Electrical and Electronics Engineers Inc., 2017. p. 390-395 7951593 (PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding).

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

TY - GEN

T1 - A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting

AU - Razak, Intan Azmira Wan Abdul

AU - Zainal Abidin, Izham

AU - Yap, Keem Siah

AU - Zainul Abidin, Aidil Azwin

AU - Rahman, Titik Khawa Abdul

AU - Nasir, Mohd Naim Mohd

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Predicting price has now become an important task in the operation of electrical power system. Day-ahead prediction provides forecast prices for a day ahead that is useful for daily operation and decision-making. The main challenge for day ahead price forecasting is the accuracy and efficiency. Lower accuracy is produced due to the nature of electricity price that is highly volatile compared to load series. Hence, some researchers have developed complex procedures to produce accurate forecast while considering significant features and optimum parameters. Therefore, a multistage optimization for hybrid Least Square Support Vector Machine (LSSVM) and Genetic Algorithm (GA) model is developed in this study to provide an accurate price forecast with optimized parameters and input features. So far, no literature has been found on multistage feature and parameter selections using the methods of LSSVM-GA for day-ahead price prediction. All the models are examined on the Ontario power market; which is reported as among the most volatile market worldwide. A huge number of features are selected by two stages of optimization to avoid from missing any important features. The developed LSSVM-GA shows higher forecast accuracy with lower complexity than the existing models.

AB - Predicting price has now become an important task in the operation of electrical power system. Day-ahead prediction provides forecast prices for a day ahead that is useful for daily operation and decision-making. The main challenge for day ahead price forecasting is the accuracy and efficiency. Lower accuracy is produced due to the nature of electricity price that is highly volatile compared to load series. Hence, some researchers have developed complex procedures to produce accurate forecast while considering significant features and optimum parameters. Therefore, a multistage optimization for hybrid Least Square Support Vector Machine (LSSVM) and Genetic Algorithm (GA) model is developed in this study to provide an accurate price forecast with optimized parameters and input features. So far, no literature has been found on multistage feature and parameter selections using the methods of LSSVM-GA for day-ahead price prediction. All the models are examined on the Ontario power market; which is reported as among the most volatile market worldwide. A huge number of features are selected by two stages of optimization to avoid from missing any important features. The developed LSSVM-GA shows higher forecast accuracy with lower complexity than the existing models.

UR - http://www.scopus.com/inward/record.url?scp=85024382225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024382225&partnerID=8YFLogxK

U2 - 10.1109/PECON.2016.7951593

DO - 10.1109/PECON.2016.7951593

M3 - Conference contribution

AN - SCOPUS:85024382225

T3 - PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding

SP - 390

EP - 395

BT - PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Razak IAWA, Zainal Abidin I, Yap KS, Zainul Abidin AA, Rahman TKA, Nasir MNM. A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting. In PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding. Institute of Electrical and Electronics Engineers Inc. 2017. p. 390-395. 7951593. (PECON 2016 - 2016 IEEE 6th International Conference on Power and Energy, Conference Proceeding). https://doi.org/10.1109/PECON.2016.7951593