Short term electricity price forecasting with multistage optimization technique of LSSVM-GA

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

Research output: Contribution to journalArticle

Abstract

Price prediction has now become an important task in the operation of electrical power system. In short term forecast, electricity price can be predicted for an hour-ahead or day-ahead. An hour-ahead prediction offers the market members with the pre-dispatch prices for the next hour. It is useful for an effective bidding strategy where the quantity of bids can be revised or changed prior to the dispatch hour. However, only a few studies have been conducted in the field of hour-ahead forecasting. This is due to most of the power markets apply two-settlement market structure (day-ahead and real time) or standard market design rather than single-settlement system (real time). 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 hour-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 three 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
Pages (from-to)117-122
Number of pages6
JournalJournal of Telecommunication, Electronic and Computer Engineering
Volume9
Issue number2-7
Publication statusPublished - 01 Jan 2017

Fingerprint

Support vector machines
Electricity
Genetic algorithms
Real time systems
Power markets

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

@article{7ce242a547374ae981e95f88bc23bcd1,
title = "Short term electricity price forecasting with multistage optimization technique of LSSVM-GA",
abstract = "Price prediction has now become an important task in the operation of electrical power system. In short term forecast, electricity price can be predicted for an hour-ahead or day-ahead. An hour-ahead prediction offers the market members with the pre-dispatch prices for the next hour. It is useful for an effective bidding strategy where the quantity of bids can be revised or changed prior to the dispatch hour. However, only a few studies have been conducted in the field of hour-ahead forecasting. This is due to most of the power markets apply two-settlement market structure (day-ahead and real time) or standard market design rather than single-settlement system (real time). 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 hour-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 three 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}",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "9",
pages = "117--122",
journal = "Journal of Telecommunication, Electronic and Computer Engineering",
issn = "2180-1843",
publisher = "Universiti Teknikal Malaysia Melaka",
number = "2-7",

}

Short term electricity price forecasting with multistage optimization technique of LSSVM-GA. / Razak, Intan Azmira Wan Abdul; Zainal Abidin, Izham; Yap, Keem Siah; Zainul Abidin, Aidil Azwin; Rahman, Titik Khawa Abdul.

In: Journal of Telecommunication, Electronic and Computer Engineering, Vol. 9, No. 2-7, 01.01.2017, p. 117-122.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Short term electricity price forecasting with multistage optimization technique of LSSVM-GA

AU - Razak, Intan Azmira Wan Abdul

AU - Zainal Abidin, Izham

AU - Yap, Keem Siah

AU - Zainul Abidin, Aidil Azwin

AU - Rahman, Titik Khawa Abdul

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Price prediction has now become an important task in the operation of electrical power system. In short term forecast, electricity price can be predicted for an hour-ahead or day-ahead. An hour-ahead prediction offers the market members with the pre-dispatch prices for the next hour. It is useful for an effective bidding strategy where the quantity of bids can be revised or changed prior to the dispatch hour. However, only a few studies have been conducted in the field of hour-ahead forecasting. This is due to most of the power markets apply two-settlement market structure (day-ahead and real time) or standard market design rather than single-settlement system (real time). 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 hour-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 three 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 - Price prediction has now become an important task in the operation of electrical power system. In short term forecast, electricity price can be predicted for an hour-ahead or day-ahead. An hour-ahead prediction offers the market members with the pre-dispatch prices for the next hour. It is useful for an effective bidding strategy where the quantity of bids can be revised or changed prior to the dispatch hour. However, only a few studies have been conducted in the field of hour-ahead forecasting. This is due to most of the power markets apply two-settlement market structure (day-ahead and real time) or standard market design rather than single-settlement system (real time). 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 hour-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 three 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=85032900285&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032900285&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85032900285

VL - 9

SP - 117

EP - 122

JO - Journal of Telecommunication, Electronic and Computer Engineering

JF - Journal of Telecommunication, Electronic and Computer Engineering

SN - 2180-1843

IS - 2-7

ER -