Forecasting day-ahead price spikes for the Ontario electricity market

被引：50

作者：

Sandhu, Harmanjot Singh ^{[1
]}

Fang, Liping ^{[1
]}

Guan, Ling ^{[2
]}

机构：

[1] Ryerson Univ, Dept Mech & Ind Engn, 350 Victoria St, Toronto, ON, Canada

[2] Ryerson Univ, Dept Elect & Comp Engn, 350 Victoria St, Toronto, ON, Canada

来源：

ELECTRIC POWER SYSTEMS RESEARCH | 2016年 / 141卷

基金：

加拿大自然科学与工程研究理事会;

关键词：

Spike forecasting; Price forecasting; Electricity prices; Neural networks; Data mining; CONFIDENCE-INTERVAL ESTIMATION; NEURAL-NETWORK; PREDICTION; MACHINE; MODEL;

D O I：

10.1016/j.epsr.2016.08.005

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A novel methodology based on neural networks is presented to forecast day-ahead electricity spikes and prices. Day-ahead electricity prices are forecasted by the first neural network trained using a data set consisting of similar price days. Next, spike prices are identified from the forecasted prices using a spike classifier, and these spikes are re-forecasted by using neural networks trained over historical spike hours. Finally, a data re-constructor is used to achieve the overall day-ahead electricity spike and price forecasting. Numerical experiments are conducted using data from the wholesale electricity market of Ontario, Canada, and significant improvements are achieved in terms of forecasting accuracy. (C) 2016 Elsevier B.V. All rights reserved.

引用

页码：450 / 459

页数：10

共 34 条

[1] Day-ahead Price Forecasting in Ontario Electricity Market Using Variable-segmented Support Vector Machine-based Model [J].

Aggarwal, S. K. ;

Saini, L. M. ;

Kumar, Ashwani .

ELECTRIC POWER COMPONENTS AND SYSTEMS, 2009, 37 (05) :495-516

[2] A new prediction strategy for price spike forecasting of day-ahead electricity markets [J].

Amjady, Nima ;

Keynia, Farshid .

APPLIED SOFT COMPUTING, 2011, 11 (06) :4246-4256

[3] Electricity market price spike analysis by a hybrid data model and feature selection technique [J].

Amjady, Nima ;

Keynia, Farshid .

ELECTRIC POWER SYSTEMS RESEARCH, 2010, 80 (03) :318-327

[4] Short-term electricity prices forecasting in a competitive market: A neural network approach [J].

Catalao, J. P. S. ;

Mariano, S. J. P. S. ;

Mendes, V. M. F. ;

Ferreira, L. A. F. M. .

ELECTRIC POWER SYSTEMS RESEARCH, 2007, 77 (10) :1297-1304

[5] Forecasting spikes in electricity prices [J].

Christensen, T. M. ;

Hurn, A. S. ;

Lindsay, K. A. .

INTERNATIONAL JOURNAL OF FORECASTING, 2012, 28 (02) :400-411

[6] Forecasting electricity prices for a day-ahead pool-based electric energy market [J].

Conejo, AJ ;

Contreras, J ;

Espínola, R ;

Plazas, MA .

INTERNATIONAL JOURNAL OF FORECASTING, 2005, 21 (03) :435-462

[7] Forecasting electricity spot-prices using linear univariate time-series models [J].

Cuaresma, JC ;

Hlouskova, J ;

Kossmeier, S ;

Obersteiner, M .

APPLIED ENERGY, 2004, 77 (01) :87-106

[8] A RBF neural network model with GARCH errors: Application to electricity price forecasting [J].

dos Santos Coelhoa, Leandro ;

Santos, Andre A. P. .

ELECTRIC POWER SYSTEMS RESEARCH, 2011, 81 (01) :74-83

[9] Models for short-term forecasting of spike occurrences in Australian electricity markets: a comparative study [J].

Eichler, Michael ;

Grothe, Oliver ;

Manner, Hans ;

Tuerk, Dennis .

JOURNAL OF ENERGY MARKETS, 2014, 7 (01) :55-81

[10] A GARCH forecasting model to predict day-ahead electricity prices [J].

Garcia, RC ;

Contreras, J ;

van Akkeren, M ;

Garcia, JBC .

IEEE TRANSACTIONS ON POWER SYSTEMS, 2005, 20 (02) :867-874

← 1 2 3 4 →