Forecasting Electricity Price in Different Time Horizons: An Application to the Italian Electricity Market

被引：24

作者：

Imani, Mahmood Hosseini ^{[1
]}

Bompard, Ettore ^{[1
]}

Colella, Pietro ^{[1
]}

Huang, Tao ^{[1
]}

机构：

[1] Politecn Torino, Dipartimento Energia, I-10129 Turin, Italy

来源：

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS | 2021年 / 57卷 / 06期

关键词：

Support vector machines; Prediction algorithms; Forecasting; Regression tree analysis; Predictive models; Machine learning algorithms; Artificial neural networks; Different forecasting horizons; electricity price prediction; Italian electricity market; machine learning (ML); prediction error distribution; PUN; GLOBAL SOLAR-RADIATION; NEURAL-NETWORK; REGRESSION TREES; MODELS; CLASSIFICATION; MACHINE; SELECTION;

D O I：

10.1109/TIA.2021.3114129

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Electricity price is a crucial element for market players to maximize their profits. In this context, the forecast of the hour-ahead, day-ahead, and week-ahead electricity prices plays a crucial role. The more accurate the prediction is, the lower the market risk is. In this article, several machine learning algorithms (support vector machine, Gaussian processes regression, regression trees, and multilayer perceptron) with different structures have been adopted to forecast Italian wholesale electricity prices. Considering different time horizons (hourly, daily, and weekly), their performances have been compared through several performance metrics, including mean absolute error, R-index, mean absolute percentage error, and the number of anomalies in which the forecast error passes a threshold. The investigation reveals that, in general, SVM and tree-based models outperform other models at different time horizons.

引用

页码：5726 / 5736

页数：11

共 48 条

[1] KERNEL SMOOTHING OF DATA WITH CORRELATED ERRORS [J].

ALTMAN, NS .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1990, 85 (411) :749-759

[2]

[Anonymous], 2002, LEARNING WITH KERNEL

[3]

[Anonymous], 2004, Introduction to machine learning

[4]

Ardian F., 2016, THESIS U PARIS SACLA

[5] Support vector machine and principal component analysis for microarray data classification [J].

Astuti, Widi ;

Adiwijaya .

INTERNATIONAL CONFERENCE ON DATA AND INFORMATION SCIENCE (ICODIS), 2018, 971

[6] Medium-Term Probabilistic Forecasting of Electricity Prices: A Hybrid Approach [J].

Bello, Antonio ;

Bunn, Derek W. ;

Reneses, Javier ;

Munoz, Antonio .

IEEE TRANSACTIONS ON POWER SYSTEMS, 2017, 32 (01) :334-343

[7]

Breiman L, 1998, ANN STAT, V26, P801

[8] Assessing the potential of support vector machine for estimating daily solar radiation using sunshine duration [J].

Chen, Ji-Long ;

Li, Guo-Sheng ;

Wu, Sheng-Jun .

ENERGY CONVERSION AND MANAGEMENT, 2013, 75 :311-318

[9]

Chivers I., 2015, Intro program fortran, V90, P359, DOI [10.1007/978-3-319-17701-4, DOI 10.1007/978-3-319-17701-4, 10.1007/978-3-319-17701-423, DOI 10.1007/978-3-319-17701-4_23, 10.1007/978-3-319-17701-4_23]

[10] Model selection in neural networks: Some difficulties [J].

Curry, B ;

Morgan, PH .

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2006, 170 (02) :567-577

← 1 2 3 4 5 →