A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey

Avni Ozozen; Gulgun Kayakutlu; Marcel Ketterer; Ozgur Kayalica

doi:10.1109/PICMET.2016.7806831

A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey

Avni Ozozen, Gulgun Kayakutlu, Marcel Ketterer, Ozgur Kayalica

Department of Management Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

29 Citations (Scopus)

Abstract

Developing countries are trying to improve the competitiveness of the energy markets with continuous liberalization. This makes the market highly sensitive. Every player in the market has a greater need to know about the smallest change in the market. Hence, ability to see what is ahead is a valuable advantage to make the right move. A time series forecasting with the smallest errors would be a powerful tool for the energy producers. This paper proposes combined methodology in time series forecasting. Generally accepted and widely used ARIMA and ANN with backpropagation learning are combined. The methodology is implemented for the day-ahead Turkish power market. It is observed that the proposed methodology gives results with reduced errors. The achievements are compared with conventional use of both ARIMA and ANN.

Original language	English
Title of host publication	PICMET 2016 - Portland International Conference on Management of Engineering and Technology
Subtitle of host publication	Technology Management For Social Innovation, Proceedings
Editors	Timothy R. Anderson, Dundar F. Kocaoglu, Kiyoshi Niwa, Gary Perman, Dilek Cetindamar Kozanoglu, Tugrul U. Daim
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2681-2690
Number of pages	10
ISBN (Electronic)	9781509035953
DOIs	https://doi.org/10.1109/PICMET.2016.7806831
Publication status	Published - 4 Jan 2017
Event	2016 Portland International Conference on Management of Engineering and Technology, PICMET 2016 - Honolulu, United States Duration: 4 Sept 2016 → 8 Sept 2016

Publication series

Name	PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings

Conference

Conference	2016 Portland International Conference on Management of Engineering and Technology, PICMET 2016
Country/Territory	United States
City	Honolulu
Period	4/09/16 → 8/09/16

Bibliographical note

Publisher Copyright:
© 2016 Portland International Conference on Management of Engineering and Technology, Inc.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/PICMET.2016.7806831

Cite this

Ozozen, A., Kayakutlu, G., Ketterer, M., & Kayalica, O. (2017). A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey. In T. R. Anderson, D. F. Kocaoglu, K. Niwa, G. Perman, D. C. Kozanoglu, & T. U. Daim (Eds.), PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings (pp. 2681-2690). Article 7806831 (PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PICMET.2016.7806831

Ozozen, Avni ; Kayakutlu, Gulgun ; Ketterer, Marcel et al. / A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting : Case study in Turkey. PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings. editor / Timothy R. Anderson ; Dundar F. Kocaoglu ; Kiyoshi Niwa ; Gary Perman ; Dilek Cetindamar Kozanoglu ; Tugrul U. Daim. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2681-2690 (PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings).

@inproceedings{098fe04a52974deb877a9f3a6b3e0a19,

title = "A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey",

abstract = "Developing countries are trying to improve the competitiveness of the energy markets with continuous liberalization. This makes the market highly sensitive. Every player in the market has a greater need to know about the smallest change in the market. Hence, ability to see what is ahead is a valuable advantage to make the right move. A time series forecasting with the smallest errors would be a powerful tool for the energy producers. This paper proposes combined methodology in time series forecasting. Generally accepted and widely used ARIMA and ANN with backpropagation learning are combined. The methodology is implemented for the day-ahead Turkish power market. It is observed that the proposed methodology gives results with reduced errors. The achievements are compared with conventional use of both ARIMA and ANN.",

author = "Avni Ozozen and Gulgun Kayakutlu and Marcel Ketterer and Ozgur Kayalica",

note = "Publisher Copyright: {\textcopyright} 2016 Portland International Conference on Management of Engineering and Technology, Inc.; 2016 Portland International Conference on Management of Engineering and Technology, PICMET 2016 ; Conference date: 04-09-2016 Through 08-09-2016",

year = "2017",

month = jan,

day = "4",

doi = "10.1109/PICMET.2016.7806831",

language = "English",

series = "PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2681--2690",

editor = "Anderson, {Timothy R.} and Kocaoglu, {Dundar F.} and Kiyoshi Niwa and Gary Perman and Kozanoglu, {Dilek Cetindamar} and Daim, {Tugrul U.}",

booktitle = "PICMET 2016 - Portland International Conference on Management of Engineering and Technology",

address = "United States",

}

Ozozen, A, Kayakutlu, G, Ketterer, M & Kayalica, O 2017, A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey. in TR Anderson, DF Kocaoglu, K Niwa, G Perman, DC Kozanoglu & TU Daim (eds), PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings., 7806831, PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 2681-2690, 2016 Portland International Conference on Management of Engineering and Technology, PICMET 2016, Honolulu, United States, 4/09/16. https://doi.org/10.1109/PICMET.2016.7806831

A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey. / Ozozen, Avni; Kayakutlu, Gulgun; Ketterer, Marcel et al.
PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings. ed. / Timothy R. Anderson; Dundar F. Kocaoglu; Kiyoshi Niwa; Gary Perman; Dilek Cetindamar Kozanoglu; Tugrul U. Daim. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2681-2690 7806831 (PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting

T2 - 2016 Portland International Conference on Management of Engineering and Technology, PICMET 2016

AU - Ozozen, Avni

AU - Kayakutlu, Gulgun

AU - Ketterer, Marcel

AU - Kayalica, Ozgur

PY - 2017/1/4

Y1 - 2017/1/4

N2 - Developing countries are trying to improve the competitiveness of the energy markets with continuous liberalization. This makes the market highly sensitive. Every player in the market has a greater need to know about the smallest change in the market. Hence, ability to see what is ahead is a valuable advantage to make the right move. A time series forecasting with the smallest errors would be a powerful tool for the energy producers. This paper proposes combined methodology in time series forecasting. Generally accepted and widely used ARIMA and ANN with backpropagation learning are combined. The methodology is implemented for the day-ahead Turkish power market. It is observed that the proposed methodology gives results with reduced errors. The achievements are compared with conventional use of both ARIMA and ANN.

AB - Developing countries are trying to improve the competitiveness of the energy markets with continuous liberalization. This makes the market highly sensitive. Every player in the market has a greater need to know about the smallest change in the market. Hence, ability to see what is ahead is a valuable advantage to make the right move. A time series forecasting with the smallest errors would be a powerful tool for the energy producers. This paper proposes combined methodology in time series forecasting. Generally accepted and widely used ARIMA and ANN with backpropagation learning are combined. The methodology is implemented for the day-ahead Turkish power market. It is observed that the proposed methodology gives results with reduced errors. The achievements are compared with conventional use of both ARIMA and ANN.

UR - http://www.scopus.com/inward/record.url?scp=85016216181&partnerID=8YFLogxK

U2 - 10.1109/PICMET.2016.7806831

DO - 10.1109/PICMET.2016.7806831

M3 - Conference contribution

AN - SCOPUS:85016216181

T3 - PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings

SP - 2681

EP - 2690

BT - PICMET 2016 - Portland International Conference on Management of Engineering and Technology

A2 - Anderson, Timothy R.

A2 - Kocaoglu, Dundar F.

A2 - Niwa, Kiyoshi

A2 - Perman, Gary

A2 - Kozanoglu, Dilek Cetindamar

A2 - Daim, Tugrul U.

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 4 September 2016 through 8 September 2016

ER -

Ozozen A, Kayakutlu G, Ketterer M, Kayalica O. A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey. In Anderson TR, Kocaoglu DF, Niwa K, Perman G, Kozanoglu DC, Daim TU, editors, PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2681-2690. 7806831. (PICMET 2016 - Portland International Conference on Management of Engineering and Technology: Technology Management For Social Innovation, Proceedings). doi: 10.1109/PICMET.2016.7806831

A combined seasonal ARIMA and ANN model for improved results in electricity spot price forecasting: Case study in Turkey

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this