Short Term Load Forecasting Using Machine Learning Algorithms: A Case Study in Turkey

Mikail Purlu; Cenk Andic; Belgin Emre Turkay; Ali Ghadiriasl Nobari

doi:10.1109/GEC55014.2022.9986779

Short Term Load Forecasting Using Machine Learning Algorithms: A Case Study in Turkey

Mikail Purlu, Cenk Andic, Belgin Emre Turkay, Ali Ghadiriasl Nobari

Department of Electrical Engineering

Cumhuriyet University

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

4 Citations (Scopus)

Abstract

In this study, short-term load forecasting of the Gebze region in Turkey was carried out using Machine Learning-based prediction algorithms such as Artificial Neural Networks, Decision Tree, Support Vector Regression and K-Nearest Neighbor. Load demand and weather variables such as temperature, humidity, pressure and wind speed are used as input variables in the forecast models. Error metrics such as Mean Absolute Error, Mean Squared Error, Mean Absolute Percentage Error and R-squared were used to control the prediction success of the proposed algorithms and models. As a result, the predictions made with all the proposed algorithms are within reliable and acceptable ranges, and Support Vector Regression algorithm showed the best performance with an error of 1.1%.

Original language	English
Title of host publication	IEEE Global Energy Conference, GEC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	13-18
Number of pages	6
ISBN (Electronic)	9781665497510
DOIs	https://doi.org/10.1109/GEC55014.2022.9986779
Publication status	Published - 2022
Event	2022 IEEE Global Energy Conference, GEC 2022 - Batman, Turkey Duration: 26 Oct 2022 → 29 Oct 2022

Publication series

Name	IEEE Global Energy Conference, GEC 2022

Conference

Conference	2022 IEEE Global Energy Conference, GEC 2022
Country/Territory	Turkey
City	Batman
Period	26/10/22 → 29/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

decision tree
electricity load forecasting
k-nearest neighbor
machine learning
neural networks
short-term
support vector regression

Access to Document

10.1109/GEC55014.2022.9986779

Cite this

@inproceedings{d0fcc44e7d554581b31d02e34ecaebe1,

title = "Short Term Load Forecasting Using Machine Learning Algorithms: A Case Study in Turkey",

abstract = "In this study, short-term load forecasting of the Gebze region in Turkey was carried out using Machine Learning-based prediction algorithms such as Artificial Neural Networks, Decision Tree, Support Vector Regression and K-Nearest Neighbor. Load demand and weather variables such as temperature, humidity, pressure and wind speed are used as input variables in the forecast models. Error metrics such as Mean Absolute Error, Mean Squared Error, Mean Absolute Percentage Error and R-squared were used to control the prediction success of the proposed algorithms and models. As a result, the predictions made with all the proposed algorithms are within reliable and acceptable ranges, and Support Vector Regression algorithm showed the best performance with an error of 1.1%.",

keywords = "decision tree, electricity load forecasting, k-nearest neighbor, machine learning, neural networks, short-term, support vector regression",

author = "Mikail Purlu and Cenk Andic and Turkay, {Belgin Emre} and Nobari, {Ali Ghadiriasl}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Global Energy Conference, GEC 2022 ; Conference date: 26-10-2022 Through 29-10-2022",

year = "2022",

doi = "10.1109/GEC55014.2022.9986779",

language = "English",

series = "IEEE Global Energy Conference, GEC 2022",

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

pages = "13--18",

booktitle = "IEEE Global Energy Conference, GEC 2022",

address = "United States",

}

Purlu, M, Andic, C , Turkay, BE & Nobari, AG 2022, Short Term Load Forecasting Using Machine Learning Algorithms: A Case Study in Turkey. in IEEE Global Energy Conference, GEC 2022. IEEE Global Energy Conference, GEC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 13-18, 2022 IEEE Global Energy Conference, GEC 2022, Batman, Turkey, 26/10/22. https://doi.org/10.1109/GEC55014.2022.9986779

Short Term Load Forecasting Using Machine Learning Algorithms: A Case Study in Turkey. / Purlu, Mikail; Andic, Cenk ; Turkay, Belgin Emre et al.
IEEE Global Energy Conference, GEC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 13-18 (IEEE Global Energy Conference, GEC 2022).

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

TY - GEN

T1 - Short Term Load Forecasting Using Machine Learning Algorithms

T2 - 2022 IEEE Global Energy Conference, GEC 2022

AU - Purlu, Mikail

AU - Andic, Cenk

AU - Turkay, Belgin Emre

AU - Nobari, Ali Ghadiriasl

PY - 2022

Y1 - 2022

N2 - In this study, short-term load forecasting of the Gebze region in Turkey was carried out using Machine Learning-based prediction algorithms such as Artificial Neural Networks, Decision Tree, Support Vector Regression and K-Nearest Neighbor. Load demand and weather variables such as temperature, humidity, pressure and wind speed are used as input variables in the forecast models. Error metrics such as Mean Absolute Error, Mean Squared Error, Mean Absolute Percentage Error and R-squared were used to control the prediction success of the proposed algorithms and models. As a result, the predictions made with all the proposed algorithms are within reliable and acceptable ranges, and Support Vector Regression algorithm showed the best performance with an error of 1.1%.

AB - In this study, short-term load forecasting of the Gebze region in Turkey was carried out using Machine Learning-based prediction algorithms such as Artificial Neural Networks, Decision Tree, Support Vector Regression and K-Nearest Neighbor. Load demand and weather variables such as temperature, humidity, pressure and wind speed are used as input variables in the forecast models. Error metrics such as Mean Absolute Error, Mean Squared Error, Mean Absolute Percentage Error and R-squared were used to control the prediction success of the proposed algorithms and models. As a result, the predictions made with all the proposed algorithms are within reliable and acceptable ranges, and Support Vector Regression algorithm showed the best performance with an error of 1.1%.

KW - decision tree

KW - electricity load forecasting

KW - k-nearest neighbor

KW - machine learning

KW - neural networks

KW - short-term

KW - support vector regression

UR - http://www.scopus.com/inward/record.url?scp=85146492961&partnerID=8YFLogxK

U2 - 10.1109/GEC55014.2022.9986779

DO - 10.1109/GEC55014.2022.9986779

M3 - Conference contribution

AN - SCOPUS:85146492961

T3 - IEEE Global Energy Conference, GEC 2022

SP - 13

EP - 18

BT - IEEE Global Energy Conference, GEC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 26 October 2022 through 29 October 2022

ER -

Short Term Load Forecasting Using Machine Learning Algorithms: A Case Study in Turkey

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this