AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach

Imaduddin; Rizka Widyarini Purwanto; Whisnu Febry Afrianto; Ivan Butar Butar; Aditya Putranto

doi:10.1109/ICT-PEP63827.2024.10733523

AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach

Imaduddin, Rizka Widyarini Purwanto, Whisnu Febry Afrianto, Ivan Butar Butar, Aditya Putranto

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

Abstract

This study applies ML (Machine Learning) techniques to enhance the efficiency of Electric Vehicle (EV) Charging Station (EVCS) load demand management in Indonesia, leveraging data from the PLN-Mobile application. It addresses the limitations of past research models by incorporating specific user behavior characteristics and EVCS location features into the forecasting model, aiming to provide a more accurate prediction of EVCS load demand. Through a comprehensive Exploratory Data Analysis (EDA) process and the evaluation of six regression models (Decision Tree, Random Forest, Gradient-Boost, XGBoost, Light GBM, and CatBoost) the study concludes that specific user behavior characteristics and EVCS location features had influenced load demand predictions, contributing to the broader discourse on the application of AI and ML in the energy sector. The best accuracy was given at $R^{2}$ 0.958 with CatBoost using 23 features.

Original language	English
Title of host publication	ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power
Subtitle of host publication	Book of Proceedings
Editors	Persero
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	106-111
Number of pages	6
ISBN (Electronic)	9798331518646
ISBN (Print)	9798331518653
DOIs	https://doi.org/10.1109/ICT-PEP63827.2024.10733523
Publication status	Published - 2024
Event	International Conference on Technology and Policy in Energy and Electric Power 2024 - Bali, Indonesia Duration: 3 Sept 2024 → 5 Sept 2024 https://ieeexplore.ieee.org/xpl/conhome/10733349/proceeding (Proceedings) https://web.archive.org/web/20241203133023/https://www.ict-pep-pln.com/ (Website)

Conference

Conference	International Conference on Technology and Policy in Energy and Electric Power 2024
Abbreviated title	ICT-PEP 2024
Country/Territory	Indonesia
City	Bali
Period	3/09/24 → 5/09/24
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10733349/proceeding (Proceedings) https://web.archive.org/web/20241203133023/https://www.ict-pep-pln.com/ (Website)

Keywords

catboost
decision tree
electric vehicle charging station
gradient-boost
light gbm
load demand prediction
machine learning
random forest
xgboost

UN SDGs

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

Access to Document

10.1109/ICT-PEP63827.2024.10733523

Cite this

Imaduddin, Purwanto, R. W., Afrianto, W. F., Butar, I. B., & Putranto, A. (2024). AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach. In P. (Ed.), ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power: Book of Proceedings (pp. 106-111). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICT-PEP63827.2024.10733523

Imaduddin ; Purwanto, Rizka Widyarini ; Afrianto, Whisnu Febry et al. / AI - Driven Prediction of EV Charging Station Load Demand in Indonesia : A Machine Learning Approach. ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power: Book of Proceedings. editor / Persero. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2024. pp. 106-111

@inproceedings{572fc62c940c4b11b2ae63b46fb3046d,

title = "AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach",

abstract = "This study applies ML (Machine Learning) techniques to enhance the efficiency of Electric Vehicle (EV) Charging Station (EVCS) load demand management in Indonesia, leveraging data from the PLN-Mobile application. It addresses the limitations of past research models by incorporating specific user behavior characteristics and EVCS location features into the forecasting model, aiming to provide a more accurate prediction of EVCS load demand. Through a comprehensive Exploratory Data Analysis (EDA) process and the evaluation of six regression models (Decision Tree, Random Forest, Gradient-Boost, XGBoost, Light GBM, and CatBoost) the study concludes that specific user behavior characteristics and EVCS location features had influenced load demand predictions, contributing to the broader discourse on the application of AI and ML in the energy sector. The best accuracy was given at $R^{2}$ 0.958 with CatBoost using 23 features.",

keywords = "catboost, decision tree, electric vehicle charging station, gradient-boost, light gbm, load demand prediction, machine learning, random forest, xgboost",

author = "Imaduddin and Purwanto, {Rizka Widyarini} and Afrianto, {Whisnu Febry} and Butar, {Ivan Butar} and Aditya Putranto",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; International Conference on Technology and Policy in Energy and Electric Power 2024, ICT-PEP 2024 ; Conference date: 03-09-2024 Through 05-09-2024",

year = "2024",

doi = "10.1109/ICT-PEP63827.2024.10733523",

language = "English",

isbn = "9798331518653",

pages = "106--111",

editor = "Persero",

booktitle = "ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/10733349/proceeding, https://web.archive.org/web/20241203133023/https://www.ict-pep-pln.com/",

}

Imaduddin, Purwanto, RW, Afrianto, WF, Butar, IB & Putranto, A 2024, AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach. in P (ed.), ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power: Book of Proceedings. IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 106-111, International Conference on Technology and Policy in Energy and Electric Power 2024, Bali, Indonesia, 3/09/24. https://doi.org/10.1109/ICT-PEP63827.2024.10733523

AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach. / Imaduddin; Purwanto, Rizka Widyarini; Afrianto, Whisnu Febry et al.
ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power: Book of Proceedings. ed. / Persero. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2024. p. 106-111.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

TY - GEN

T1 - AI - Driven Prediction of EV Charging Station Load Demand in Indonesia

T2 - International Conference on Technology and Policy in Energy and Electric Power 2024

AU - Imaduddin,

AU - Purwanto, Rizka Widyarini

AU - Afrianto, Whisnu Febry

AU - Butar, Ivan Butar

AU - Putranto, Aditya

PY - 2024

Y1 - 2024

N2 - This study applies ML (Machine Learning) techniques to enhance the efficiency of Electric Vehicle (EV) Charging Station (EVCS) load demand management in Indonesia, leveraging data from the PLN-Mobile application. It addresses the limitations of past research models by incorporating specific user behavior characteristics and EVCS location features into the forecasting model, aiming to provide a more accurate prediction of EVCS load demand. Through a comprehensive Exploratory Data Analysis (EDA) process and the evaluation of six regression models (Decision Tree, Random Forest, Gradient-Boost, XGBoost, Light GBM, and CatBoost) the study concludes that specific user behavior characteristics and EVCS location features had influenced load demand predictions, contributing to the broader discourse on the application of AI and ML in the energy sector. The best accuracy was given at $R^{2}$ 0.958 with CatBoost using 23 features.

AB - This study applies ML (Machine Learning) techniques to enhance the efficiency of Electric Vehicle (EV) Charging Station (EVCS) load demand management in Indonesia, leveraging data from the PLN-Mobile application. It addresses the limitations of past research models by incorporating specific user behavior characteristics and EVCS location features into the forecasting model, aiming to provide a more accurate prediction of EVCS load demand. Through a comprehensive Exploratory Data Analysis (EDA) process and the evaluation of six regression models (Decision Tree, Random Forest, Gradient-Boost, XGBoost, Light GBM, and CatBoost) the study concludes that specific user behavior characteristics and EVCS location features had influenced load demand predictions, contributing to the broader discourse on the application of AI and ML in the energy sector. The best accuracy was given at $R^{2}$ 0.958 with CatBoost using 23 features.

KW - catboost

KW - decision tree

KW - electric vehicle charging station

KW - gradient-boost

KW - light gbm

KW - load demand prediction

KW - machine learning

KW - random forest

KW - xgboost

UR - http://www.scopus.com/inward/record.url?scp=85210876998&partnerID=8YFLogxK

U2 - 10.1109/ICT-PEP63827.2024.10733523

DO - 10.1109/ICT-PEP63827.2024.10733523

M3 - Conference Paper

AN - SCOPUS:85210876998

SN - 9798331518653

SP - 106

EP - 111

BT - ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power

A2 - , Persero

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

Y2 - 3 September 2024 through 5 September 2024

ER -

Imaduddin, Purwanto RW, Afrianto WF, Butar IB, Putranto A. AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach. In P, editor, ICT-PEP 2024 - International Conference on Technology and Policy in Energy and Electric Power: Book of Proceedings. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2024. p. 106-111 doi: 10.1109/ICT-PEP63827.2024.10733523

AI - Driven Prediction of EV Charging Station Load Demand in Indonesia: A Machine Learning Approach

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Cite this