Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism

Silvana Matrone; Amirhossein  Heydarian Ardakani; Emanuele Ogliari; Elham Shirazi; Sonia Leva

doi:10.1145/3679240.3734687

Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism

Silvana Matrone^*
, Amirhossein Heydarian Ardakani
, Emanuele Ogliari
, Elham Shirazi
, Sonia Leva

^*Corresponding author for this work

Advanced Manufacturing, Sustainable Products & Energy Systems

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

4 Citations (Scopus)

14 Downloads (Pure)

Abstract

The electrification of transportation has significantly increased electric vehicle (EV) charging demand on energy systems. Accurately capturing the uncertainty of future EV loads is essential for flexible system operation. This study proposes an LSTM-attention model for probabilistic EV load forecasting, featuring an encoder-decoder architecture with an intermediate attention layer. Using Quantile Regression (QR), the model predicts upper, median, and lower load quantiles. Evaluation is performed on parking station data from the SmoothEMS Met GridShield project in the Netherlands.

Original language	English
Title of host publication	E-ENERGY '25
Subtitle of host publication	Proceedings of the 2025 16th ACM International Conference on Future and Sustainable Energy Systems
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	1005-1007
Number of pages	3
ISBN (Electronic)	979-8-4007-1125-1
DOIs	https://doi.org/10.1145/3679240.3734687
Publication status	Published - 17 Jun 2025
Event	16th ACM International Conference on Future and Sustainable Energy Systems, ACM E-Energy 2025 - Nhow Rotterdam Hotel, Rotterdam, Netherlands Duration: 17 Jun 2025 → 20 Jun 2025 Conference number: 16 https://energy.acm.org/conferences/eenergy/2025/

Publication series

Name	E-ENERGY Conference Proceedings
Publisher	ACM
Volume	2025

Conference

Conference	16th ACM International Conference on Future and Sustainable Energy Systems, ACM E-Energy 2025
Abbreviated title	ACM E-Energy 2025
Country/Territory	Netherlands
City	Rotterdam
Period	17/06/25 → 20/06/25
Internet address	https://energy.acm.org/conferences/eenergy/2025/

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Electric Vehicles
EV Load Forecast
Long Short-Term Memory
Probabilistic Forecast
Quantile Regression

Access to Document

10.1145/3679240.3734687Licence: CC BY

Conference paperFinal published version, 774 KBLicence: CC BY

Cite this

Matrone, S., Heydarian Ardakani, A., Ogliari, E., Shirazi, E., & Leva, S. (2025). Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism. In E-ENERGY '25: Proceedings of the 2025 16th ACM International Conference on Future and Sustainable Energy Systems (pp. 1005-1007). (E-ENERGY Conference Proceedings; Vol. 2025). Association for Computing Machinery, Inc. https://doi.org/10.1145/3679240.3734687

Matrone, Silvana ; Heydarian Ardakani, Amirhossein ; Ogliari, Emanuele et al. / Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism. E-ENERGY '25: Proceedings of the 2025 16th ACM International Conference on Future and Sustainable Energy Systems. New York : Association for Computing Machinery, Inc, 2025. pp. 1005-1007 (E-ENERGY Conference Proceedings).

@inproceedings{99935ccaebea4718b5fc17e9624834b5,

title = "Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism",

abstract = "The electrification of transportation has significantly increased electric vehicle (EV) charging demand on energy systems. Accurately capturing the uncertainty of future EV loads is essential for flexible system operation. This study proposes an LSTM-attention model for probabilistic EV load forecasting, featuring an encoder-decoder architecture with an intermediate attention layer. Using Quantile Regression (QR), the model predicts upper, median, and lower load quantiles. Evaluation is performed on parking station data from the SmoothEMS Met GridShield project in the Netherlands.",

keywords = "Electric Vehicles, EV Load Forecast, Long Short-Term Memory, Probabilistic Forecast, Quantile Regression",

author = "Silvana Matrone and \{Heydarian Ardakani\}, Amirhossein and Emanuele Ogliari and Elham Shirazi and Sonia Leva",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; 16th ACM International Conference on Future and Sustainable Energy Systems, ACM E-Energy 2025, ACM E-Energy 2025 ; Conference date: 17-06-2025 Through 20-06-2025",

year = "2025",

month = jun,

day = "17",

doi = "10.1145/3679240.3734687",

language = "English",

series = "E-ENERGY Conference Proceedings",

publisher = "Association for Computing Machinery, Inc",

pages = "1005--1007",

booktitle = "E-ENERGY '25",

url = "https://energy.acm.org/conferences/eenergy/2025/",

}

Matrone, S, Heydarian Ardakani, A, Ogliari, E, Shirazi, E & Leva, S 2025, Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism. in E-ENERGY '25: Proceedings of the 2025 16th ACM International Conference on Future and Sustainable Energy Systems. E-ENERGY Conference Proceedings, vol. 2025, Association for Computing Machinery, Inc, New York, pp. 1005-1007, 16th ACM International Conference on Future and Sustainable Energy Systems, ACM E-Energy 2025, Rotterdam, Netherlands, 17/06/25. https://doi.org/10.1145/3679240.3734687

Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism. / Matrone, Silvana; Heydarian Ardakani, Amirhossein ; Ogliari, Emanuele et al.
E-ENERGY '25: Proceedings of the 2025 16th ACM International Conference on Future and Sustainable Energy Systems. New York: Association for Computing Machinery, Inc, 2025. p. 1005-1007 (E-ENERGY Conference Proceedings; Vol. 2025).

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

TY - GEN

T1 - Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism

AU - Matrone, Silvana

AU - Heydarian Ardakani, Amirhossein

AU - Ogliari, Emanuele

AU - Shirazi, Elham

AU - Leva, Sonia

N1 - Conference code: 16

PY - 2025/6/17

Y1 - 2025/6/17

N2 - The electrification of transportation has significantly increased electric vehicle (EV) charging demand on energy systems. Accurately capturing the uncertainty of future EV loads is essential for flexible system operation. This study proposes an LSTM-attention model for probabilistic EV load forecasting, featuring an encoder-decoder architecture with an intermediate attention layer. Using Quantile Regression (QR), the model predicts upper, median, and lower load quantiles. Evaluation is performed on parking station data from the SmoothEMS Met GridShield project in the Netherlands.

AB - The electrification of transportation has significantly increased electric vehicle (EV) charging demand on energy systems. Accurately capturing the uncertainty of future EV loads is essential for flexible system operation. This study proposes an LSTM-attention model for probabilistic EV load forecasting, featuring an encoder-decoder architecture with an intermediate attention layer. Using Quantile Regression (QR), the model predicts upper, median, and lower load quantiles. Evaluation is performed on parking station data from the SmoothEMS Met GridShield project in the Netherlands.

KW - Electric Vehicles

KW - EV Load Forecast

KW - Long Short-Term Memory

KW - Probabilistic Forecast

KW - Quantile Regression

UR - https://www.scopus.com/pages/publications/105016327743

U2 - 10.1145/3679240.3734687

DO - 10.1145/3679240.3734687

M3 - Conference contribution

AN - SCOPUS:105016327743

T3 - E-ENERGY Conference Proceedings

SP - 1005

EP - 1007

BT - E-ENERGY '25

PB - Association for Computing Machinery, Inc

CY - New York

T2 - 16th ACM International Conference on Future and Sustainable Energy Systems, ACM E-Energy 2025

Y2 - 17 June 2025 through 20 June 2025

ER -

Matrone S, Heydarian Ardakani A, Ogliari E, Shirazi E, Leva S. Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism. In E-ENERGY '25: Proceedings of the 2025 16th ACM International Conference on Future and Sustainable Energy Systems. New York: Association for Computing Machinery, Inc. 2025. p. 1005-1007. (E-ENERGY Conference Proceedings). Epub 2025 Jun 16. doi: 10.1145/3679240.3734687

Probabilistic Forecast of EV Charging Demand using Quantile Regression and LSTM with Attention Mechanism

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this