Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network

Md Raza Ali; Deep Kiran; N. P. Padhy

doi:10.1109/ELEXCOM58812.2023.10370170

Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network

Md Raza Ali
, Deep Kiran
, N. P. Padhy

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

Abstract

This paper proposes a data-driven based optimal operation of distribution systems integrated with electric vehicles (EV) using Deep Neural Networks (DNNs). Historical data on EV charging patterns and loads are employed to train the DNN, which is then tested on distribution systems. It is observed that the used DNN architecture accurately predicts the voltage magnitudes and angles, which can be used for calculating the remaining optimal power flow (OPF) parameters. This process reduces the computational burden substantially and demonstrates adaptability for varying EV penetration levels and load patterns, making it a scalable and flexible solution for smart grid implementations. The proposed model is implemented and validated on the IEEE-33 bus distribution system.

Original language	English
Title of host publication	IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350305111
DOIs	https://doi.org/10.1109/ELEXCOM58812.2023.10370170
State	Published - 2023
Externally published	Yes
Event	2023 IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023 - Roorkee, India Duration: 26 Aug 2023 → 27 Aug 2023

Publication series

Name	IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023

Conference

Conference	2023 IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023
Country/Territory	India
City	Roorkee
Period	26/08/23 → 27/08/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Data-driven methods
Deep Neural Networks
Electric Vehicles
Optimal Power Flow

ASJC Scopus subject areas

Information Systems and Management
Electrical and Electronic Engineering
Mechanical Engineering
Safety, Risk, Reliability and Quality
Instrumentation
Computer Science Applications
Artificial Intelligence
Computer Networks and Communications

Access to Document

10.1109/ELEXCOM58812.2023.10370170

Cite this

Ali, M. R., Kiran, D., & Padhy, N. P. (2023). Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network. In IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023 (IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ELEXCOM58812.2023.10370170

Ali, Md Raza ; Kiran, Deep ; Padhy, N. P. / Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network. IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023).

@inproceedings{b980b1d879e3446688e666c77965b5c9,

title = "Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network",

abstract = "This paper proposes a data-driven based optimal operation of distribution systems integrated with electric vehicles (EV) using Deep Neural Networks (DNNs). Historical data on EV charging patterns and loads are employed to train the DNN, which is then tested on distribution systems. It is observed that the used DNN architecture accurately predicts the voltage magnitudes and angles, which can be used for calculating the remaining optimal power flow (OPF) parameters. This process reduces the computational burden substantially and demonstrates adaptability for varying EV penetration levels and load patterns, making it a scalable and flexible solution for smart grid implementations. The proposed model is implemented and validated on the IEEE-33 bus distribution system.",

keywords = "Data-driven methods, Deep Neural Networks, Electric Vehicles, Optimal Power Flow",

author = "Ali, \{Md Raza\} and Deep Kiran and Padhy, \{N. P.\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023 ; Conference date: 26-08-2023 Through 27-08-2023",

year = "2023",

doi = "10.1109/ELEXCOM58812.2023.10370170",

language = "English",

series = "IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023",

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

booktitle = "IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023",

address = "United States",

}

Ali, MR, Kiran, D & Padhy, NP 2023, Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network. in IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023. IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023, Roorkee, India, 26/08/23. https://doi.org/10.1109/ELEXCOM58812.2023.10370170

Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network. / Ali, Md Raza; Kiran, Deep; Padhy, N. P.
IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023).

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

TY - GEN

T1 - Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network

AU - Ali, Md Raza

AU - Kiran, Deep

AU - Padhy, N. P.

PY - 2023

Y1 - 2023

N2 - This paper proposes a data-driven based optimal operation of distribution systems integrated with electric vehicles (EV) using Deep Neural Networks (DNNs). Historical data on EV charging patterns and loads are employed to train the DNN, which is then tested on distribution systems. It is observed that the used DNN architecture accurately predicts the voltage magnitudes and angles, which can be used for calculating the remaining optimal power flow (OPF) parameters. This process reduces the computational burden substantially and demonstrates adaptability for varying EV penetration levels and load patterns, making it a scalable and flexible solution for smart grid implementations. The proposed model is implemented and validated on the IEEE-33 bus distribution system.

AB - This paper proposes a data-driven based optimal operation of distribution systems integrated with electric vehicles (EV) using Deep Neural Networks (DNNs). Historical data on EV charging patterns and loads are employed to train the DNN, which is then tested on distribution systems. It is observed that the used DNN architecture accurately predicts the voltage magnitudes and angles, which can be used for calculating the remaining optimal power flow (OPF) parameters. This process reduces the computational burden substantially and demonstrates adaptability for varying EV penetration levels and load patterns, making it a scalable and flexible solution for smart grid implementations. The proposed model is implemented and validated on the IEEE-33 bus distribution system.

KW - Data-driven methods

KW - Deep Neural Networks

KW - Electric Vehicles

KW - Optimal Power Flow

UR - https://www.scopus.com/pages/publications/85182919437

U2 - 10.1109/ELEXCOM58812.2023.10370170

DO - 10.1109/ELEXCOM58812.2023.10370170

M3 - Conference contribution

AN - SCOPUS:85182919437

T3 - IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023

BT - IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023

Y2 - 26 August 2023 through 27 August 2023

ER -

Ali MR, Kiran D, Padhy NP. Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network. In IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (IEEE International Conference on Electrical, Electronics, Communication and Computers, ELEXCOM 2023). doi: 10.1109/ELEXCOM58812.2023.10370170

Data-Driven Based Optimal Operation of Distribution Systems Integrated with Electric Vehicles Using Deep Neural Network

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this