A Comparative Analysis of Machine Learning Based Power Flow Study with Custom Made Open Source Python Codes

Bilal Ahmad; Onyema Nduka

A Comparative Analysis of Machine Learning Based Power Flow Study with Custom Made Open Source Python Codes

Department of Electronic Engineering

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

8 Downloads (Pure)

Abstract

Power flow analysis is a cornerstone of power system planning and operation, involving the solution of nonlinear equations to determine the steady-state operating conditions of the power grid. Traditionally, these equations are solved using iterative methods, which, despite their accuracy, are computationally intensive, may not converge to the solution and involve high time and space complexity. The challenges above can be overcome using Machine Learning (ML). Consequently, in this paper, a comprehensive comparative analysis of different ML algorithms developed for solving the power flow equations are presented. Experimental simulations for IEEE 3-bus and IEEE 118-bus networks have been conducted using custom-developed, open-source Python codes and technical insights are highlighted.

Original language	English
Title of host publication	13th International conference on Smart Grid
Pages	1-6
Number of pages	6
Publication status	Published - 29 May 2025
Event	13th International conference on Smart Grid - Glasgow, United Kingdom Duration: 27 May 2025 → 29 May 2025 https://www.icsmartgrid.org/

Conference

Conference	13th International conference on Smart Grid
Abbreviated title	IcSmartGrid2025
Country/Territory	United Kingdom
City	Glasgow
Period	27/05/25 → 29/05/25
Internet address	https://www.icsmartgrid.org/

UN SDGs

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

Access to Document

Published ManuscriptAccepted author manuscript, 1.79 MBLicence: CC BY

1 Master's Thesis

Machine Learning Applications in Power Systems Operation and Management
Ahmad, B., 4 Nov 2025, 111 p.
Research output: Thesis › Master's Thesis

Third Best Paper Award
Ahmad, B. (Recipient) & Nduka, O. (Recipient), 29 May 2025
Prize: Prize (including medals and awards)

File

Cite this

@inproceedings{ebb8645f66cb4e82857afd8c08a8fd59,

title = "A Comparative Analysis of Machine Learning Based Power Flow Study with Custom Made Open Source Python Codes",

abstract = "Power flow analysis is a cornerstone of power system planning and operation, involving the solution of nonlinear equations to determine the steady-state operating conditions of the power grid. Traditionally, these equations are solved using iterative methods, which, despite their accuracy, are computationally intensive, may not converge to the solution and involve high time and space complexity. The challenges above can be overcome using Machine Learning (ML). Consequently, in this paper, a comprehensive comparative analysis of different ML algorithms developed for solving the power flow equations are presented. Experimental simulations for IEEE 3-bus and IEEE 118-bus networks have been conducted using custom-developed, open-source Python codes and technical insights are highlighted.",

author = "Bilal Ahmad and Onyema Nduka",

year = "2025",

month = may,

day = "29",

language = "English",

pages = "1--6",

booktitle = "13th International conference on Smart Grid",

note = "13th International conference on Smart Grid, IcSmartGrid2025 ; Conference date: 27-05-2025 Through 29-05-2025",

url = "https://www.icsmartgrid.org/",

}

TY - GEN

T1 - A Comparative Analysis of Machine Learning Based Power Flow Study with Custom Made Open Source Python Codes

AU - Ahmad, Bilal

AU - Nduka, Onyema

PY - 2025/5/29

Y1 - 2025/5/29

N2 - Power flow analysis is a cornerstone of power system planning and operation, involving the solution of nonlinear equations to determine the steady-state operating conditions of the power grid. Traditionally, these equations are solved using iterative methods, which, despite their accuracy, are computationally intensive, may not converge to the solution and involve high time and space complexity. The challenges above can be overcome using Machine Learning (ML). Consequently, in this paper, a comprehensive comparative analysis of different ML algorithms developed for solving the power flow equations are presented. Experimental simulations for IEEE 3-bus and IEEE 118-bus networks have been conducted using custom-developed, open-source Python codes and technical insights are highlighted.

AB - Power flow analysis is a cornerstone of power system planning and operation, involving the solution of nonlinear equations to determine the steady-state operating conditions of the power grid. Traditionally, these equations are solved using iterative methods, which, despite their accuracy, are computationally intensive, may not converge to the solution and involve high time and space complexity. The challenges above can be overcome using Machine Learning (ML). Consequently, in this paper, a comprehensive comparative analysis of different ML algorithms developed for solving the power flow equations are presented. Experimental simulations for IEEE 3-bus and IEEE 118-bus networks have been conducted using custom-developed, open-source Python codes and technical insights are highlighted.

M3 - Conference contribution

SP - 1

EP - 6

BT - 13th International conference on Smart Grid

T2 - 13th International conference on Smart Grid

Y2 - 27 May 2025 through 29 May 2025

ER -

A Comparative Analysis of Machine Learning Based Power Flow Study with Custom Made Open Source Python Codes

Abstract

Conference

UN SDGs

Access to Document

Research output

Machine Learning Applications in Power Systems Operation and Management

Prizes

Third Best Paper Award

Cite this