Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63127
Volume:
10 |
5 |
May 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department Of Electrical And Electronics Engineering
Sree Narayana Gurukulam College Of Engineering
Department Of Electrical And Electronics Engineering
Sree Narayana Gurukulam College Of Engineering
Department Of Electrical And Electronics Engineering
Sree Narayana Gurukulam College Of Engineering
Department Of Electrical And Electronics Engineering
Sree Narayana Gurukulam College Of Engineering
Department Of Electrical And Electronics Engineering
Sree Narayana Gurukulam College Of Engineering
Reliability of modern power systems is critical for maintaining a continuous and uninterrupted electricity supply. As traditional network monitoring becomes increasingly difficult for predicting faults early due to the growing size and complexity of interconnected systems, new methods have been developed specifically for these types of situations. Power systems face challenges in maintaining their reliability due to increased loading from renewable sources. This work provides a solution using artificial intelligence-based approaches to improve the power system reliability by enabling real-time condition monitoring and predictive capabilities. Modelling an IEEE 5-bus power system as a model and simulating it using MATLAB and Simulink for analysis of the system operation during normal operation and under fault conditions. Electrical apparent power is collected together to create data sets for further analysis and modelling of these systems. Gradient boosting machine learning algorithms are employed for analyzing data sets, predicting near-overloaded transmissions via predictive modelling techniques utilizing gradient-boosted machines. Accuracy, precision, recall, and F-1 score are used as metrics for evaluating our system's predictive capabilities and effectiveness. Results clearly show that the proposed AI-based solution is significantly good for the ability to predict near-overload transmission lines to increase the reliability of systems.
KEYWORDS
This project used the AI based techniques for near overload transmission line prediction in the power system network. A simulated model of IEEE 5-bus system has been created in MATLAB for generating the dataset considering the conditions of system under normal and fault. Algorithms of gradient boosting were used to learn from apparent power of transmission lines. Gradient Boosting out of all models has achieved high accuracy, precision, recall and F1-score. It was found that the model had correctly learned the nature of dataset and classify the system conditions correctly. And developed system could successfully predict the fault condition and transmission line nearing to be overload. The accuracy shown by model at training and testing time is quite high and reliable. It reduces the necessity for continuous human monitoring on the system and also the probability of potential failure occurrence. Therefore the system contributes towards efficiency, reliability and stability of power system network.
[1] T. Hubana and M. Hodzic, "Artificial Intelligence Based Fault Detection and Classification in Power Systems: An Automated Machine Learning Approach," 2024 23rd International Symposium INFOTEH-JAHORINA (INFOTEH), East Sarajevo, Bosnia and Herzegovina, 2024 [2] J. Dai and J. Shao, "Application of Artificial Intelligence in Fault Detection and Isolation of Power System," 2025 International Conference on Electrical Drives, Power [3] L. Gong, A. Sharma, M. Abdul Bhuiya, H. Awad and M. Z. Youssef, "An Artificial Intelligence Based Fault Monitoring of Power Trains: Design & Implementation," 2021 IEEE Applied Power Electronics Conference and Exposition (APEC) [4] AI-Driven Fault Detection and Diagnosis in Smart Grids for Enhanced Power System Reliability Dr. Gaurav Goya, Ismot Tasmary Salsabil, Dr Ashutosh Kumar, Manda Ukey. Dr. Velumani [5] Fault diagnosis in low voltage smart distribution grids using gradient Boosting trees, Nikolaos Sapount zogloua, Jesus Lagob, Bertrand Raisona [6] Enhancing Reliability of Advanced Driver-Assistance Systems through Predictive Maintenance and Data-Driven Insights Amit Jain, Vishal Goyal,amal Sharma (2024) [7] Tarik Hubana and Migdat Hodzic “ Artificial Intelligence Based Fault Detection and Classification in Power Systems: An Automated Machine Learning Approach” (March 2024)
Publication Date
5/13/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...