Home / Current Issue / Paper 1717470
Diagnosis of South-Western Nigeria Electrical Power Network Using Optimized CNN-PMA Model
Subject area: Science,Engineering and Technology · Area of research: Optimization of CNN to Power Systems Network
DOI: https://doi.org/10.64388/IREV9I11-1717470
Abstract
Accurate diagnosis of electrical network is essential in system stability. However, existing models such as state of the art and artificial intelligence based require improvement due to their rate of response and accuracy of their diagnosis. Hence, this research proposed optimized convolutional neural network with pelican mayfly algorithm optimization CNN-PMA model for adequate diagnosis of electrical network in south western Nigeria (SWN). Pelican optimization was applied to mayfly in order to achieve a balance in exploration and exploitation of mayfly and was then used to select optimal hyper-parameters of CNN. CNN-PMA was designed and implemented to detect, classify and predict electrical faults in SWN using MATLAB software packages toolboxes such as deep learning and optimization and data division was achieved using random sampling cross validation technique. Confusion metrics was adopted to analyze fault detection and classification. The performance of CNN-PMA was evaluated on a standard IEEE 9-Bus system using MAPE, MSE, SNR, PSNR, RMSE. The performance of the proposed model is excellent compared to conventional CNN and other existing models.
Keywords
Diagnosis, artificial intelligence, CNN-PMA, South-western Nigeria.
How to cite this paper
@article{1717470,
author = {Bolarinwa Samson Adeleke, Adewale Abayomi Alabi, Akin Olugbami Adekanmbi, Oyetope Muzedik Oyedokun},
title = {Diagnosis of South-Western Nigeria Electrical Power Network Using Optimized CNN-PMA Model},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {5618-5628},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717470.pdf},
abstract = {Accurate diagnosis of electrical network is essential in system stability. However, existing models such as state of the art and artificial intelligence based require improvement due to their rate of response and accuracy of their diagnosis. Hence, this research proposed optimized convolutional neural network with pelican mayfly algorithm optimization CNN-PMA model for adequate diagnosis of electrical network in south western Nigeria (SWN). Pelican optimization was applied to mayfly in order to achieve a balance in exploration and exploitation of mayfly and was then used to select optimal hyper-parameters of CNN. CNN-PMA was designed and implemented to detect, classify and predict electrical faults in SWN using MATLAB software packages toolboxes such as deep learning and optimization and data division was achieved using random sampling cross validation technique. Confusion metrics was adopted to analyze fault detection and classification. The performance of CNN-PMA was evaluated on a standard IEEE 9-Bus system using MAPE, MSE, SNR, PSNR, RMSE. The performance of the proposed model is excellent compared to conventional CNN and other existing models.},
keywords = {Diagnosis, artificial intelligence, CNN-PMA, South-western Nigeria.},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717470}
}