An Efficient Power System Stabilizer Design Using GWO-Tuned Convolutional Neural Network for Enhanced Damping of Power Oscillations
Pratik R. Dhulap
, Prof. Samadhan Patil
Power system stabilizer, Power oscillation, Deep neural network, Convolutional neural network, Grey wolf optimization, power oscillation, single machine infinite bus test system
Modern power system networks are becoming more and more complex, with complex structural configurations that make them vulnerable to a variety of disruptions like low-frequency power oscillations, transmission line faults, and generator outages. Low-frequency oscillations are one of these that seriously jeopardize system stability and need to be successfully reduced to guarantee dependable and secure operation. In order to improve the damping of low-frequency oscillations in a Single-Machine Infinite Bus (SMIB) system, this paper proposes a novel design of a Power System Stabilizer (PSS) based on a Grey Wolf Optimizer (GWO)-tuned Convolutional Neural Network (CNN). Choosing the right hyperparameters, such as the number of convolutional layers and filter sizes, is crucial to the CNN-based PSS's efficacy. An adaptive and reliable stabilizer design is produced in this work by methodically adjusting these hyperparameters using the GWO algorithm. To assess the performance of the suggested GWO-CNN-based PSS, extensive simulation studies are carried out under a variety of operating conditions. The suggested method's superior ability to reduce power oscillations and improve overall system stability is amply demonstrated by comparisons with traditional PSS designs.
"An Efficient Power System Stabilizer Design Using GWO-Tuned Convolutional Neural Network for Enhanced Damping of Power Oscillations", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.10, Issue 3, page no.b663-b669, March-2025, Available :https://ijsdr.org/papers/IJSDR2503187.pdf
Volume 10
Issue 3,
March-2025
Pages : b663-b669
Paper Reg. ID: IJSDR_301200
Published Paper Id: IJSDR2503187
Downloads: 000157
Research Area: Science and Technology
Country: Raigad, Mumbai, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
