Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198971,
        author = {Poonam Rani and Rajneesh and Rajni},
        title = {Real time grid stability and frequency regulation for outage minimization using hybrid neural architecture},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15363-15376},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198971},
        abstract = {The growing complexity of modern smart grids and increasing penetration of renewable energy sources have made real-time stability and frequency regulation critical for preventing large-scale outages. Traditional control systems often fail to respond quickly to sudden disturbances, resulting in delayed correction and higher outage risk. To address this challenge, the present work proposes a hybrid neural architecture that integrates CNN and RNN models to enhance prediction accuracy and response speed for real-time grid stability assessment. Using the UCI Electrical Grid Stability Simulated Dataset, the study performs comprehensive preprocessing including normalization, feature extraction, label encoding, and class balancing, followed by training of CNN, RNN, and hybrid models on a 60–40 train–test split. The hybrid model leverages spatial–temporal learning to detect early instability patterns with high reliability. Experimental results show that the proposed hybrid model achieves 94% accuracy, 92% precision, 90% recall, and 91% F1-score, outperforming individual models. Latency is maintained at 8 ms, enabling rapid detection of frequency deviations and supporting real-time outage minimization in dynamic grid environments.},
        keywords = {Real-time grid stability, Frequency regulation, Hybrid neural network, CNN–RNN model, Electrical Grid Stability Dataset,},
        month = {April},
        }