The financial benefit of a refined, intelligent power system that meets rising demand is known as a smart grid (SG). Energy use has increased significantly due to new technology and population growth, creating significant issues for the environment and energy security. Utilizing the Deep Learning (DL) Method in conjunction with power management is important for issue solving. Data is pre-processed using a normalization method after being gathered via a smart city in a power-hungry smart grid. The research used a Discrete Fourier Transform (DFT) to extract features and estimate smart city power usage within a smart grid setting utilizing large-scale, high-dimensional data. The research introduced a unique DL-based, Hybrid Mountain Gazelle Optimized Graph Neural Networks (HMGO-GNN) for real-time forecast and adaptive management of smart grid stability. The suggested technique may stabilize critical machines; predict transient stability, and the stability limit. It may also be used to detect instability during the first swing and multiple times. Imitations on test systems demonstrate that the suggested technique may forecast system stability with high accuracy in real-time. To measure performance on critical assessment metrics, such as F1-score (96%), precision (94%), accuracy (97%), AUC (98%), and recall (95), provide a complete indication of whether the model is successful or not in predicting occurrences of grid instability. The savings on cost, energy usage, and major contributions to the elimination of greenhouse gas emissions eventually point towards increased environmental sustainability. Further, the flexibility of the framework and its potential scalability for application in other urban scenarios are also illustrated.
Singh et al. (Fri,) studied this question.