Enhancing Power Grid Stability with an Advanced Deep Learning Model for Smart Grids

Abstract

The integration of renewable energy sources and the introduction of smart grids have raised serious concerns about the reliability and effectiveness of power systems. To address these challenges, this research paper proposes a novel hybrid deep learning model for power grid stability enhancement. To increase the accuracy of short-term electric load forecasting and daily peak load forecasting, the proposed model combines gradient-boosting based multiple kernel learning, dynamic time warping distance, gated RNNs, and Bayesian deep LSTM neural networks, resulting in probabilistic residential net load forecasting. With a training accuracy of 99.94% and a validation accuracy of 99.13%, this model produces remarkable results. The suggested model is also superior in terms of accuracy and predicting performance when compared to existing methodologies. The proposed hybrid deep learning model offers a promising approach to power grid stability enhancement in smart grids