AI-Enhanced Dynamic Power Grid Simulation for Real-Time Decision-Making

Traditional power grid simulation methods often struggle to meet the real-time requirements of modern smart grid operations due to high computational overhead and limited adaptability. To address these challenges, this paper proposes an AI-enhanced dynamic power grid simulation and intelligent decision-making framework. The system integrates Random Forest Regression for rapid load prediction and Random Forest Classification for accurate fault detection, significantly reducing simulation time while maintaining high predictive accuracy. Experimental results on a synthetic 500-node, 1000-line power grid dataset demonstrate an 80% reduction in average simulation time and a 98.4% fault detection accuracy, validating the model's effectiveness in real-time grid management. The proposed framework provides a scalable solution for next-generation power grids, capable of supporting real-time state estimation, fault diagnosis, and optimal control. Future work will focus on incorporating diverse data sources, such as weather forecasts and market dynamics, to enhance model robustness and extend the approach to ultra-high voltage grids and multi-energy systems.