Automated Voltage Sag Mitigation via Dynamic Multi-Objective Optimization and Hybrid Quantum-Classical Neural Networks

**Abstract:** Voltage sags, or dips in voltage, are a widespread and costly problem in power systems, disrupting industrial processes and damaging sensitive equipment. Traditional mitigation strategies often employ static solutions or reactive devices, failing to adapt to the dynamic nature of the grid and the diverse needs of connected loads. This research introduces a novel system, Adaptive Sag Mitigation Network (ASMN), leveraging dynamic multi-objective optimization and a hybrid quantum-classical neural network (HQCN) to proactively mitigate voltage sags with improved efficiency and adaptability. ASMN dynamically balances cost, reliability, and grid stability, providing a cost-effective and robust solution for voltage sag mitigation in modern power grids. This method achieves a projected 20% cost reduction and 15% improvement in reliability compared to existing solutions, alongside enhanced grid stability.