International Journal of Scientific Research and Engineering Development

Efficient resource allocation is a central concern in large-scale electrical engineering (EE) projects due to the complexity, high costs, and dynamic environments involved. Traditional decision-making models, often heuristic or manual, are inadequate to handle large datasets, real-time demands, and uncertainty. This study explores the integration of Artificial Intelligence (AI) techniques—including supervised machine learning (ML), deep learning (DL), reinforcement learning (RL), and expert systems—into intelligent decision-making processes for optimizing resource allocation in EE. We formulate resource allocation as a multi-objective optimization problem involving cost, efficiency, and availability under multiple constraints. Through simulated and real-world case studies, the proposed AI models demonstrate superior performance in decision speed, resource utilization, and adaptability when compared to conventional methods. Reinforcement learning showed high robustness and scalability. This work provides a framework for embedding AI into EE resource management systems and highlights the path toward autonomous, intelligent infrastructure planning.