Predictive Energy Demand and Optimization in Metro Systems Using AI and IoT Technologies

Introduction: With the rapid urbanization of modern cities, metro systems have become indispensable for efficient mobility. However, the increasing demand for public transportation has led to rising energy consumption, posing significant challenges for operational sustainability. Current energy management strategies in metro networks rely on static models and centralized systems, which often fail to adapt to real-time fluctuations in energy demand, leading to inefficiencies and wasted resources. Methods: This paper proposes an innovative approach to optimizing energy demand in metro systems by integrating Artificial Intelligence (AI) and the Internet of Things (IoT). By leveraging real-time data collected from IoT sensors deployed throughout the metro network, we apply machine learning algorithms such as Random Forests and Neural Networks to dynamically predict energy demand. These predictions enable metro operators to adjust energy consumption in real-time, thus improving overall system efficiency and reducing operational waste. Our approach was validated using data from the Parisian metro system through extensive simulations. Results: The results of simulations demonstrate significant improvements in energy efficiency. Optimized energy demand management led to a reduction in wasted energy during metro operations, particularly through the utilization of regenerative braking systems. Conclusions: Our findings suggest that integrating AI and IoT technologies into metro systems significantly improves energy efficiency by enabling dynamic energy demand prediction and real-time adjustment of energy consumption. The proposed system is scalable and adaptable, making it suitable for application in metro networks globally, thereby enhancing energy efficiency and supporting sustainable transport initiatives.