IoT Powered Energy Optimization and Monitoring System for Smart Buildings Using Learning Based Artificial Intelligence Association

Energy consumption in smart buildings is a growing concern as these environments become more complex with increased energy demand for heating, ventilation, air conditioning (HVAC), lighting, and other appliances. This paper presents a novel IoT-powered energy optimization and monitoring system for smart buildings, leveraging a hybrid learning-based approach combining Reinforcement Learning (RL) and Supervised Learning (SL). The proposed model optimizes energy consumption both reactively, by adjusting energy usage in real-time, and proactively, by predicting future energy demands based on historical data. The system utilizes various IoT sensors to collect data on environmental parameters such as temperature, occupancy, and appliance status. By employing this hybrid model, we achieve enhanced accuracy, energy savings, and occupant comfort. The proposed model was evaluated against nine existing energy optimization models, and it achieved an accuracy of 95.34% in predicting energy demand, outperforming traditional models like XGBoost (89.10%) and LightGBM (89.32%). Additionally, the proposed model achieved energy savings of 24.89%, while maintaining a response time of 0.64 seconds and an occupant comfort level of 96.89%. These results demonstrate the superiority of the proposed RL-SL model in enhancing the energy efficiency of smart buildings without compromising comfort.