Dependable Software-Optimized Energy Management for IoT-Enabled Smart Buildings

The rise of IoT has enabled advancements in smart buildings, particularly through the integration of electric vehicles (EVs) and IoT devices like Heating, Ventilation, and Air Conditioning (HVAC) systems and lighting. As IoT adoption grows, managing energy consumption across multiple devices becomes critical for grid stability. This paper introduces a Dependable Software-Optimized Energy Management System for IoT-enabled smart buildings (DSOEMS-IoT), designed to allocate energy across EV chargers and IoT devices dynamically. To achieve this, we implemented a range of control and optimization algorithms—Model Predictive Control (MPC), Adaptive MPC (AMPC), Particle Swarm Optimization (PSO), and Fuzzy Logic (FL)—and evaluated the system by simulating different demand levels—light, medium, and heavy—using real-time data and user preferences. Results show that while PSO minimizes waiting time under light and medium demand, AMPC reduces waiting time by 30% under heavy demand. FL consistently offers the fastest computation, reducing processing time by 80% to 92% compared to other algorithms. These results demonstrate that our system can effectively manage energy distribution across varying demand levels, ensuring grid stability in IoT-enabled smart infrastructure.