Intelligent Building Automation and Energy Optimization: Exploring How AI and IoT Frameworks Can Dynamically Manage HVAC Systems, Lighting, and Other Building Infrastructure Based on Real-Time Occupancy and Environmental Data

Intelligent building automation uses IoT sensing and AI control to coordinate HVAC, lighting, and ventilation in real-time. Current occupancy prediction and building dynamics models often report strong performance on held-out test sets drawn from the same distribution as the training data. However, operational buildings experience persistent distribution shifts due to hybrid work schedules, seasonal changes, organizational restructuring, sensor drift, and equipment degradation. Under these shifts, models can remain confidently incorrect, causing comfort violations, energy waste, excessive equipment cycling, and loss of operator trust. This study frames intelligent building automation as a cyber-physical deployment problem in which competence boundaries must be detected, communicated, and enforced at runtime. It contributes a six-dimensional human-centered AI framework adapted to building control and uses it to identify gaps in robustness evaluation, uncertainty quantification, drift detection for building time-series, and graceful degradation strategies when AI components become unreliable. The metrics-and-methodology section specifies shift-aware evaluation procedures, calibration and drift indicators, and closed-loop control benchmarks that connect prediction reliability to energy and comfort outcomes. Case analyses illustrate API-integrated occupancy-based HVAC, environmental-sensor occupancy detection, multi-zone occupant-centric control, and reinforcement-learning control under drift, demonstrating how a safe fallback to MPC and conservative modes stabilizes performance.