Cognitive Digital Twins for Climate-Resilient Building Energy Systems: Diagnosis-Informed Control under Extreme Thermal Stress

Abstract

Climate change is increasingly exposing building energy systems to prolonged and severe thermal stress, revealing fundamental limitations in conventional control strategies that rely on static models and reactive feedback. Under extreme heatwave conditions, buildings often experience gradual performance drift driven by equipment degradation, sensing bias, and evolving internal loads, leading to declining energy efficiency and growing thermal discomfort. Existing control architectures, however, lack the capability to interpret the underlying causes of these deviations or to adapt their operation in a timely and causally informed manner. This study proposes a cognitive digital twin framework that shifts building energy management from reactive regulation toward diagnosis-informed and adaptive control under climate-extreme operation. The framework integrates physics-based building energy modeling with real-time sensing and data assimilation to enable continuous state estimation, early detection of performance drift, and explicit root-cause attribution. Diagnostic information is embedded directly within the control loop, allowing control actions to be conditioned on diagnosed system states rather than solely on predictive trajectories or residual-based feedback. In this formulation, cognition emerges from the closed-loop interaction of interpretation, reasoning, and memory as operating conditions evolve. The framework is evaluated using a representative medium-scale commercial office building equipped with a variable air volume HVAC system and subjected to structured heatwave-driven stress scenarios, including progressive cooling capacity degradation, sensor temperature drift, demand response constraints, occupancy shocks, and elevated operational uncertainty. Simulations are conducted across hot-dry, hot-humid, and temperate climates to assess robustness and generalizability. Compared with rule-based control, conventional model predictive control, and a non-cognitive digital twin baseline, the proposed approach reduces energy use intensity by 10.9%, peak electric demand by 13.4%, and discomfort hours by 54.6% under climate-extreme conditions. Performance drift is detected 3.3–3.4× earlier, unmet cooling hours are reduced by 58.2%, and post-event comfort recovery is accelerated by approximately 46%. These results demonstrate that cognitive digital twins can function as self-interpreting and adaptive building energy systems, providing a scalable and resilient pathway for sustaining energy performance and thermal comfort under increasingly uncertain and climate-stressed environments.