Attentive Neural Processes and Batch Bayesian Optimization for Scalable Calibration of Physics-Informed Digital Twins
This addresses the problem of scalable calibration for digital twins in energy-efficient infrastructure, though it appears incremental as it builds on existing Bayesian optimization and neural process methods.
The paper tackles the challenge of calibrating physics-informed digital twins for buildings, which is computationally expensive due to many parameters and simulations, by proposing ANP-BBO, a scalable batch Bayesian optimization method using attentive neural processes, achieving efficient calibration without exorbitant computational costs.
Physics-informed dynamical system models form critical components of digital twins of the built environment. These digital twins enable the design of energy-efficient infrastructure, but must be properly calibrated to accurately reflect system behavior for downstream prediction and analysis. Dynamical system models of modern buildings are typically described by a large number of parameters and incur significant computational expenditure during simulations. To handle large-scale calibration of digital twins without exorbitant simulations, we propose ANP-BBO: a scalable and parallelizable batch-wise Bayesian optimization (BBO) methodology that leverages attentive neural processes (ANPs).