Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems

TL;DR

This paper introduces a scalable data-driven simulation framework for large-scale HVAC systems, combining physics-informed neural ODEs with DAE solvers for efficient and accurate modeling.

Contribution

It develops a novel approach integrating PINODEs with DAE solvers and Bayesian optimization, enabling fast, accurate, and scalable HVAC system simulations.

Findings

Achieves multi-fold speedups over high-fidelity simulation.

Maintains low errors with MAPE below a few percent.

Scales to systems with up to 16 compressor-condenser pairs.

Abstract

We present a scalable, data-driven simulation framework for large-scale heating, ventilation, and air conditioning (HVAC) systems that couples physics-informed neural ordinary differential equations (PINODEs) with differential-algebraic equation (DAE) solvers. At the component level, we learn heat-exchanger dynamics using an implicit PINODE formulation that predicts conserved quantities (refrigerant mass $M_r$ and internal energy $E_\text{hx}$) as outputs, enabling physics-informed training via automatic differentiation of mass/energy balances. Stable long-horizon prediction is achieved through gradient-stabilized latent evolution with gated architectures and layer normalization. At the system level, we integrate learned components with DAE solvers (IDA and DASSL) that explicitly enforce junction constraints (pressure equilibrium and mass-flow consistency), and we use Bayesian optimization to tune solver parameters for accuracy--efficiency trade-offs. To reduce residual system-level bias, we introduce a lightweight corrector network trained on short trajectory segments. Across dual-compressor and scaled network studies, the proposed approach attains multi-fold speedups over high-fidelity simulation while keeping errors low (MAPE below a few percent) and scales to systems with up to 16 compressor-condenser pairs.