BESTOpt: A Modular, Physics-Informed Machine Learning based Building Modeling, Control and Optimization Framework

TL;DR

BESTOpt is a modular, physics-informed machine learning framework that enhances modeling, control, and optimization of complex building systems for decarbonization, scalability, and physical consistency.

Contribution

It introduces a unified, hierarchical PIML framework for building modeling and control, embedding physics priors to improve accuracy and consistency across multi-scale systems.

Findings

Demonstrates improved model accuracy with physics priors

Enables multi-level centralized and decentralized control

Supports benchmarking and diagnostics in building systems

Abstract

Modern buildings are increasingly interconnected with occupancy, heating, ventilation, and air-conditioning (HVAC) systems, distributed energy resources (DERs), and power grids. Modeling, control, and optimization of such multi-domain systems play a critical role in achieving building-sector decarbonization. However, most existing tools lack scalability and physical consistency for addressing these complex, multi-scale ecosystem problems. To bridge this gap, this study presents BESTOpt, a modular, physics-informed machine learning (PIML) framework that unifies building applications, including benchmarking, evaluation, diagnostics, control, optimization, and performance simulation. The framework adopts a cluster-domain-system/building-component hierarchy and a standardized state-action-disturbance-observation data typology. By embedding physics priors into data-driven modules, BESTOpt improves model accuracy and physical consistency under unseen conditions. Case studies on single-building and cluster scenarios demonstrate its capability for multi-level centralized and decentralized control. Looking ahead, BESTOpt lays the foundation for an open, extensible platform that accelerates interdisciplinary research toward smart, resilient, and decarbonized building ecosystems.