Physics-informed sparse Gaussian processes for model predictive control in building energy systems

Wietzke T, Graichen K (2025)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2025

Book Volume: 59

Pages Range: 43-48

Conference Proceedings Title: IFAC-PapersOnLine

Event location: Vienna (Austria)

URI: https://www.sciencedirect.com/science/article/pii/S2405896325002265

DOI: 10.1016/j.ifacol.2025.03.009

Open Access Link: https://www.sciencedirect.com/science/article/pii/S2405896325002265

Abstract

Efficient energy management in building energy systems (BES) is essential for
reducing energy consumption while maintaining thermal comfort. One effective approach is
Model Predictive Control (MPC), which optimizes control actions based on a model of the
building; however, deriving such models can be costly and time-consuming. This paper combines
Gaussian Processes (GP) with parametric mean functions which can be viewed as Physics
Informed Gaussian Processes (PIGP). The PIGP is evaluated against other approaches to
identify the thermal dynamics of BES, showing that the PIGP provides the best predictive
accuracy. Furthermore, these models are integrated into a nonlinear MPC to compare energy
demand and constraint violations in a sample BES, with simulations indicating that the PIGP
results in lower energy demand.

Authors with CRIS profile

Related research project(s)

How to cite

APA:

Wietzke, T., & Graichen, K. (2025). Physics-informed sparse Gaussian processes for model predictive control in building energy systems. In IFAC-PapersOnLine (pp. 43-48). Vienna (Austria).

MLA:

Wietzke, Thore, and Knut Graichen. "Physics-informed sparse Gaussian processes for model predictive control in building energy systems." Proceedings of the 11th Vienna International Conference on Mathematical Modelling (MATHMOD 25), Vienna (Austria) 2025. 43-48.

BibTeX: Download