Application of stochastic model predictive control for building energy systems using latent force models

Wietzke T, Landgraf D, Graichen K (2025)


Publication Language: English

Publication Type: Journal article

Publication year: 2025

Journal

Book Volume: 73

Pages Range: 441-450

Journal Issue: 6

URI: https://www.degruyterbrill.com/document/doi/10.1515/auto-2024-0160/html

DOI: 10.1515/auto-2024-0160

Open Access Link: https://www.degruyterbrill.com/document/doi/10.1515/auto-2024-0160/pdf?licenseType=open-access

Abstract

The model-based control of building energy systems (BES) is a hard task, since the system identification is very labor-intensive. This results in inexact models, which are subject to parameter uncertainties. Additionally, disturbances like solar radiation have a great impact on the system dynamics. In this paper we used stochastic model predictive control (SMPC) to account for parameter and disturbance uncertainties. The disturbances are modeled as time-dependent Gaussian Processes (GP), which are known as Latent-Force Models (LFM). The proposed approach is evaluated for two different BES using experimentally obtained data. The results show that the LFM-SMPC results in the lowest discomfort with a reasonable higher energy consumption compared to a constant disturbance prediction.

Authors with CRIS profile

Related research project(s)

How to cite

APA:

Wietzke, T., Landgraf, D., & Graichen, K. (2025). Application of stochastic model predictive control for building energy systems using latent force models. At-Automatisierungstechnik, 73(6), 441-450. https://doi.org/10.1515/auto-2024-0160

MLA:

Wietzke, Thore, Daniel Landgraf, and Knut Graichen. "Application of stochastic model predictive control for building energy systems using latent force models." At-Automatisierungstechnik 73.6 (2025): 441-450.

BibTeX: Download