Saved in:
Bibliographic Details
Main Authors: Mallick, Samuel, de de Giuli, Laura Boca, La Bella, Alessio, Dabiri, Azita, De Schutter, Bart, Scattolini, Riccardo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.12187
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915857785946112
author Mallick, Samuel
de de Giuli, Laura Boca
La Bella, Alessio
Dabiri, Azita
De Schutter, Bart
Scattolini, Riccardo
author_facet Mallick, Samuel
de de Giuli, Laura Boca
La Bella, Alessio
Dabiri, Azita
De Schutter, Bart
Scattolini, Riccardo
contents This paper addresses the design of an event-triggered, data-based, and performance-oriented adaption method for model predictive control (MPC). The performance of such a strategy strongly depends on the accuracy of the prediction model, which may require online adaption to prevent performance degradation under changing operating conditions. Unlike existing methods that continuously update model and control parameters from data, potentially leading to catastrophic forgetting and unnecessary control modifications, we propose a novel approach based on statistical monitoring of closed-loop performance indicators. This framework enables the detection of performance degradation, and, when required, controller adaption is performed via reinforcement learning and identification techniques. The proposed strategy is validated on a high-fidelity simulation of a district heating system benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12187
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Integrated Online Monitoring and Adaption of Process Model Predictive Controllers
Mallick, Samuel
de de Giuli, Laura Boca
La Bella, Alessio
Dabiri, Azita
De Schutter, Bart
Scattolini, Riccardo
Systems and Control
This paper addresses the design of an event-triggered, data-based, and performance-oriented adaption method for model predictive control (MPC). The performance of such a strategy strongly depends on the accuracy of the prediction model, which may require online adaption to prevent performance degradation under changing operating conditions. Unlike existing methods that continuously update model and control parameters from data, potentially leading to catastrophic forgetting and unnecessary control modifications, we propose a novel approach based on statistical monitoring of closed-loop performance indicators. This framework enables the detection of performance degradation, and, when required, controller adaption is performed via reinforcement learning and identification techniques. The proposed strategy is validated on a high-fidelity simulation of a district heating system benchmark.
title Integrated Online Monitoring and Adaption of Process Model Predictive Controllers
topic Systems and Control
url https://arxiv.org/abs/2603.12187