Transfer Learning for Neural Parameter Estimation applied to Building RC Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Raisch, Fabian, Germann, Timo, Kutz, J. Nathan, Goebel, Christoph, Tischler, Benjamin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913011651837952
author Raisch, Fabian
Germann, Timo
Kutz, J. Nathan
Goebel, Christoph
Tischler, Benjamin
author_facet Raisch, Fabian
Germann, Timo
Kutz, J. Nathan
Goebel, Christoph
Tischler, Benjamin
contents Parameter estimation for dynamical systems remains challenging due to non-convexity and sensitivity to initial parameter guesses. Recent deep learning approaches enable accurate and fast parameter estimation but do not exploit transferable knowledge across systems. To address this, we introduce a transfer-learning-based neural parameter estimation framework based on a pretraining-fine-tuning paradigm. This approach improves accuracy and eliminates the need for an initial parameter guess. We apply this framework to building RC thermal models, evaluating it against a Genetic Algorithm and a from-scratch neural baseline across eight simulated buildings, one real-world building, two RC model configurations, and four training data lengths. Results demonstrate an 18.6-24.0% performance improvement with only 12 days of training data and up to 49.4% with 72 days. Beyond buildings, the proposed method represents a new paradigm for parameter estimation in dynamical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05904
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Transfer Learning for Neural Parameter Estimation applied to Building RC Models
Raisch, Fabian
Germann, Timo
Kutz, J. Nathan
Goebel, Christoph
Tischler, Benjamin
Systems and Control
Machine Learning
Parameter estimation for dynamical systems remains challenging due to non-convexity and sensitivity to initial parameter guesses. Recent deep learning approaches enable accurate and fast parameter estimation but do not exploit transferable knowledge across systems. To address this, we introduce a transfer-learning-based neural parameter estimation framework based on a pretraining-fine-tuning paradigm. This approach improves accuracy and eliminates the need for an initial parameter guess. We apply this framework to building RC thermal models, evaluating it against a Genetic Algorithm and a from-scratch neural baseline across eight simulated buildings, one real-world building, two RC model configurations, and four training data lengths. Results demonstrate an 18.6-24.0% performance improvement with only 12 days of training data and up to 49.4% with 72 days. Beyond buildings, the proposed method represents a new paradigm for parameter estimation in dynamical systems.
title Transfer Learning for Neural Parameter Estimation applied to Building RC Models
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2604.05904