Adapting to Change: A Comparison of Continual and Transfer Learning for Modeling Building Thermal Dynamics under Concept Drifts

2025-08-29 · Fabian Raisch, Max Langtry, Felix Koch, Ruchi Choudhary, Christoph Goebel, Benjamin Tischler arxiv

Transfer Learning (TL) is currently the most effective approach for modeling building thermal dynamics when only limited data are available. TL uses a pretrained model that is fine-tuned to a specific target building. However, it remains unclear how to proceed after initial fine-tuning, as more operational measurement data are collected over time. This challenge becomes even more complex when the dynamics of the building change, for example, after a retrofit or a change in occupancy. In Machine Learning literature, Continual Learning (CL) methods are used to update models of changing systems. TL approaches can also address this challenge by reusing the pretrained model at each update step and fine-tuning it with new measurement data. A comprehensive study on how to incorporate new measurement data over time to improve prediction accuracy and address the challenges of concept drifts (changes in dynamics) for building thermal dynamics is still missing. Therefore, this study compares several CL and TL strategies, as well as a model trained from scratch, for thermal dynamics modeling during building operation. The methods are evaluated using 5--7 years of simulated data representative of single-family houses in Central Europe, including scenarios with concept drifts from retrofits and changes in occupancy. We propose a CL strategy (Seasonal Memory Learning) that provides greater accuracy improvements than existing CL and TL methods, while maintaining low computational effort. SML outperformed the benchmark of initial fine-tuning by 28.1\% without concept drifts and 34.9\% with concept drifts.

📄 PDF Abstract BibTeX arXiv:2508.21615

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning Transfer Learning

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

2023-09-21 · NeurIPS 2023 11

Existing methods for adapting Neural Radiance Fields (NeRFs) to scene changes require extensive data capture and model retraining, which is both time-consuming and labor-intensive. In this paper, we tackle the challenge …

Heterogeneous Continual Learning

2023-06-14 · CVPR 2023 1 · Divyam Madaan, Hongxu Yin, Wonmin Byeon, Jan Kautz 외

We propose a novel framework and a solution to tackle the continual learning (CL) problem with changing network architectures. Most CL methods focus on adapting a single architecture to a new task/class by modifying its …

Continual Learning Knowledge Distillation Transfer Learning

Regularization-Based Efficient Continual Learning in Deep State-Space Models

2024-03-15 · Yuanhang Zhang, Zhidi Lin, Yiyong Sun, Feng Yin 외

Deep state-space models (DSSMs) have gained popularity in recent years due to their potent modeling capacity for dynamic systems. However, existing DSSM works are limited to single-task modeling, which requires retrainin…

Continual Learning State Space Models

Continual Learning Using Multi-view Task Conditional Neural Networks

2020-05-08 · Honglin Li, Payam Barnaghi, Shirin Enshaeifar, Frieder Ganz

Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interfere…

Continual Learning

GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments

2025-08-12 · Lin Zeng, Boming Zhao, Jiarui Hu, Xujie Shen 외 arxiv

Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-intensive, requiring extensive model ret…

Novel View Synthesis Continual Learning