Thermal-GEMs: Generalized Models for Building Thermal Dynamics

• URL: http://arxiv.org/abs/2604.16443v1
• Date: Tue, 07 Apr 2026 09:50:57 GMT
• Title: Thermal-GEMs: Generalized Models for Building Thermal Dynamics
• Abstract summary: Transfer Learning mitigates the challenge by employing pretrained models based on single or multiple source buildings.<n>General multi-source TL models promise to outperform single-source TL.<n>Time series foundation models (TSFM) have emerged as candidates for the best-performing general models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data-driven models for building thermal dynamics are a scalable approach for enabling energy-efficient operation through fault detection & diagnosis or advanced control. To obtain accurate models, measurement data from a target building spanning months to years are required. Transfer Learning (TL) mitigates this challenge by employing pretrained models based on single or multiple source buildings. General multi-source TL models promise to outperform single-source TL, but alternative multi-source modeling architectures remain to be explored, and evaluation on real-world data is missing. Moreover, time series foundation models (TSFM) have emerged as candidates for the best-performing general models. Hence, we conduct a first, comprehensive assessment of general modeling approaches for building thermal dynamics, including multi-source TL and TSFMs. Our assessment includes ablations using four state-of-the-art multi-source TL architectures and evaluations on synthetic as well as real-world data. We demonstrate that multi-source TL models are highly effective in accurately modeling buildings in real-world applications, yielding up to 63% lower forecasting errors compared to single-source TL. Moreover, our results suggest a trade-off between multi-source TL models exclusively pretrained with building data and TSFMs pretrained with a multitude of different time series, revealing that data from 16-32 source buildings must be available over 1 year for pretraining multi-source TL models to consistently outperform TSFMs as evaluated using the mean absolute error. These findings provide practical guidance for selecting modeling strategies based on the number of source buildings available for pretraining multi-source TL models.

Related papers

• Very Exciting: Zero-Shot Model Predictive Control of Buildings via Excitation-Based Generalized Transfer Learning Models [0.0]
  Transfer learning has gained increasing attention for target building modeling.<n>State-of-the-art TL approach pretrained a generalized model on multiple source buildings using standard operational data.<n>We show that this approach is insufficient to achieve satisfactory control performance.
  arXiv  Detail & Related papers  (2026-09-11T13:42:45Z)
• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• On What Depends the Robustness of Multi-source Models to Missing Data in Earth Observation? [4.388282062290401]
  We evaluate the predictive performance of six state-of-the-art multi-source models in predicting scenarios where either a single data source is missing or only a single source is available.<n>Our analysis reveals that the efficacy of these models is intricately tied to the nature of the task, the complement among data sources, and the model design.
  arXiv  Detail & Related papers  (2025-03-25T14:45:23Z)
• A Theory for Conditional Generative Modeling on Multiple Data Sources [20.539424639329564]
  This paper takes the first step toward a rigorous analysis of multi-source training in conditional generative modeling.<n>Our result shows that when source distributions share certain similarities and the model is expressive enough, multi-source training guarantees a sharper bound than single-source training.
  arXiv  Detail & Related papers  (2025-02-20T14:13:24Z)
• GenTL: A General Transfer Learning Model for Building Thermal Dynamics [0.0]
  GenTL is a transfer learning model for single-family houses in Central Europe.<n>It is pretrained on a Long Short-Term Memory (LSTM) network with data from 450 different buildings.
  arXiv  Detail & Related papers  (2025-01-23T14:34:55Z)
• Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains [114.76612918465948]
  Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data.<n>We propose a complementary approach towards self-improvement where finetuning is applied to a multiagent society of language models.
  arXiv  Detail & Related papers  (2025-01-10T04:35:46Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Learning from models beyond fine-tuning [78.20895343699658]
  Learn From Model (LFM) focuses on the research, modification, and design of foundation models (FM) based on the model interface.<n>The study of LFM techniques can be broadly categorized into five major areas: model tuning, model distillation, model reuse, meta learning and model editing.<n>This paper gives a comprehensive review of the current methods based on FM from the perspective of LFM.
  arXiv  Detail & Related papers  (2023-10-12T10:20:36Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• Comparison of Transfer Learning based Additive Manufacturing Models via A Case Study [3.759936323189418]
  This paper defines a case study based on an open-source dataset about metal AM products. Five TL methods are integrated with decision tree regression (DTR) and artificial neural network (ANN) to construct six TL-based models. The comparisons are used to quantify the performance of applied TL methods and are discussed from the perspective of similarity, training data size, and data preprocessing.
  arXiv  Detail & Related papers  (2023-05-17T00:29:25Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [47.432215933099016]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models.<n>This creates a barrier to fusing knowledge across individual models to yield a better single model.<n>We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.