Query-adaptive training data recommendation for cross-building predictive modeling - Archive ouverte HAL Access content directly
Journal Articles Knowledge and Information Systems (KAIS) Year : 2023

Query-adaptive training data recommendation for cross-building predictive modeling

Abstract

Predictive modeling in buildings is a key task for the optimal management of building energy. Relevant building operational data are a prerequisite for such task, notably when deep learning is used. However, building operational data are not always available, such is the case in newly built, newly renovated, or even not yet built buildings. To address this problem, we propose a deep similarity learning approach to recommend relevant training data to a target building solely by using a minimal contextual description on it. Contextual descriptions are modeled as user queries. We further propose to ensemble most used machine learning algorithms in the context of predictive modeling. This contributes to the genericity of the proposed methodology. Experimental evaluations show that our methodology offers a generic methodology for cross-building predictive modeling and achieves good generalization performance.

Dates and versions

hal-04026112 , version 1 (13-03-2023)

Identifiers

Cite

Mouna Labiadh, Christian Obrecht, Catarina Ferreira da Silva, Parisa Ghodous, Khalid Benabdeslem. Query-adaptive training data recommendation for cross-building predictive modeling. Knowledge and Information Systems (KAIS), 2023, 65 (2), pp.707-732. ⟨10.1007/s10115-022-01771-9⟩. ⟨hal-04026112⟩
31 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More