A microservice-based framework for exploring data selection in cross-building knowledge transfer
- PDF / 1,584,882 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 88 Downloads / 183 Views
SPECIAL ISSUE PAPER
A microservice-based framework for exploring data selection in cross-building knowledge transfer Mouna Labiadh1
· Christian Obrecht2 · Catarina Ferreira da Silva3 · Parisa Ghodous1
Received: 29 April 2020 / Revised: 14 August 2020 / Accepted: 13 October 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Supervised deep learning has achieved remarkable success in various applications. Successful machine learning application however depends on the availability of sufficiently large amount of data. In the absence of data from the target domain, representative data collection from multiple sources is often needed. However, a model trained on existing multi-source data might generalize poorly on the unseen target domain. This problem is referred to as domain shift. In this paper, we explore the suitability of multi-source training data selection to tackle the domain shift challenge in the context of domain generalization. We also propose a microservice-oriented methodology for supporting this solution. We perform our experimental study on the use case of building energy consumption prediction. Experimental results suggest that minimal building description is capable of improving cross-building generalization performances when used to select energy consumption data. Keywords Data selection · Domain generalization · Knowledge transfer · Data-driven modeling · Energy consumption modeling
1 Introduction Predictive modeling in buildings plays an integral part in the efficient planning and operation of power systems. Adequate operational data are usually a prerequisite, especially when deep learning is adopted [22,36,38]. Powerful machine learning models should rely on insightful utilization of relevant operational data in a sufficient amount. Nevertheless, building historical data is not always available, such as in newly built and renovated buildings [12].
B
Mouna Labiadh [email protected] Christian Obrecht [email protected] Catarina Ferreira da Silva [email protected] Parisa Ghodous [email protected]
1
LIRIS UMR5205, Univ Lyon, CNRS, Université Claude Bernard Lyon 1, 69100 Villeurbanne, France
2
CETHIL UMR5008, Univ Lyon, CNRS, INSA-Lyon, 69621 Villeurbanne, France
3
Instituto Universitário de Lisboa (ISCTE-IUL), Lisbon, Portugal
Renovation or replacement of existing buildings consider improving their energy efficiency based on energy saving measures (e.g., enhanced thermal insulation, highly energyefficient electrical systems). It plays an important role in reducing the total energy consumption and lowering the greenhouse gas emissions of the existing building stock. Modeling of these buildings thus poses a challenge since that we do not have a priori knowledge about their improved energy consumption performance. Already existing energy consumption data about other buildings can howbeit be obtained. The main idea of our work thus consists in leveraging representative data from multiple different (but related) sour
Data Loading...
