Search

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. info:eu-repo/semantics/acceptedVersion

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., Service Oriented Computing and Applications, Springer, 2020

This paper presents the design and the characterisation of a high powered energy dense zeolite thermal heat storage system using water vapour sorbate. The specification requirements of the system are to supply a heating power of 2 kW during 2 h in order to shave the electricity peak loads in a house. The open reactor has been designed, built and instrumented with temperature sensors, chilled mirror hygrometer and airflow meter. Several tests have been carried out both during hydration – heat release – and dehydration – heat storage. Tests have also been carried out for different flow rates, relative humidity and temperatures of hydration. The results show that the reactor can supply a constant power of 2.25 kW during more than two hours, namely 27.5 W kg−1 of material.

Thermal flow prediction is a subject of interest from a scientific and engineering points of view. Our motivation is to develop an accurate, easy to implement and highly scalable method for convective flows simulation. To this end, we present an extension to the link-wise artificial compressibility method (LW-ACM) for thermal simulation of weakly compressible flows. The novel hybrid formulation uses second-order finite difference operators of the energy equation based on the same stencils as the LW-ACM. For validation purposes, the differentially heated cubic cavity was simulated. The simulations remained stable for Rayleigh numbers up to Ra = 10 8 . The Nusselt numbers at isothermal walls and dynamics quantities are in good agreement with reference values from the literature. Our results show that the hybrid thermal LW-ACM is an effective and easy-to-use solution to solve convective flows.

International audience; The link-wise artificial compressibility method (LW-ACM) is a recent formulation of the artificial compressibility method for solving the incompressible Navier-Stokes equations. Two implementations of the LW-ACM in three dimensions on CUDA enabled GPUs are described. The first one is a modified version of a state-of-the-art CUDA implementation of the lattice Boltzmann method (LBM), showing that an existing GPU LBM solver might easily be adapted to LW-ACM. The second one follows a novel approach, which leads to a performance increase of up to 1.8× compared to the LBM implementation considered here, while reducing the memory requirements by a factor of 5.25. Large-scale simulations of the lid-driven cubic cavity at Reynolds number Re=2000Re=2000 were performed for both LW-ACM and LBM. Comparison of the simulation results against spectral elements reference data shows that LW-ACM performs almost as well as multiple-relaxation-time LBM in terms of accuracy.

International audience; In this contribution, a single-node multi-GPU thermal lattice Boltzmann solver is presented. We implement a simplified version of the hybrid model developed by Lallemand and Luo in 2003, which combines multiple-relaxation-time lattice Boltzmann for the fluid flow with a finite-difference method for temperature. The program is based on the TheLMA framework which was developed for that purpose. The chosen implementation and optimisation strategies are described, both for inter-GPU communication and for coupling with the thermal component of the model. Validation and performance results are provided as well.

International audience; Interpolated bounce-back boundary conditions for the lattice Boltzmann method (LBM) make the accurate representation of complex geometries possible. In the present work, we describe an implementation of a linearly interpolated bounce-back (LIBB) boundary condition for graphics processing units (GPUs). To validate our code, we simulated the flow past a sphere in a square channel. At low Reynolds numbers, results are in good agreement with experimental data. Moreover, we give an estimate of the critical Reynolds number for transition from steady to periodic flow. Performance recorded on a single node server with eight GPU based computing devices ranged up to 2.63×1092.63×109 fluid node updates per second. Comparison with a simple bounce-back version of the solver shows that the impact of LIBB on performance is fairly low.