Benchmark of identification methods for the estimation of building wall thermal resistance using active method: Numerical study for IWI and single-wall structures

Ha, Thanh-Tung; Feuillet, Vincent; Waeytens, Julien; Zibouche, Kamel; Thébault, Simon; Bouchié, Rémi; Sant, Véronique Le; Ibos, Laurent

doi:10.1016/j.enbuild.2020.110130

Cited by 13 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Statistical machine learning methods implement a straightforward linear regression model [20] for modeling the pattern among predictors to deal with internal gains and solar gains [21,22]. Similarly, [22] proposed a linear regression method to analyze the energy consumption by using conditional demand analysis.…”

Section: Literature Reviewmentioning

confidence: 99%

“…We utilized various assessment metrics such as mean square error (MSE), root means square error (RMSE), mean average percentage error (MAPE) and mean absolute error (MAE) to evaluate the performance of the proposed system. A mathematical representation of all these assessment metrics is expressed in Equation (19)(20)(21)(22). The MAE metric reports the difference of the predicted variables in percentage and variation among predicted and testing variables are represented by RMSE.…”

Section: B Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

2021

View full text Add to dashboard Cite

Industrial and building sectors demand efficient smart energy strategies, techniques of optimization, and efficient management for reducing global energy consumption due to the increasing world population. Nowadays, various artificial intelligence (AI) based methods are utilized to perform optimal energy forecasting, different simulation tools, and engineering methods to predict future demand based on historical data. Nevertheless, nonlinear energy demand modeling is still unfledged for a better solution to handle short-term and long-term dependencies and avoid static nature because it is purely on historical datadriven. In this paper, we propose an ensemble deep learning-based approach to predict and forecast energy demand and consumption by using chronological dependencies. Our system initially processes the data, cleaning, normalization, and transformation to ensure the model performance. Furthermore, the preprocess data is fed to propose the ensemble model to extract hybrid discriminative features by using convolution neural network (CNN), stacked, and bi-directional long-short term memory (LSTM) architectures. We trained our proposed system on the historical data to forecast the energy demand and consumption with a different time interval. In the proposed technique, we utilized the concept of active learning based on moving windows to ensure and improve the prediction performance of the system. The proposed system could be applicable to employ energy consumption in industrial and building sectors to demonstrate their significance and effectiveness. We evaluated the proposed system by using benchmark, residential UCI, and local Korean commercial building datasets. We conducted different extensive experimentation to show the error rate and used various kinds of evaluation matrices, which indicate the lower error rate of the proposed system.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: B Evaluation Metricsmentioning

confidence: 99%

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

2021

View full text Add to dashboard Cite

show abstract

“…Depending on the energy system, there are many existing characterization techniques [ 40 ]. For building envelope characterization, several industrial and experimental methods have also been developed [ 41 , 42 , 43 ]. Nevertheless, most methods were too specific and costly for our research project.…”

Section: Feedback On the Implementation And Operation Of The Sensor N...mentioning

confidence: 99%

A Wireless Sensor Network for Residential Building Energy and Indoor Environmental Quality Monitoring: Design, Instrumentation, Data Analysis and Feedback

Bourdeau,

Waeytens,

Aouani

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

This article outlines the implementation and use of a large wireless instrumentation solution to collect data over a long time period of a few years for three collective residential buildings. The sensor network consists of a variety of 179 sensors deployed in building common areas and in apartments to monitor energy consumption, indoor environmental quality, and local meteorological conditions. The collected data are used and analyzed to assess the building performance in terms of energy consumption and indoor environmental quality following major renovation operations on the buildings. Observations from the collected data show energy consumption of the renovated buildings in agreement with expected energy savings calculated by an engineering office, many different occupancy patterns mainly related to the professional situation of the households, and seasonal variation in window opening rates. The monitoring was also able to detect some deficiencies in the energy management. Indeed, the data reveal the absence of time-of-day-dependent heating load control and higher than expected indoor temperatures because of a lack of occupant awareness on energy savings, thermal comfort, and the new technologies installed during the renovation such as thermostatic valves on the heaters. Lastly, we also provide feedback on the performed sensor network from the experiment design and choice of measured quantities to data communication, through the sensors’ technological choices, implementation, calibration, and maintenance.

show abstract

“…The physical elements, such as the building envelope (walls, roof, floor, etc. ), and the windows, shades, etc., are considered as single-layered or multilayered elements for developing building energy models [16,17]. Single-layered modeling has been mostly used to develop energy control strategies for heating, ventilation, and air-conditioning (HVAC) [18][19][20] and lighting systems [21,22].…”

Section: Literature Surveymentioning

confidence: 99%

Assessment of State-Space Building Energy System Models in Terms of Stability and Controllability

et al. 2021

View full text Add to dashboard Cite

Building energy management system involves the development of control strategies for the heating, ventilation, and air-conditioning (HVAC), as well as lighting, systems. Building energy modeling is a significant part of designing such strategies. In order to analyze the feasibility of a building energy system model for any desired control strategy, a mathematical assessment tool is developed in this paper. A multi-input multi-output (MIMO) building energy system model, consisting of an outdoor wall, an external wall, two partition walls, one roof, and a ceiling, has been considered as the virtual test setup. A methodology for conducting stability and controllability assessment tests on the building energy model is proposed using inverse dynamics input theory (IDIT). IDIT enables the decoupling of control variables so as to enable the conversion of an MIMO system to a number of independent single-input single-output systems. The controllability is assessed based on the design properties for continuous systems: asymptotes and transmission zeros. The results show that the relative humidity and air temperature of the building space were controllable for all operating points; however, in unconditioned situations, where the humidity levels of the building space were greater than that of the outdoor levels, the models were unstable.

show abstract

Benchmark of identification methods for the estimation of building wall thermal resistance using active method: Numerical study for IWI and single-wall structures

Cited by 13 publications

References 29 publications

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

A Wireless Sensor Network for Residential Building Energy and Indoor Environmental Quality Monitoring: Design, Instrumentation, Data Analysis and Feedback

Assessment of State-Space Building Energy System Models in Terms of Stability and Controllability

Contact Info

Product

Resources

About