scholarly journals An Intelligent Model to Predict Energy Performances of Residential Buildings Based on Deep Neural Networks

Energies ◽  
2020 ◽  
Vol 13 (3) ◽  
pp. 571 ◽  
Author(s):  
Azadeh Sadeghi ◽  
Roohollah Younes Sinaki ◽  
William A. Young ◽  
Gary R. Weckman
Keyword(s):  
Neural Networks ◽  
Sensitivity Analysis ◽  
Goodness Of Fit ◽  
Deep Neural Networks ◽  
Residential Buildings ◽  
Independent Set ◽  
Energy Performance ◽  
Processing Technique ◽  
Building Structures ◽  
Wall Area

As the level of greenhouse gas emissions increases, so does the importance of the energy performance of buildings (EPB). One of the main factors to measure EPB is a structure’s heating load (HL) and cooling load (CL). HLs and CLs depend on several variables, such as relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution. This research uses deep neural networks (DNNs) to forecast HLs and CLs for a variety of structures. The DNNs explored in this research include multi-layer perceptron (MLP) networks, and each of the models in this research was developed through extensive testing with a myriad number of layers, process elements, and other data preprocessing techniques. As a result, a DNN is shown to be an improvement for modeling HLs and CLs compared to traditional artificial neural network (ANN) models. In order to extract knowledge from a trained model, a post-processing technique, called sensitivity analysis (SA), was applied to the model that performed the best with respect to the selected goodness-of-fit metric on an independent set of testing data. There are two forms of SA—local and global methods—but both have the same purpose in terms of determining the significance of independent variables within a model. Local SA assumes inputs are independent of each other, while global SA does not. To further the contribution of the research presented within this article, the results of a global SA, called state-based sensitivity analysis (SBSA), are compared to the results obtained from a traditional local technique, called sensitivity analysis about the mean (SAAM). The results of the research demonstrate an improvement over existing conclusions found in literature, which is of particular interest to decision-makers and designers of building structures.

scholarly journals Application of sensitivity analysis and genopt to optimize the energy performance of a building in Morocco

2018 ◽  
Vol 7 (4) ◽  
pp. 2068 ◽  
Author(s):  
Abdelhadi Serbouti ◽  
Mourad Rattal ◽  
Abdellah Boulal ◽  
Mohammed Harmouchi ◽  
Azeddine Mouhsen
Keyword(s):  
Sensitivity Analysis ◽  
Residential Buildings ◽  
Energy Performance ◽  
High Energy ◽  
Performance Requirement ◽  
Input Parameters ◽  
Sensitivity Analysis Method ◽  
Python Programming ◽  
Industry Sectors ◽  
High Energy Consumption

The worldwide demographic and economic growth increases the global need for energy and directly contributes to climate change. In Morocco, the residential real estate is the third largest consumer of energy after transport and industry sectors. Thus, the aim of this study is to help engineers improve the energy performance of residential buildings by coupling the TRNSYS software both with a sensitivity analysis method and with an optimization tool. In fact, sensitivity analysis allows reducing the number of input parameters of any studied model, by ranking their degree of impact on any chosen output, and then discard the parameters with the least influence on that output. To do so, we developed algorithms in Python programming language to combine the open source library SALib, available in Github platform, with the TRNSYS software. Then, the chosen input parameters can be optimized through coupling the generic optimization program Genopt with TRNSYS. This article will also explain how these tools were applied to reduce the heating & air-conditioning needs of a high-energy consumption building in Morocco, while studying the variation of nineteen input parameters in TRNSYS. The main aim is to meet the energy performance requirement of the Moroccan thermal regulation for buildings.  

ANALYZING PLANNING SOLUTIONS FOR RESIDENTIAL BUILDINGS WITH ACCOUNT OF THEIR ENERGY EFFICIENCY

2015 ◽  
Vol 5 (4) ◽  
pp. 104-107
Author(s):  
Yuriy Pavlovich SOLOGUBOV ◽  
Tatyana Evgen'evna GORDEEVA
Keyword(s):  
Energy Efficiency ◽  
Energy Efficient ◽  
Residential Buildings ◽  
Energy Performance ◽  
Heat Losses ◽  
Building Structures ◽  
Space Planning ◽  
Efficient Planning ◽  
Key Dimensions

The paper introduces the analysis of interrelation of a space planning solution with energy efficiency of building envelops and building structures insolation. The aim of the research is to find out an energy-efficient planning solution for a definite construction area, that of Samara city. The authors compare buildings key dimensions and introduce their energy performance certificates. Heat losses through front building envelops are also calculated. The paper concludes that from the standpoint of their energy efficiency corridor-type arrangements are preferable to tower blocks.

scholarly journals Tuning Deep Neural Networks for Predicting Energy Consumption in Arid Climate Based on Buildings Characteristics

2021 ◽  
Vol 13 (22) ◽  
pp. 12442
Author(s):  
Amal A. Al-Shargabi ◽  
Abdulbasit Almhafdy ◽  
Dina M. Ibrahim ◽  
Manal Alghieth ◽  
Francisco Chiclana
Keyword(s):  
Neural Networks ◽  
Energy Consumption ◽  
Mean Square Error ◽  
Deep Neural Networks ◽  
Prediction Models ◽  
Residential Buildings ◽  
Arid Climate ◽  
Mean Square ◽  
Heating And Cooling ◽  
Cooling Loads

The dramatic growth in the number of buildings worldwide has led to an increase interest in predicting energy consumption, especially for the case of residential buildings. As the heating and cooling system highly affect the operation cost of buildings; it is worth investigating the development of models to predict the heating and cooling loads of buildings. In contrast to the majority of the existing related studies, which are based on historical energy consumption data, this study considers building characteristics, such as area and floor height, to develop prediction models of heating and cooling loads. In particular, this study proposes deep neural networks models based on several hyper-parameters: the number of hidden layers, the number of neurons in each layer, and the learning algorithm. The tuned models are constructed using a dataset generated with the Integrated Environmental Solutions Virtual Environment (IESVE) simulation software for the city of Buraydah city, the capital of the Qassim region in Saudi Arabia. The Qassim region was selected because of its harsh arid climate of extremely cold winters and hot summers, which means that lot of energy is used up for cooling and heating of residential buildings. Through model tuning, optimal parameters of deep learning models are determined using the following performance measures: Mean Square Error (MSE), Root Mean Square Error (RMSE), Regression (R) values, and coefficient of determination (R2). The results obtained with the five-layer deep neural network model, with 20 neurons in each layer and the Levenberg–Marquardt algorithm, outperformed the results of the other models with a lower number of layers. This model achieved MSE of 0.0075, RMSE 0.087, R and R2 both as high as 0.99 in predicting the heating load and MSE of 0.245, RMSE of 0.495, R and R2 both as high as 0.99 in predicting the cooling load. As the developed prediction models were based on buildings characteristics, the outcomes of the research may be relevant to architects at the pre-design stage of heating and cooling energy-efficient buildings.

scholarly journals Diverse deep neural networks all predict human IT well, after training and fitting

2020 ◽  
Author(s):  
Katherine R. Storrs ◽  
Tim C. Kietzmann ◽  
Alexander Walther ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
High Performance ◽  
Deep Neural Networks ◽  
Model Fitting ◽  
Receptive Fields ◽  
Recognition Task ◽  
Independent Set ◽  
Dissimilarity Matrix ◽  
Weighted Combination

ABSTRACTDeep neural networks (DNNs) trained on object recognition provide the best current models of high-level visual areas in the brain. What remains unclear is how strongly network design choices, such as architecture, task training, and subsequent fitting to brain data contribute to the observed similarities. Here we compare a diverse set of nine DNN architectures on their ability to explain the representational geometry of 62 isolated object images in human inferior temporal (hIT) cortex, as measured with functional magnetic resonance imaging. We compare untrained networks to their task-trained counterparts, and assess the effect of fitting them to hIT using a cross-validation procedure. To best explain hIT, we fit a weighted combination of the principal components of the features within each layer, and subsequently a weighted combination of layers. We test all models across all stages of training and fitting for their correlation with the hIT representational dissimilarity matrix (RDM) using an independent set of images and subjects. We find that trained models significantly outperform untrained models (accounting for 57% more of the explainable variance), suggesting that features representing natural images are important for explaining hIT. Model fitting further improves the alignment of DNN and hIT representations (by 124%), suggesting that the relative prevalence of different features in hIT does not readily emerge from the particular ImageNet object-recognition task used to train the networks. Finally, all DNN architectures tested achieved equivalent high performance once trained and fitted. Similar ability to explain hIT representations appears to be shared among deep feedforward hierarchies of nonlinear features with spatially restricted receptive fields.

scholarly journals Bilateral Sensitivity Analysis for Understandable Neural Networks and its application to Reservoir Engineering

2020 ◽  
Author(s):  
Jian Wang ◽  
Huaqing Zhang ◽  
Kai Zhang ◽  
Nikhil Ranjan Pal
Keyword(s):  
Neural Networks ◽  
Sensitivity Analysis ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Water Injection ◽  
Superior Performance ◽  
Reservoir Engineering ◽  
Model Independent ◽  
The Relationship ◽  
Subsequent Layer

<div>In this paper, a model-independent sensitivity analysis</div><div>for (deep) neural network, Bilateral Sensitivity Analysis (BiSA), is proposed to measure the relationship between neurons and layers. Both the BiSA between pair of layers and the BiSA between any pair neurons in different layers are defined for (deep) neural networks. This sensitivity can measure the influence or contribution from any layer to another layer behind this layer in the (deep) neural networks. It provides a helpful tool to interpret the learned model. The BiSA can also measure the influence or contribution from any neuron to another neuron in a subsequent layer and is critical to analyze the relationship between neurons in different layers. Then the BiSA from any input to any output of a network is easily defined to assess the connections between the inputs and outputs. The proposed BiSA of (deep) neural networks is then applied to characterize the well connectivity in reservoir engineering. Given a network trained by Water Injection Rates (WIRs) and Liquid Production Rates (LPRs) data, the well connectivity can be efficiently described through BiSA. The empirical results verify the effectiveness of</div><div>the proposed method. The comparisons with the exiting methods demonstrate the robustness and the superior performance of the proposed method.</div>

scholarly journals Investigating the Interrelationships among Occupant Attitude, Knowledge and Behaviour in LEED-Certified Buildings Using Structural Equation Modelling

Energies ◽  
2020 ◽  
Vol 13 (12) ◽  
pp. 3158
Author(s):  
Mehreen Saleem Gul ◽  
Elmira NezamiFar
Keyword(s):  
Energy Consumption ◽  
Structural Equation Modelling ◽  
Latent Variables ◽  
Structural Equation ◽  
Goodness Of Fit ◽  
Residential Buildings ◽  
Environmentally Friendly ◽  
Energy Performance ◽  
Equation Modelling ◽  
The Impact

The proliferation of residential building energy consumption and CO2 emissions has led many countries to develop buildings under the green rating systems umbrella. Many such buildings, however, fail to meet their designed energy performance, which is possibly attributable to occupant behaviour and unforeseen building usages. The research problem lies in the fact that occupant environmental behaviour is a complex socio-cultural-technical issue that needs to be addressed to achieve the desired energy savings. This study is novel as it investigates complex interrelationships between many observed and unobserved variables using data from four LEED-certified multi-residential buildings in the United Arab Emirates. Structural Equation Modelling was used to analyse the impact of three unobserved/latent variables: occupant environmental Attitude, Knowledge and Behaviour (AKB) with respect to occupant energy consumption, based on measured/observed variables. Although our Goodness-of-Fit values indicated that we achieved a good model fit, the interrelationship between Knowledge and Behaviour (p = 0.557) and between Attitude and Behaviour (p = 0.931) was insignificant, as the p-values > 0.05. The key study outcomes were: (i) providing information alone could not motivate people towards environmentally friendly behaviour; (ii) even changes in their attitude, belief and lifestyle were not significantly related to their behaviour, as the interrelationships among occupant environmental AKB were not significant; and (iii) knowledge and attitude change should be combined with other motivational factors to trigger environmentally friendly actions and influence behaviour.

scholarly journals Bilateral Sensitivity Analysis for Understandable Neural Networks and its application to Reservoir Engineering

2020 ◽  
Author(s):  
Jian Wang ◽  
Huaqing Zhang ◽  
Kai Zhang ◽  
Nikhil Ranjan Pal
Keyword(s):  
Neural Networks ◽  
Sensitivity Analysis ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Water Injection ◽  
Superior Performance ◽  
Reservoir Engineering ◽  
Model Independent ◽  
The Relationship ◽  
Subsequent Layer

<div>In this paper, a model-independent sensitivity analysis</div><div>for (deep) neural network, Bilateral Sensitivity Analysis (BiSA), is proposed to measure the relationship between neurons and layers. Both the BiSA between pair of layers and the BiSA between any pair neurons in different layers are defined for (deep) neural networks. This sensitivity can measure the influence or contribution from any layer to another layer behind this layer in the (deep) neural networks. It provides a helpful tool to interpret the learned model. The BiSA can also measure the influence or contribution from any neuron to another neuron in a subsequent layer and is critical to analyze the relationship between neurons in different layers. Then the BiSA from any input to any output of a network is easily defined to assess the connections between the inputs and outputs. The proposed BiSA of (deep) neural networks is then applied to characterize the well connectivity in reservoir engineering. Given a network trained by Water Injection Rates (WIRs) and Liquid Production Rates (LPRs) data, the well connectivity can be efficiently described through BiSA. The empirical results verify the effectiveness of</div><div>the proposed method. The comparisons with the exiting methods demonstrate the robustness and the superior performance of the proposed method.</div>

Sign in / Sign up

Export Citation Format

Share Document