Abstract:Abstractachine learning methods can be used to help design energy-efficient buildings reducing energy loads while maintaining the desired internal temperature. They work by estimating a response from a set of inputs such as building geometry, material properties, project costs, local weather conditions, as well as environmental impacts. These methods require a training phase which considers a dataset drawn from selected variables in the problem domain. This paper evaluates the performance of four machine learn… Show more
“…In contrast, our proposed model is better than the others existing baseline models because, we employed a sequential learning model for nonsequential data which improved the SO and MO performances on both hold-out and 10-fold. Table 7 presents the SO results based on the hold-out technique with recent state-of the-art models [2,4,12,22,23,25,26,28,[31][32][33][34][35][36]44]. For HL prediction, the proposed model (GRU) achieved the least error rates for MAE (0.0102), MSE (0.0003), and RMSE (0.0166).…”
Section: Comparison With State-of-the-art Modelsmentioning
In the current technological era, energy-efficient buildings have a significant research body due to increasing concerns about energy consumption and its environmental impact. Designing an appropriate energy-efficient building depends on its layout, such as relative compactness, overall area, height, orientation, and distribution of the glazing area. These factors directly influence the cooling load (CL) and heating load (HL) of residential buildings. An accurate prediction of these load facilitates a better management of energy consumption and enhances the living standards of inhabitants. Most of the traditional machine learning (ML)-based approaches are designed for single-output (SO) prediction, which is a tedious task due to separate training processes for each output with low performance. In addition, these approaches have a high level of nonlinearity between input and output, which need more enhancement in terms of robustness, predictability, and generalization. To tackle these issues, we propose a novel framework based on gated recurrent unit (GRU) that reliably predicts the CL and HL concurrently. To the best of our knowledge, we are the first to propose a multi-output (MO) sequential learning model followed by utility preprocessing under the umbrella of a unified framework. A comprehensive set of ablation studies on ML and deep learning (DL) techniques is done over an energy efficiency dataset, where the proposed model reveals an incredible performance as compared to other existing models.
“…In contrast, our proposed model is better than the others existing baseline models because, we employed a sequential learning model for nonsequential data which improved the SO and MO performances on both hold-out and 10-fold. Table 7 presents the SO results based on the hold-out technique with recent state-of the-art models [2,4,12,22,23,25,26,28,[31][32][33][34][35][36]44]. For HL prediction, the proposed model (GRU) achieved the least error rates for MAE (0.0102), MSE (0.0003), and RMSE (0.0166).…”
Section: Comparison With State-of-the-art Modelsmentioning
In the current technological era, energy-efficient buildings have a significant research body due to increasing concerns about energy consumption and its environmental impact. Designing an appropriate energy-efficient building depends on its layout, such as relative compactness, overall area, height, orientation, and distribution of the glazing area. These factors directly influence the cooling load (CL) and heating load (HL) of residential buildings. An accurate prediction of these load facilitates a better management of energy consumption and enhances the living standards of inhabitants. Most of the traditional machine learning (ML)-based approaches are designed for single-output (SO) prediction, which is a tedious task due to separate training processes for each output with low performance. In addition, these approaches have a high level of nonlinearity between input and output, which need more enhancement in terms of robustness, predictability, and generalization. To tackle these issues, we propose a novel framework based on gated recurrent unit (GRU) that reliably predicts the CL and HL concurrently. To the best of our knowledge, we are the first to propose a multi-output (MO) sequential learning model followed by utility preprocessing under the umbrella of a unified framework. A comprehensive set of ablation studies on ML and deep learning (DL) techniques is done over an energy efficiency dataset, where the proposed model reveals an incredible performance as compared to other existing models.
“…While accuracy and robustness increase compared to a single tree, interpretability of the model significantly decreases. Furthermore, the accuracy of tree ensembles, such as random forest, is in many cases still inferior to that of other techniques for engineering problems [20,96].…”
Heating electrification and distributed renewable generation in the residential sector are among prominent solutions advocated for energy saving and carbon emission reduction. However, research shows these low-carbon technologies may create issues at the low-voltage (LV) distribution grid. High-level policy assessment currently lacks the support to take into account such local grid restrictions. To achieve this, we propose the use of a probabilistic simulation framework in combination with metamodeling, that allows to assess the potential LV grid impact for a wide range of cases. The probabilistic framework is first presented, which is developed for Belgian residential neighborhoods with air-source heat pumps and rooftop PV, based on previous work. Given the complexity and computational requirements of this approach, the paper furthermore proposes metamodeling as a technique to obtain inexpensive evaluation of low-voltage grid impact indicators, suitable for high-level assessments. Although metamodeling is extensively used in various engineering domains, no application in district-level grid-related indicators is available. Consequently, this paper's focus lies on discussing the various steps and options of the metamodeling procedure, while emphasizing problemspecific challenges. Lastly, the proposed metamodeling methodology is used for training simple metamodels for voltage indicators in neighborhood-level LV grids. Linear regression performed fairly well in predicting the minimum voltage levels, though less accurately close to the lower voltage limit, while logistic regression effectively detected feeders with violations.
System modeling is a main task in several research fields. The development of numerical models is of crucial importance at the present because of its wide use in the applications of the generically named machine learning technology, including different kinds of neural networks, random field models, and kernel-based methodologies. However, some problems involving the reliability of their predictions are common to their use in the real world. Octahedric regression is a kernel averaged methodology developed by the authors that tries to simplify the entire process from raw data acquisition to model generation. A discussion about the treatment and prevention of overfitting is presented and, as a result, models are obtained that allow for the measurement of this effect. In this paper, this methodology is applied to the problem of estimating the energetic needs of different buildings according to their principal characteristics, a problem that has importance in architecture and civil and environmental engineering due to increasing concerns about energetic efficiency and ecological footprint.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.