Search results

This study aims to compare and evaluate the application of commonly used machine learning (ML) algorithms used to develop models for assessing energy efficiency of buildings.

This study foremostly combined building energy efficiency ratings from several data sources and used them to create predictive models using a variety of ML methods. Secondly, to test the hypothesis of ensemble techniques, this study designed a hybrid stacking ensemble approach based on the best performing bagging and boosting ensemble methods generated from its predictive analytics.

Based on performance evaluation metrics scores, the extra trees model was shown to be the best predictive model. More importantly, this study demonstrated that the cumulative result of ensemble ML algorithms is usually always better in terms of predicted accuracy than a single method. Finally, it was discovered that stacking is a superior ensemble approach for analysing building energy efficiency than bagging and boosting.

While the proposed contemporary method of analysis is assumed to be applicable in assessing energy efficiency of buildings within the sector, the unique data transformation used in this study may not, as typical of any data driven model, be transferable to the data from other regions other than the UK.

This study aids in the initial selection of appropriate and high-performing ML algorithms for future analysis. This study also assists building managers, residents, government agencies and other stakeholders in better understanding contributing factors and making better decisions about building energy performance. Furthermore, this study will assist the general public in proactively identifying buildings with high energy demands, potentially lowering energy costs by promoting avoidance behaviour and assisting government agencies in making informed decisions about energy tariffs when this novel model is integrated into an energy monitoring system.

This study fills a gap in the lack of a reason for selecting appropriate ML algorithms for assessing building energy efficiency. More importantly, this study demonstrated that the cumulative result of ensemble ML algorithms is usually always better in terms of predicted accuracy than a single method.

At the beginning of the Corona Virus Disease 2019 (COVID-19) pandemic, a digitalized construction environments surfaced in the heating, ventilation and air conditioning (HVAC) systems in the form of a modern delivery system called demand controlled ventilation (DCV). Demand controlled ventilation has the potential to solve the building ventilation's biggest problem of managing indoor air quality (IAQ) for controlling COVID-19 transmission in indoor environments. However, the improper evaluation and information management of infection prevention on dense crowd activities such as measurement errors and volatile organic compound (VOC) generation failure rates, is fragmented so the aim of this research is to integrate this and explore potentials with machine learning algorithms (MLAs).

The method used is a thorough systematic literature review (SLR) approach. The results of this research consist of a detailed description of the DCV system and digitalized construction process of its IAQ elements.

The discussion revealed that DCV has a potential for being further integrated by perceiving it as a MLAs and hereby enabling the management of IAQ level from the perspective of health risk function mechanism (i.e. VOC and CO₂) for maintaining a comfortable thermal environment and save energy of public and private buildings (PPBs). The appropriate MLA can also be selected in different occupancy patterns for seasonal variations, ventilation behavior, building type and locations, as well as current indoor air pollution control strategies. Furthermore, the conceptual framework showed that MLA application such as algorithm design/Model Predictive Control (MPC) integration can alleviate the high spread limitation of COVID-19 in the indoor environment.

Finally, the research concludes that a large unexploited potential within integration and innovation is recognized in the DCV system and MLAs which can be improved to optimize level of IAQ from the perspective of health throughout the building sector DCV process systems. The requirements of CO₂ based DCV along with VOC concentrations monitoring practice should be taken into consideration through further research and experience with adaption and implementation from the ventilation control initial stage of the DCV process.

Buildings require significant energy, and meeting energy demands is becoming exceedingly challenging. Energy demand reduction goals are now prioritised as the demand is rising. Energy-saving improvements and opportunities can be provided if enough information is provided through building energy benchmarking. The study focuses on developing a framework for benchmarking the energy efficiency of residential buildings.

This study applied multiple linear regression analysis to analyse the energy use of residential buildings and establish energy benchmarks. Over 2000 data from Jaipur city were surveyed, and regression analysis was done on 1527 datasets after fundamental statistical analysis. The research considered the significant energy used by household appliances and placed a greater emphasis on end-use appliances.

The comparison of the developed framework with the standard rating plan was carried out to evaluate the accuracy of the benchmarks. The validation of the model determines the gap between the predicted and actual value of the building energy. The recommendations were made for organisations and policymakers to employ multiple or combinations of methods to assess the reliability of the developed benchmark framework.

Policymakers may promote awareness campaigns encouraging homeowners to consume less energy and make buildings more energy efficient. This technique may be applied worldwide with the proper and suitable adjustments and information provided.

To our knowledge, India needs residential building energy benchmarking framework studies. In addition, a new framework based on Composite Indicators was implemented to overcome the scepticism of the EPI/BPI or floor-based approach held by several academics and to offer energy benchmarking for residential buildings.

Solar power forecasting will have a significant impact on the future of large-scale renewable energy plants. Predicting photovoltaic power generation depends heavily on climate conditions, which fluctuate over time. In this research, we propose a hybrid model that combines machine-learning methods with Theta statistical method for more accurate prediction of future solar power generation from renewable energy plants. The machine learning models include long short-term memory (LSTM), gate recurrent unit (GRU), AutoEncoder LSTM (Auto-LSTM) and a newly proposed Auto-GRU. To enhance the accuracy of the proposed Machine learning and Statistical Hybrid Model (MLSHM), we employ two diversity techniques, i.e. structural diversity and data diversity. To combine the prediction of the ensemble members in the proposed MLSHM, we exploit four combining methods: simple averaging approach, weighted averaging using linear approach and using non-linear approach, and combination through variance using inverse approach. The proposed MLSHM scheme was validated on two real-time series datasets, that sre Shagaya in Kuwait and Cocoa in the USA. The experiments show that the proposed MLSHM, using all the combination methods, achieved higher accuracy compared to the prediction of the traditional individual models. Results demonstrate that a hybrid model combining machine-learning methods with statistical method outperformed a hybrid model that only combines machine-learning models without statistical method.

Industrial simulations of turbulent flows often rely on Reynolds-averaged Navier-Stokes (RANS) turbulence models, which contain numerous closure coefficients that need to be calibrated. This paper aims to address this issue by proposing a semi-automated calibration of these coefficients using a new framework (referred to as turbo-RANS) based on Bayesian optimization.

The authors introduce the generalized error and default coefficient preference (GEDCP) objective function, which can be used with integral, sparse or dense reference data for the purpose of calibrating RANS turbulence closure model coefficients. Then, the authors describe a Bayesian optimization-based algorithm for conducting the calibration of these model coefficients. An in-depth hyperparameter tuning study is conducted to recommend efficient settings for the turbo-RANS optimization procedure.

The authors demonstrate that the performance of the k-ω shear stress transport (SST) and generalized k-ω (GEKO) turbulence models can be efficiently improved via turbo-RANS, for three example cases: predicting the lift coefficient of an airfoil; predicting the velocity and turbulent kinetic energy fields for a separated flow; and, predicting the wall pressure coefficient distribution for flow through a converging-diverging channel.

To the best of the authors’ knowledge, this work is the first to propose and provide an open-source black-box calibration procedure for turbulence model coefficients based on Bayesian optimization. The authors propose a data-flexible objective function for the calibration target. The open-source implementation of the turbo-RANS framework includes OpenFOAM, Ansys Fluent, STAR-CCM+ and solver-agnostic templates for user application.

This paper endeavors to create a predictive model for the energy consumption associated with the multi-material fused deposition modeling (FDM) printing process.

An online measurement system for monitoring power and temperature has been integrated into the dual-extruder FDM printer. This system enables a comprehensive study of energy consumption during the dual-material FDM printing process, achieved by breaking down the entire dual-material printing procedure into distinct operational modes. Concurrently, the analysis of the G-code related to the dual-material FDM printing process is carried out.

This work involves an investigation of the execution instructions that delineate the tooling plan for FDM. We measure and simulate the nozzle temperature distributions with varying filament materials. In our work, we capture intricate details of energy consumption accurately, enabling us to predict fluctuations in power demand across different operational phases of multi-material FDM 3D printing processes.

This work establishes a model for quantifying the energy consumption of the dual-material FDM printing process. This model carries significant implications for enhancing the design of 3D printers and advancing their sustainability in mobile manufacturing endeavors.

Coal is the basic energy and essential resource in China, which is crucial to the economic lifeline and energy security of the country. Coal mining has been ever exposed to potential safety risks owing to the complex geologic environment. Effective safety supervision is a vital guarantee for safe production in coal mines. This paper aims to explore the impacts of the internet+ coal mine safety supervision (CMSS) mode that is being emerged in China.

In this study, the key factors influencing CMSS are identified by social network analysis. They are used to develop a multiple linear regression model of law enforcement frequency for conventional CMSS mode, which is then modified by an analytical hierarchy process to predict the law enforcement frequency of internet+ CMSS mode.

The regression model demonstrated high accuracy and reliability in predicting law enforcement frequency. Comparative analysis revealed that the law enforcement frequency in the internet+ mode was approximately 40% lower than the conventional mode. This reduction suggests a potential improvement in cost-efficiency, and the difference is expected to become even more significant with an increase in law enforcement frequency.

To the best of the authors’ knowledge, this is one of the few available pieces of research which explore the cost-efficiency of CMSS by forecasting law enforcement frequency. The study results provide a theoretical basis for promoting the internet+ CMSS mode to realize the healthy and sustainable development of the coal mining industry.

This study aims to examine the price and income elasticities of short- and long-run industrial electricity demand in Brazil between 2003 and 2020. The research also examines the impacts of COVID-19 in Brazil’s industrial electricity sector, including an analysis in states more and less industrialized.

Dynamic adjustments models in panel data are used to present robust estimates and analyze the impact of different methodologies on reported elasticities.

The short-run price elasticity is estimated at −0.448, while the long-run values are around −1.60. Regarding income elasticity, the value is 0.069 in the short-run and is concentrated in 0.25 in the long-run. The inelastic results of income show that the industrial demand for electric energy follows the trend of loss of competitiveness of the Brazilian industry in the past years. In addition, the price of natural gas, the level of employment, and, in specific cases, the level of imports also influence industrial electricity demand.

The research is a pioneer in the investigation of the industrial behavior of electricity of the Brazilian industrial branch, using as control variables, the average temperature, and the level of rainfall, this one, so important for a country whose main source is hydroelectric. In addition, to the best of the authors’ knowledge, it is the first study, which is prepared to analyze the effects of COVID-19 on electric consumption in the industrial sector, investigating these impacts, including in the states considered more and less industrialized. The estimates generated may help in the design of the Brazilian energy policy.

Near-fault pulse-like ground motions have distinct and very severe effects on reinforced concrete (RC) structures. However, there is a paucity of recorded data from Near-Fault Ground Motions (NFGMs), and thus forecasting the dynamic seismic response of structures, using conventional techniques, under such intense ground motions has remained a challenge.

The present study utilizes a 2D finite element model of an RC structure subjected to near-fault pulse-like ground motions with a focus on the storey drift ratio (SDR) as the key demand parameter. Five machine learning classifiers (MLCs), namely decision tree, k-nearest neighbor, random forest, support vector machine and Naïve Bayes classifier , were evaluated to classify the damage states of the RC structure.

The results such as confusion matrix, accuracy and mean square error indicate that the Naïve Bayes classifier model outperforms other MLCs with 80.0% accuracy. Furthermore, three MLC models with accuracy greater than 75% were trained using a voting classifier to enhance the performance score of the models. Finally, a sensitivity analysis was performed to evaluate the model's resilience and dependability.

The objective of the current study is to predict the nonlinear storey drift demand for low-rise RC structures using machine learning techniques, instead of labor-intensive nonlinear dynamic analysis.

Sustainable development hinges on a crucial shift to renewable energy, which is essential in the fight against global warming and climate change. This study explores the relationships between artificial intelligence (AI), fuel, green stocks, geopolitical risk, and Ethereum energy consumption (ETH) in an era of rapid technological advancement and growing environmental concerns.

This research stands at the forefront of interdisciplinary research and forges a path toward a comprehensive understanding of the intricate dynamics governing green sustainability investments. These objectives have been fulfilled by implementing the innovative quantile time-frequency connectedness approach in conjunction with geopolitical and climate considerations.

Our findings highlight coal market dominance and Ethereum energy consumption as critical short- and long-term market volatility sources. Additionally, geopolitical risks and Ethereum energy consumption significantly contribute to volatility. Long-term factors are the primary drivers of directional volatility spillover, impacting green stocks and energy assets over extended periods. Additionally, SHapley Additive exPlanations (SHAP) findings corroborate the quantile time-frequency connectedness outcomes.

This study highlights the critical importance of transitioning to sustainable energy sources and embracing digital finance in fostering green sustainability investments, illuminating their roles in shaping market dynamics, influencing geopolitics and ensuring the long-term sustainability required to combat climate change effectively.

The study offers practical sustainability implications by informing green investment choices, strengthening risk management strategies, encouraging interdisciplinary cooperation and fostering digital finance innovations to promote sustainable practices.

The implementation of the quantile time-frequency connectedness approach, in line with considering geopolitical and climate factors, marks the originality of this paper. This approach allows for a dynamic analysis of connectedness across different distribution quantiles, providing a deeper understanding of variable interactions under varying market conditions.