The development of data-driven building energy consumption prediction models has gained more attention in research due to its relevance for energy planning and conservation. However, many studies have conducted the inappropriate application of data-driven tools for energy consumption prediction in the wrong conditions. For example, employing a data-driven tool to develop a model using a small sample size, despite the recognition of the tool for producing good results in large data conditions. This study delivers a review of 63 studies with a precise focus on evaluating the performance of data-driven tools based on certain conditions; i.e., data properties, the type of energy considered, and the type of building explored. This review identifies gaps in research and proposes future directions in the field of data-driven building energy consumption prediction. Based on the studies reviewed, the outcome of the evaluation of the data-driven tools performance shows that Support Vector Machine (SVM) produced better performance than other data-driven tools in the majority of the review studies. SVM, Artificial Neural Network (ANN), and Random Forest (RF) produced better performances in more studies than statistical tools such as Linear Regression (LR) and Autoregressive Integrated Moving Average (ARIMA). However, it is deduced that none of the reviewed tools are predominantly better than the other tools in all conditions. It is clear that data-driven tools have their strengths and weaknesses, and tend to elicit distinctive results in different conditions. Hence, this study provides a proposed guideline for the selection tool based on strengths and weaknesses in different conditions.
In recent years, there has been a surge in the global digitization of corporate processes and concepts such as digital technology development which is growing at such a quick pace that the construction industry is struggling to catch up with latest developments. A formidable digital technology, artificial intelligence (AI), is recognized as an essential element within the paradigm of digital transformation, having been widely adopted across different industries. Also, AI is anticipated to open a slew of new possibilities for how construction projects are designed and built. To obtain a better knowledge of the trend and trajectory of research concerning AI technology application in the construction industry, this research presents an exhaustive systematic review of seventy articles toward AI applicability to the entire lifecycle of the construction value chain identified via the guidelines outlined by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). The review’s findings show foremostly that AI technologies are mostly used in facility management, creating a huge opportunity for the industry to profit by allowing facility managers to take proactive action. Secondly, it shows the potential for design expansion as a key benefit according to most of the selected literature. Finally, it found data augmentation as one of the quickest prospects for technical improvement. This knowledge will assist construction companies across the world in recognizing the efficiency and productivity advantages that AI technologies can provide while helping them make smarter technology investment decisions.
Purpose: 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. Design/methodology/approach: 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. Findings: 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. Research limitations/implications: 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. Practical implications: 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. Originality/value: 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.
12 December 2022 in Smart and Sustainable Built Environment
Purpose: Several factors influence OSC adoption, but extant literature did not articulate the dominant barriers or drivers influencing adoption. Therefore, this research has not only ventured into analyzing the core influencing factors but has also employed one of the best-known predictive means, Machine Learning, to identify the most influencing OSC adoption factors.Design/methodology/approach: The research approach is deductive in nature, focusing on finding out the most critical factors through literature review and reinforcing — the factors through a 5- point Likert scale survey questionnaire. The responses received were tested for reliability before being run through Machine Learning algorithms to determine the most influencing OSC factors within the Nigerian Construction Industry (NCI).Findings: The research outcome identifies seven (7) best-performing algorithms for predicting OSC adoption: Decision Tree, Random Forest, K-Nearest Neighbour, Extra-Trees, AdaBoost, Support Vector Machine and Artificial Neural Network. It also reported finance, awareness, use of Building Information Modeling (BIM) and belief in OSC as the main influencing factors.Research limitations/implications: Data were primarily collected among the NCI professionals/workers and the whole exercise was Nigeria region-based. The research outcome, however, provides a foundation for OSC adoption potential within Nigeria, Africa and beyond.Practical implications: The research concluded that with detailed attention paid to the identified factors, OSC usage could find its footing in Nigeria and, consequently, Africa. The models can also serve as a template for other regions where OSC adoption is being considered.Originality/value: The research establishes the most effective algorithms for the prediction of OSC adoption possibilities as well as critical influencing factors to successfully adopting OSC within the NCI as a means to surmount its housing shortage.