• Energy Research

Abstract The development of advanced data-driven approaches for building energy management is becoming increasingly essential in the era of big data. Machine learning techniques have gained great popularity in predictive modeling due to their excellence in capturing nonlinear and complicated relationships. However, it is a big challenge for building professionals to fully understand the inference mechanism learnt and put trust into the prediction made, as the models developed are typically of high complexity and low interpretability. To enhance the practical value of advanced machine learning techniques in the building field, this study proposes a comprehensive methodology to explain and evaluate data-driven building energy performance models. The methodology is developed based on the framework of interpretable machine learning. It can help building professionals to understand the inference mechanism learnt, e.g., why a certain prediction is made and what are the supporting and conflicting evidences towards the prediction. A novel metric, i.e., trust, is proposed as an alternative approach other than conventional accuracy metrics to evaluate model performance. The methodology has been validated based on actual building operational data. The results obtained are valuable for the development of intelligent and user-friendly building management systems.

Abstract Global governments only collect landfill taxes and fees for the disposal of most construction waste and ignore discount and economic compensation measures. Thus, stimulating construction contractors’ enthusiasm for recycling waste resources becomes difficult, and construction waste utilization remains at a comparatively low level. This study first constructs a compensation model of evolutionary game for construction waste treatment costs, wherein the government, developer, and contractor are the players. It aims to solve the corresponding game equilibrium points. Then, this work establishes a stock-flow diagram of the evolutionary game among the three players using the system dynamics principle to analyze the stability of the local equilibrium points obtained during the evolutionary game. The research conclusion can improve the theory of construction waste management in the theoretical contribution, especially in the field of economic incentive theory. On the other hand, the practical significance of this paper lies in exploring the active measures to lead the contractors and developers willing to recycle and reuse waste, and promoting the recycling rate of construction waste.

Abstract Energy consumption of buildings is at the forefront of the total energy consumption list, and its environmental impact is increasing, thus making construction industry as a key player in energy. A systematic and comprehensive life cycle perspective assessment of building energy is crucial for maintaining project sustainability. Building energy analysis from life cycle perspective has been increasingly favoured by scholars. However, the links and contents of many literatures have not been summarized and lacking systematic literature research. This review-based research used a holistic analysis approach as the framework. Bibliometrics method in the first stage was used to select 255 papers published during 2009–2019 related to life cycle energy of buildings (LCE-B). Scientometric analysis in the second stage was adopted for identifying the journal sources, scholars, regions and articles that have been fruitful and influential in LCE-B research, and keywords analysis was proposed to preliminarily explore the research topics in the domain (e.g. analysis of optimisation). Results showed that BIM and multi-objective optimisation have become research hotspots recently. An in-depth qualitative discussion in the last stage was conducted to achieve three main objectives: (1) summarise mainstream research topics (e.g. calculation and parameter determination of embodied energy); (2) discuss existing research gaps (e.g. the spatial heterogeneity of embodied energy); and (3) identify future research directions. This study provides a comprehensive knowledge framework combined with philosophical theories that links current research fields with future research trends, providing researchers with multi-disciplinary guidance to gain insight into the latest research on LCE-B.

Abstract Effectively controlling and reducing the energy consumption of buildings is the global focus. A considerable variety of research on building energy saving (BES) had been raised in the past. However, most of the previous reviews focus on a single topic within the area, and systematic review and objective analysis are lacking. This study comprehensively reviews 2569 papers on BES published between 1974 and 2020 through bibliometrics, network mapping analysis and in-depth content analysis to fill this research gap. This paper discusses the development evolution and research trends in the field based on the analysis results, and the following three major research themes are identified and discussed: (1) influence factors of building energy consumption (BEC), (2) implementation of BES and (3) barriers and drivers of BES. Lastly, the current study indicates the possible potential research direction in the future; for example, intelligent integration of energy management and control system, quantitative and qualitative analyses of the interaction of BESM and comprehensive summary and quantitative analysis of the driving and hindering factors of BES. The contribution of this study is that it can help scholars and practitioners to have a comprehensive cognition of the research status and trends in the field of BES.

Abstract Building operations account for the largest proportion of energy use throughout the building life cycle. The energy saving potential is considerable taking into account the existence of a wide variety of building operation deficiencies. The advancement in information technologies has made modern buildings to be not only energy-intensive, but also information-intensive. Massive amounts of building operational data, which are in essence the reflection of actual building operating conditions, are available for knowledge discovery. It is very promising to extract potentially useful insights from big building operational data, based on which actionable measures for energy efficiency enhancement are devised. Data mining is an advanced technology for analyzing big data. It consists of two main types of data analytics, i.e., supervised and unsupervised analytics. Despite of the power of supervised analytics in predictive modeling, unsupervised analytics are more practical and promising in discovering novel knowledge given limited prior knowledge. This paper provides a comprehensive review on the current utilization of unsupervised data analytics in mining massive building operational data. The commonly used unsupervised analytics are summarized according to their knowledge representations and applications. The challenges and opportunities are elaborated as guidance for future research in this multi-disciplinary field.