Accurate building energy prediction plays an important role in improving the energy efficiency of buildings. This paper proposes a homogeneous ensemble approach, i.e., use of Random Forest (RF), for ...hourly building energy prediction. The approach was adopted to predict the hourly electricity usage of two educational buildings in North Central Florida. The RF models trained with different parameter settings were compared to investigate the impact of parameter setting on the prediction performance of the model. The results indicated that RF was not very sensitive to the number of variables (mtry) and using empirical mtry is preferable because it saves time and is more accurate. RF was compared with regression tree (RT) and Support Vector Regression (SVR) to validate the superiority of RF in building energy prediction. The prediction performances of RF measured by performance index (PI) were 14–25% and 5–5.5% better than RT and SVR, respectively, indicating that RF was the best prediction model in the comparison.
Moreover, an analysis based on the variable importance of RF was performed to identify the most influential features during different semesters. The results showed that the most influential features vary depending on the semester, indicating the existence of different operational conditions for the tested buildings. A further comparison between RF trained with yearly and monthly data indicated that the energy usage prediction for educational buildings could be improved by taking into consideration their energy behavior changes during different semesters.
•An ensemble bagging tree model (EBT) was used to predict institutional building electricity demand.•Three prediction modules representing different semesters of the test building were developed.•The ...proposed ensemble bagging tree was proven to be effective for short-term building energy prediction.•The proposed variable selection method reduces the computation time of EBT without sacrificing its prediction accuracy.
Broadly speaking, building energy use prediction can be classified into two categories based on modeling approaches namely engineering and Artificial Intelligence (AI). While engineering approach requires solving physical equations representing the thermal performance of systems and components that constitute the buildings, the AI-based approach uses historical data to predict future performance. Although engineering approach estimates energy use with greater accuracy, it falls short in the overall complexity of model building and simulation in which detailed data that represent the building geometry, systems, configurations, and occupant schedule is needed. Whereas, the AI-based approach offers a rapid prediction of building energy use and, if appropriately trained and tested, may be used for quick and efficient decision-making of energy use reduction. Nevertheless, for robust integration with and to improve automated building systems management and intelligence, the need for consistent, stable, and higher prediction accuracy cannot be understated. To alleviate the instability issue, and to improve prediction accuracy, we have exploited and tested an ensemble learning technique, ‘Ensemble Bagging Trees’ (EBT), using data obtained from meteorological systems and building-level occupancy and meters.Results showed that the proposed EBT model predicted hourly electricity demand of the test building with improved accuracy of Mean Absolute Prediction Error that ranged from 2.97% to 4.63%. Additionally, results showed that proposed variable selection method could reduce the computation time of EBT by 38–41% without sacrificing the prediction accuracy. The proposed ensemble learning model that exemplifies improved prediction accuracy over other AI techniques can be used for real-time applications such as system fault detection and diagnosis.
In developed countries, buildings are involved in almost 50% of total energy use and 30% of global green-house gas emissions. Buildings' operational energy is highly dependent on various building ...physical, operational, and functional characteristics, as well as meteorological and temporal properties. Besides physics-based building energy modeling, machine learning techniques can provide faster and higher accuracy estimates, given buildings' historic energy consumption data. Looking beyond individual building levels, forecasting buildings’ energy performance helps city and community managers have a better understanding of their future energy needs, and plan for satisfying them more efficiently. Focusing on an urban-scale, this study systematically reviews 70 journal articles, published in the field of building energy performance forecasting between 2015 and 2018. The recent literature have been categorized according to five criteria: 1. Learning Method, 2. Building Type, 3. Energy Type, 4. Input Data, and 5. Time-scale. The scarcity of building energy performance forecasting studies in urban-scale versus individual level is considerable. There is no study incorporating building functionality in terms of space functionality share percentages, nor assessing the effects of climate change on urban buildings energy performance using machine learning approaches and future weather scenarios. There is no optimal criteria combination for achieving the most accurate machine learning-based forecast, as there is no universal measure able to provide such global comparison. Accuracy levels are highly correlated with the characteristics of forecasting problems. The goal is to provide a comprehensive status of machine learning applications in urban building energy performance forecasting, during 2015–2018.
•Urban-level scarcity over individual level building energy performance forecasting.•No study incorporates buildings' space functionality share percentages.•No study assesses the effects of climate change using future weather scenarios.•No optimal criteria combination to provide the most accurate forecast.
The 21st century is witnessing a fast-paced digital revolution. A significant trend is that cyber and physical environments are being unprecedentedly entangled with the emergence of Internet of ...Things (IoT). IoT has been widely immersed into various domains in the industry. Among those areas where IoT would make significant impacts are building construction, operation, and management by facilitating high-class services, providing efficient functionalities, and moving towards sustainable development goals. So far, IoT itself has entered an ambiguous phase for industrial utilization, and there are limited number of studies focusing on the application of IoT in the building industry. Given the promising future impact of IoT technologies on buildings, and the increasing interests in interdisciplinary research among academics, this paper investigates the state-of-the-art projects and adoptions of IoT for the development of smart buildings within both academia and industry contexts. The wide-ranging IoT concepts are provided, covering the necessary breadth as well as relevant topic depth that directly relates to smart buildings. Current enabling technologies of IoT, especially those applied to buildings and related areas are summarized, which encompasses three different layers based on the conventional IoT architecture. Afterwards, several recent applications of IoT technologies on buildings towards the critical goals of smart buildings are selected and presented. Finally, the priorities and challenges of successful and seamless IoT integration for smart buildings are discussed. Besides, this paper discusses the future research questions to advance the implementation of IoT technologies in both building construction and operation phases. The paper argues that a mature adoption of IoT technologies in the building industry is not yet realized and, therefore, calls for more attention from researchers in the relevant fields from the application perspective.
•The common technologies of Internet of Things (IoT) used in the building industry on a layering basis are summarized.•The potentials of IoT technology application towards the development of smart buildings are recognized and highlighted.•An outline for developing IoT architecture to implement critical functionalities of smart buildings is provided.•Current trends and priorities, and future research areas of IoT application in the building industry are presented.
Energy consumption and indoor environment of buildings are proved to be largely influenced by the presence and behaviors of occupants. The uncertainty caused by occupant behaviors accounts for a ...significant discrepancy between the predicted and actual energy usage. In a real world, building system operations and control will be directly affected by occupant behavior, which may lead to over thirty percent waste against building's designed performance. Therefore, the capability to seamlessly integrate occupant behavior in energy simulation tools and building management systems in the future is clearly important to optimize building energy use while maintaining the same level of services. However, research has not reached the phase that occupant behaviors could be effectively modeled. Thus, the traditional schedule based approach is not adequate to satisfy the needs of building efficiency. In this paper, a thorough survey of occupant behavior modeling and simulation state-of-the-art technologies and methodologies for building energy efficiency is conducted. The paper first identifies and discusses the significance and application scale of building occupant behavior model. Based on the information collected, some recent data acquisition technologies for behavior-related research and occupant behavior modeling approaches are summarized. The advantages and limitations of these modeling methods are compared and analyzed, as well as appropriate recommendations are made for the future research. The paper finally outlines the findings and potential development areas in the field of occupant behavior modeling for energy efficient buildings.
ABSTRACT
This study extends prior research on supply chain planning and integration by examining the underlying capabilities by which firms exploit the information they gain from integration ...activities. We use organizational information processing theory (OIPT) to develop hypotheses that identify the comprehensiveness of an organization's supply chain planning capabilities as an important mediator in the relationship between its supply chain integration activities and its operational performance. Further, our interpretation of OIPT suggests that an organization's usage of technology‐enabled supply chain management systems (SCMS) moderates these effects. Using survey data from 445 global firms, we estimate the corresponding moderated‐mediation structural model. The results indicate that usage of SCMS enables organizations to better utilize the information they gain from external integration efforts (relationships with customers and suppliers), thus improving the comprehensiveness of their supply chain planning capabilities. In contrast, the use of SCMS appears to be a partial substitute for internal integration as a driver of planning comprehensiveness. Most importantly, the results suggest that planning comprehensiveness is a significant generative means by which integration and technology investments produce superior operational performance. These findings provide a richer and more theoretically grounded explanation of relationships between supply chain integration, supply chain planning, and operational performance.
Building energy use prediction plays an important role in building energy management and conservation as it can help us to evaluate building energy efficiency, conduct building commissioning, and ...detect and diagnose building system faults. Building energy prediction can be broadly classified into engineering, Artificial Intelligence (AI) based, and hybrid approaches. While engineering and hybrid approaches use thermodynamic equations to estimate energy use, the AI-based approach uses historical data to predict future energy use under constraints. Owing to the ease of use and adaptability to seek optimal solutions in a rapid manner, the AI-based approach has gained popularity in recent years. For this reason and to discuss recent developments in the AI-based approaches for building energy use prediction, this paper conducts an in-depth review of single AI-based methods such as multiple linear regression, artificial neural networks, and support vector regression, and ensemble prediction method that, by combining multiple single AI-based prediction models improves the prediction accuracy manifold. This paper elaborates the principles, applications, advantages and limitations of these AI-based prediction methods and concludes with a discussion on the future directions of the research on AI-based methods for building energy use prediction.
<p><b> Provides the foundations and principles needed for addressing the various challenges of developing smart cities </b> <p> Smart cities are emerging as a priority for ...research and development across the world. They open up significant opportunities in several areas, such as economic growth, health, wellness, energy efficiency, and transportation, to promote the sustainable development of cities. This book provides the basics of smart cities, and it examines the possible future trends of this technology. <i>Smart Cities: Foundations, Principles, and Applications</i> provides a systems science perspective in presenting the foundations and principles that span multiple disciplines for the development of smart cities. <p> Divided into three parts&mdash;foundations, principles, and applications&mdash;<i>Smart Cities</i> addresses the various challenges and opportunities of creating smart cities and all that they have to offer. It also covers smart city theory modeling and simulation, and examines case studies of existing smart cities from all around the world. In addition, the book: <ul> <li>Addresses how to develop a smart city and how to present the state of the art and practice of them all over the world</li> <li>Focuses on the foundations and principles needed for advancing the science, engineering, and technology of smart cities&mdash;including system design, system verification, real-time control and adaptation, Internet of Things, and test beds</li> <li>Covers applications of smart cities as they relate to smart transportation/connected vehicle (CV) and Intelligent Transportation Systems (ITS) for improved mobility, safety, and environmental protection</li> </ul> <br> <p><i> Smart Cities: Foundations, Principles, and Applications</i> is a welcome reference for the many researchers and professionals working on the development of smart cities and smart city-related industries.
The threats posed by climate change to Earth's ecosystems, human health, and the global economy are self-evident, and the building sector has contributed significantly to the creation of this ...problem. For two decades, the construction industry has attempted to mitigate its environmental impact by adopting green building strategies. However, due to a lack of a secure and accurate measurement, reporting, and verification (MRV) system, lowering the industry's carbon footprint has not been embraced by building owners. The building industry has not been able to participate in the carbon credit markets as well. Several factors are contributing to this failure. The primary issue is the complicated and insecure accounting system for accurately tracking energy consumption and carbon emissions. Although there are several building energy performance (BEP) audit schemes, these programs do not provide a suitable structure for a secure and accurate carbon emission MRV. Some climate action groups have navigated an overview of Blockchain for climate actions, especially in registries and tracking solutions, digital MRV, decentralized environment of clean energies, and climate finance. Moreover, there are several attempts to adopt blockchain MRV systems in the climate action projects, and blockchain carbon credit markets were already in place since Blockchain technology can offer a transparent, reliable, and affordable MRV system. This research walked through the literature of the BEP audit programs, the carbon credit market for the building sector, the possibility of adopting Blockchain technology to a digital BEP MRV. The study found that the digital MRV system, which climate action projects require, can be applied to the building sector with the adoption of Blockchain technology. Next, because a few blockchain carbon credit markets are already running, a blockchain digital MRV system needs to be developed to help the building sector participate in the carbon credit markets.
•A novel agent-based model (ABM) was developed to explore occupant behaviors in the context of built environment.•Relevant data was collected using customized sensor nodes and paper-based survey in a ...test bed building.•A validation study was conducted to test the occupant behavior model with the methods of visualization and calculation of quantification metrics for performance evaluation.•The proposed research framework has the potential to improve both building energy efficiency and occupant comfort during the life cycle of a building.
Occupant behaviors are one of the dominant factors that influence building energy use. Traditional building energy modeling programs use typical occupant schedules that often do not reflect actual situations. Robust occupant behavior modeling that seamlessly integrates with building energy models will not only improve simulation performance, but also provide a deeper understanding of occupant behaviors in buildings. This paper presents a development and validation approach to a novel occupant behavior model in commercial buildings. A robust agent-based modeling (ABM) tool, namely Performance Moderator Functions server (PMFserv), is used as the basis of the occupant behavior model. The ABM considers various occupant perceptions and interactions with window, door, and window-blinds based on the environmental conditions. An elaborate agent-based model that represents an office space in an existing building is developed. This is followed by a validation study of the ABM through the use of embedded sensors that capture the indoor ambient conditions and a survey to record actual occupant behaviors. By comparing the recorded behavior data with ABM output, this paper discusses the proposed ABM's prediction ability, limitations, and extensibility. Finally, the paper concludes with the potential of integrating the occupant behavior model with building energy simulation programs.