Now showing 1 - 10 of 14
  • Publication
    A Framework To Assess The Interoperability Of Commercial Buildings At A District Scale
    (International Building Simulation Association England, 2018-09-12) ; ; ;
    Expensive control technology coupled with absence of a proper framework result in buildings that operate independently for their entire operating life. This paper introduces a framework to assess the potential of buildings to function together using heat load demand patterns and buildings thermal mass. Buildings are characterized as possessing variable and stable heat demand patterns and internal conditions are modified to achieve a peak heat demand reduction. Results indicate 8% reduction in overall peak heat demand when two buildings are operated together. The analysis clearly establishes the significance of an integrated energy system that leads to a reduction in peak loads.
  • Publication
    Comparative Analysis of Machine Learning Algorithms for Building Archetypes Development in Urban Building Energy Modeling
    The most common approach for urban building energy modeling (UBEM) involves segmenting a building stock into archetypes. Development Building archetypes for urban scale is a complex task and requires a lot of extensive data. The archetype development methodology proposed in this paper uses unsupervised machine learning approaches to identify similar clusters of buildings based on building specific features. The archetype development process considers four crucial processes of machine learning: data preprocessing, feature selection, clustering algorithm adaptation and results validation. The four different clustering algorithms investigated in this study are KMean, Hierarchical, Density-based, K-Medoids. All the algorithms are applied on Irish Energy Performance Certificate (EPC) that consist of 203 features. The obtained results are then used to compare and analyze the chosen algorithms with respect to performance, quality and cluster instances. The K-mean algorithm preforms the best in terms of cluster formation.
  • Publication
    Development of a Model View Definition (MVD) for thermal comfort analysis in commercial buildings using BIM and EnergyPlus
    (Construction IT Allance of Ireland, 2017-11-24) ; ; ; ;
    Buildings are major consumers of global energy resources. Approximately 80% of the energy used in commercial office spaces, is typically used for maintaining optimal comfort levels through delivery of heating, cooling, ventilating, and lighting. Building Information Modelling (BIM) has seen a significant uptake by designers in pursuit of sustainable building designs. Furthermore, general BIM systems already contain much of the information that can be further reused for additional project tasks such as thermal comfort analysis. Integration and improvement of information flows between BIM and Building Energy Performance Simulation (BEPS) tools has the capacity to help designers assess building performance under various design conditions. In doing so, assessments of building performance and thermal comfort requires additional representative data about indoor environmental conditions and energy consumption. The process of connecting BIM to energy simulation tools, for the explicit purpose of thermal comfort analysis, requires a well-defined Model View Definition (MVD). MVDs define a subset of the Industry Foundation Classes (IFC) schema, which is needed to support a particular business process. This paper develops a MVD for thermal comfort that represents the data needed by building designers or operators to deliver a satisfactory level of thermal comfort in a typical small, single occupant office. The use case consists of a single thermal zone with a HVAC system. The detailed specification for these requirements is based on the IFC data representation. The IfcDoc application tool is used to improve the consistency and define computer-interpretable definition of the MVD. The outputs of this work will allow a standardised exchange of the necessary requirements from BIM to BEPS tools (e.g. EnergyPlus) for thermal comfort analysis.
  • Publication
    A generalization approach for reduced order modelling of commercial buildings
    Grey-box techniques can counter the computational inefficiency and resource-intensive nature of the conventional complex white-box models. However, these approaches might tend to be too specific in their application and scalability is limited by network order. To overcome these challenges, this study proposes a generalized approach for selection of reduced-order RC network models for commercial buildings using the peak power consumption characterization. The devised methodology is used to design the RC networks of buildings connected to district heating network at University College Dublin. The close proximity between measured and simulated demand indicate the influence of power demand on RC network selection.
      430Scopus© Citations 7
  • Publication
    A data-driven approach for multi-scale GIS-based building energy modeling for analysis, planning and support decision making
    Urban planners, local authorities, and energy policymakers often develop strategic sustainable energy plans for the urban building stock in order to minimize overall energy consumption and emissions. Planning at such scales could be informed by building stock modeling using existing building data and Geographic Information System-based mapping. However, implementing these processes involves several issues, namely, data availability, data inconsistency, data scalability, data integration, geocoding, and data privacy. This research addresses the aforementioned information challenges by proposing a generalized integrated methodology that implements bottom-up, data-driven, and spatial modeling approaches for multi-scale Geographic Information System mapping of building energy modeling. This study uses the Irish building stock to map building energy performance at multiple scales. The generalized data-driven methodology uses approximately 650,000 Irish Energy Performance Certificates buildings data to predict more than 2 million buildings’ energy performance. In this case, the approach delivers a prediction accuracy of 88% using deep learning algorithms. These prediction results are then used for spatial modeling at multiple scales from the individual building level to a national level. Furthermore, these maps are coupled with available spatial resources (social, economic, or environmental data) for energy planning, analysis, and support decision-making. The modeling results identify clusters of buildings that have a significant potential for energy savings within any specific region. Geographic Information System-based modeling aids stakeholders in identifying priority areas for implementing energy efficiency measures. Furthermore, the stakeholders could target local communities for retrofit campaigns, which would enhance the implementation of sustainable energy policy decisions.
    Scopus© Citations 78  417
  • Publication
    A generalization approach for reduced order modelling of commercial buildings
    (Informa UK Limited, 2019-07-26) ; ;
    Energy-efficient retrofits have become crucial in building sector as approximately 80% of buildings in developed countries are over 10 years old. Building simulation tools are now being used to provide estimates of energy consumption and implement various models which differ on the basis of enclosed details. Not all of these models are effective in terms of computation and the associated computational costs. This work devises a novel and generalized reduced-order grey-box modelling approach to predict the thermal behaviour of commercial buildings. The generalization approach reduces the order/complexity of model and lays out a general structure to obtain reduced-order models based on easily identifiable building metrics. We also implemented a forward-selection procedure to compare results obtained using a metrics-based approach. The network order obtained using metrics-based approach matches with the network order predicted by the forward selection procedure. The generalized structure would reduce the complexities involved in the dynamic simulation of urban building stock.
    Scopus© Citations 8  465
  • Publication
    A data-driven approach for multi-scale building archetypes development
    Globally the building sector accounts for a significant portion of the overall energy demand and greenhouse gas emissions of any country. The most common approach for the collection of modeling and benchmarking data that can be used for predictions of energy performance at a national or urban scale is through classification of the building stock into representative archetypes. Developing such building archetypes is a complex task due to the difficulties associated with gathering detailed geometric and non-geometric data at an urban scale. Although existing databases and projects provide a valuable overview of a building stock, the information about buildings’ physical descriptions are not regularly updated. Moreover, these databases cover only the national top-level archetypes and lack crucial information related to city or district scale building stocks. The use of national scale archetypes requires many assumptions that may not hold true for energy modeling at urban or district scale. This paper proposes a multi-scale (national, city, county and district) archetype development methodology using different data-driven approaches. The methodology consists of following five steps: 1) data collection, 2) segmentation, 3) characterization, 4) quantification, and 5) modeling results. We developed a test case based on the available building stock data of Ireland. The test case used previously developed archetype geometries coupled with the parameters determined by the characterization process to calculate annual energy use (kWh) of buildings at a multiple-scales. The resulting archetypes at national, city, county and district scale are analyzed and compared against one another. The results indicate that significant differences occur in terms of energy modeling results when national scale archetypes are used to simulate the energy performance of buildings at the local scale. These multi-scale building archetypes will aid local authorities and city planners when analyzing energy efficiency and consequently, help to improve sustainable energy policy decisions.
      591Scopus© Citations 48
  • Publication
    Extending IFC to support thermal comfort prediction during design
    (European Council on Computing in Construction, 2019-07-12) ; ; ; ; ;
    During the early design stage, designers often rely on general rules of thumb to make critical decisions about the geometry, construction systems and materials without fully evaluating their effects on indoor thermal environment requirements and constraints. Currently, reviewing a design’s sustainability requires designers to spend a significant amount of time manually extracting Thermal Comfort (TC) data from BIMs because of the tedious nature of this task. This paper is motivated by the absence of a standard method and a schema for extracting the necessary data for an automated TC assessment of building designs. The aim is to generate a reusable and retrievable set of Exchange Requirement’s for BIM-based BTCS to facilitate efficient data extraction and exchanges from design models using the IFC file format. Furthermore, we develop an MVD mechanism that provides a structured framework for the definition and exchange of the target data as a step towards standardisation and production of BTCS related information, the results from which contribute to a proposed MVD. The application of the MVD in building design has the potential to improve the early-stage TC assessment of design alternatives. Further, it could reduce the time required to conduct the assessment, increase the reproducibility of results, and formalises the method used.
  • Publication
    Application Of Intelligent Algorithms For Residential Building Energy Performance Rating Prediction
    Energy Performance Certificates (EPC) provide an indication of buildings’ energy use. The creation of an EPC for individual building requires information surveys. Hence, these ratings are typically non-existent for entire building stock. This paper addresses these information gaps using machine-learning models. Developed models were evaluated with Irish EPC data that included approximately 650,000 residential buildings with 199 inputs variables. Results indicate that the deep learning algorithm produces results with highest accuracy level of 88% when only 82 input variables are available. This identified approach will allow stakeholders such as authorities, policy makers and urban-planners to determine the EPC rating for the rest of the building stock using limited data.
  • Publication
    A data-driven approach to optimize urban scale energy retrofit decisions for residential buildings
    Urban planners face significant challenges when identifying building energy efficiency opportunities and developing strategies to achieve efficient and sustainable urban environments. A possible scalable solution to tackle this problem is through the analysis of building stock databases. Such databases can support and assist with building energy benchmarking and potential retrofit performance analysis. However, developing a building stock database is a time-intensive modeling procedure that requires extensive data (both geometric and non-geometric). Furthermore, the available data for developing a building database is sparse, inconsistent, diverse and heterogeneous in nature. The main aim of this study is to develop a generic methodology to optimize urban scale energy retrofit decisions for residential buildings using data-driven approaches. Furthermore, data-driven approaches identify the key features influencing building energy performance. The proposed methodology formulates retrofit solutions and identifies optimal features for the residential building stock of Dublin. Results signify the importance of data-driven retrofit modeling as the feature selection process reduces the number of features in Dublin's building stock database from 203 to 56 with a building rating prediction accuracy of 86%. Amongst the 56 features, 16 are identified to be recommended as retrofit measures (such as fabric renovation values and heating system upgrade features) associated with each energy-efficiency rating. Urban planners and energy policymakers could use this methodology to optimize large-scale retrofit implementation, particularly at an urban scale with limited resources. Furthermore, stakeholders at the local authority level can estimate the required retrofit investment costs, emission reductions and energy savings using the target retrofit features of energy-efficiency ratings.
    Scopus© Citations 67  396