Now showing 1 - 10 of 55
  • Publication
    An Intelligent Knowledge-based Energy Retrofit Recommendation System for Residential Buildings at an Urban Scale
    Buildings play a significant role in driving the urban demand and supply of energy. Research conducted in the urban buildings sector indicates that there is a considerable potential to achieve significant reductions in energy consumption and greenhouse gas emissions. These reductions are possible through retrofitting existing buildings into more efficient and sustainable buildings. Building retrofitting poses a huge challenge for owners and city planners because they usually lack expertise and resources to identify and evaluate cost-effective energy retrofit strategies. This paper proposes a new methodology based on machine learning algorithms to develop an intelligent knowledge-based recommendation system which has the ability to recommend energy retrofit measures. The proposed methodology is based on the following four steps: archetypes development, knowledge-base development, recommendation system development and building retrofitting or performance analysis. A case study of Irish buildings dataset shows that the proposed system can provide effective energy retrofits recommendation and improve building energy performance.
      335
  • Publication
    GIS-Based Residential Building Energy Modeling at District Scale
    (International Building Performance Simulation Association, 2018-09-12) ; ; ;
    Urban planners often develop strategic sustainable energy planning processes that aim to minimize the overall energy consumption and CO2 emissions of buildings. Planning at such scales could be informed by the use of building energy modeling approaches. However, due to inconsistencies in available urban energy data and a lack of scalable building modeling approaches, a gap persists between building energy modeling and traditional planning practices. This paper develops a methodology based on bottom-up approach for GIS-based residential building energy modeling at a district scale. The methodology is applied to districts in Dublin and modeling results indicate where and what type of buildings have the greatest potential for energy savings throughout the city.
      690
  • Publication
    Requirements for a BIM-Based Life-Cycle Performance Evaluation Framework to Enable Optimum Building Operation
    (Eindhoven University of Technology, 2015-10-29) ; ;
    Buildings rarely perform as well in practice as anticipated during design, and often consume 20-30% more energy than necessary. One of the main causes of inefficient operation is the lack of data integration and system interoperability inherent in the AEC/FM industry. In many cases, the assumptions and specifications defined during design are not transferred throughout the life-cycle of the building, and actual operation deviates from design intent. Building Information Modelling enables designers to create digital models of buildings. Theoretically, these models should be exchangeable between disciplines and over different life-cycle stages, but in practice the lack of information exchange protocols in the building performance area inhibits such exchanges. In order to improve building operation throughout the building life-cycle, this paper proposes a BIM-based performance evaluation framework to compare design intent with actual operation. The framework uses the IFC schema to facilitate the information exchange process for better qualification and validation of data.
      488
  • 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.
      522
  • Publication
    Building Manager Requirement Specifications for Efficient Building Operation
    Building management plays a significant role in an organisation aiming to achieve an energy efficient status. In this context, there is growing pressure on building managers to provide not only high-quality building services, but to run and manage buildings as economically and efficiently as possible. As such, management activities require a comprehensive data management system to capture, retrieve and put to optimal use, information related to building performance. In this scenario, Building Information Modelling (BIM) can play the role of data repository and provide easy access to information pertaining to precise equipment locations, equipment affected by a system failure, maintenance history information, etc. Therefore, this paper uses building manager’s business processes and associated information identified throughout the paper to propose a BIM-based building management framework that enables accumulation and management of energy life-cycle data based on Industry Foundations Classes (IFC).
      162
  • Publication
    Data-Requirements Specification to Support BIM-Based HVAC-Definitions in Modelica
    Recent developments in Building Information Model (BIM) capable software are leading to increased interoperability among heterogeneous tools. The results are representing greater levels of data available for all stakeholders involved in the building industry. The increasing range of data within BIMs enables the reuse of data for downstream applications such as Building Energy Performance Simulation (BEPS). Current BEPS tools work well in many modeling scenarios, but fail to support innovative and flexible model configurations due to existing tool limitations. Modelica is an object-oriented, equation-based programming language used for detailed dynamic simulation purposes across different industries. The use of Modelica in the building industry is increasing and it is a promising and flexible tool to provide modeling solutions addressing the upcoming challenges in the building industry and beyond. This paper illustrates a method of using BIM based information as the primary data source for a flexible simulation application. It includes an implementation for a defined generic use case.
      626
  • Publication
    Requirements specification to support BIM-based Thermal Comfort analysis
    Traditionally and during a building's operation, thermal comfort levels are often evaluated using equipment that is expensive to purchase and maintain. Through advanced technologies, Building Information Model (BIM) and energy simulation tools, thermal comfort and its impacts can be evaluated at the conceptual and early design stages. The development of Building Energy Performance Simulation (BEPS) tools, through the implementation of BIM, will provide design teams with rich, comprehensive data to evaluate indoor thermal conditions in order to provide acceptable comfort levels. Current energy simulation models focus on entering data manually, increasing time and cost. BIM-based energy and thermal comfort analysis provides designers with the means to explore a variety of design alternatives, as well as avoiding the time-consuming process of re-entering all of the building's geometry and HVAC specifications to perform an analysis. However, integrating BEPS with BIM-based building design tools is still limited, with one of the key obstacles being the lack of standardised methods for information exchange between the two domains. To address the needs and bridge the gaps, this paper aims to improve the information exchange process by describing data and information needed to perform thermal comfort simulation using a standardised format in order to develop a Model View Definition (MVD) for thermal comfort. This approach represents the data needed by building designers or operators to provide an acceptable level of thermal comfort in a typical small, single occupant office. Through analysis of the performance of the proposed approach, this work provides a standardised exchange of data from BIM to BEPS tools, such as EnergyPlus, using the Industry Foundation Classes (IFC) standard.
      230
  • Publication
    Requirements for BIM-based thermal comfort analysis
    When designing and creating a working or living space, the provision of thermal comfort for a building’s occupants remains a key objective. However, energy consumption associated with the delivery of indoor environmental conditioning in the commercial building stock is not necessarily translated into improved thermal comfort conditions. When collaborative design utilises Building Information Models (BIMs), much of the data required for thermal comfort analysis is already defined by other project stakeholders. Furthermore, mechanical equipment such as HVAC and lighting fixtures, play a major role in functional performance, resultant thermal comfort and energy consumption. Monitoring building performance and thermal comfort requires additional representative data about indoor environmental conditions and energy consumption. This paper presents a holistic review of the data and information needed for the integration of BIM with thermal comfort modelling for commercial office spaces. Thermal comfort is dependent on multiple factors such as indoor environmental conditions, user behaviour, properties of building materials, etc. For inclusion in the design process this data must first be categorised in a standardised manner. The outputs of this work contribute to a Model View Definition (MVD) for thermal comfort using the IFC standard.
      326
  • Publication
    Model View Definition for Advanced Building Energy Performance Simulation
    Recent demand for higher energy efficiency within the building sector has led to the use of Building Energy Performance Simulation (BEPS) tools. These powerful predictive tools enable investigation of environmental and energy performance for different design and retrofit design alternatives. However, integrating BEPS with Building Information Modelling (BIM) based building design tools still experiences limitations due to a lack of standardised methods of information exchange between these domains. As a result, this paper presents a Model View Definition (MVD) for advanced BEPS. In doing so this work enables a standardised exchange of data from BIM to BEPS tools, such as Modelica, using the Industry Foundation Classes (IFC) standard. The entire process becomes available through the open source software framework emerged from the IEA EBC Annex 60.
      307
  • Publication
    BIM to Building Energy Performance Simulation: An Evaluation of Current Transfer Processes
    For over 25 years, data exchange between architectural BIM-based designs and Building Energy Performance Simulation (BEPS) have been proposed as a solution to reduce the amount of manual and error prone rework required to create typical BEPS models. The current state of the art lacks an effective, universal and robust system of data collation, processing, quality assessment and analysis while interfacing with existing tool-chains through a streamlined data transfer process.This paper investigates the reproducibility of current BIM to BEPS transfer processes through an experiment that compares these transfer processes, as used in industry, against each other. The experiment uses five residential archetype buildings and results from BEPS models in EnergyPlus indicate that there are many barriers, both technical and methodological, to achieving reproducible results between commonly available software tools. In some cases difficulties could not be overcome as the transformation process itself did not complete, leading to inconclusive results. In cases where successful transformations occurred, variations of up to 25.89% in annual energy consumption were discovered between processes. This hints to issues and limitations of the current processes and results.
      339