scholarly journals Machine learning for energy performance prediction at the design stage of buildings

2022 ◽  
Vol 66 ◽  
pp. 12-25
Author(s):  
Razak Olu-Ajayi ◽  
Hafiz Alaka ◽  
Ismail Sulaimon ◽  
Funlade Sunmola ◽  
Saheed Ajayi
Keyword(s):  
Machine Learning ◽  
Performance Prediction ◽  
Energy Performance ◽  
Design Stage

scholarly journals Machine Learning–enabled Scalable Performance Prediction of Scientific Codes

2021 ◽  
Vol 31 (2) ◽  
pp. 1-28
Author(s):  
Gopinath Chennupati ◽  
Nandakishore Santhi ◽  
Phill Romero ◽  
Stephan Eidenbenz
Keyword(s):  
Machine Learning ◽  
Performance Prediction ◽  
Prediction Models ◽  
Radiation Transport ◽  
Discrete Event ◽  
Basic Block ◽  
Distribution Models ◽  
Scientific Application ◽  
High Level ◽  
Access Patterns

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. We present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. PPT-AMMP uses machine learning and regression techniques to build the prediction models based on small instances of the input code, then integrates into a higher-order discrete-event simulation model of PPT running on Simian PDES engine. We validate PPT-AMMP on four standard computational physics benchmarks and present a use case of hardware parameter sensitivity analysis to identify bottleneck hardware resources on different code inputs. We further extend PPT-AMMP to predict the performance of a scientific application code, namely, the radiation transport mini-app SNAP. To this end, we analyze multi-variate regression models that accurately predict the reuse profiles and the basic block counts. We validate predicted SNAP runtimes against actual measured times.

scholarly journals Energy Rating of Buildings to Promote Energy-Conscious Design in Israel

Buildings ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 59
Author(s):  
Abraham Yezioro ◽  
Isaac Guedi Capeluto
Keyword(s):  
Design Process ◽  
Architectural Design ◽  
Residential Building ◽  
Green Building ◽  
Energy Performance ◽  
Basic Unit ◽  
Design Stage ◽  
Design Decision ◽  
Rating Systems ◽  
New Buildings

Improving the energy efficiency of existing and new buildings is an important step towards achieving more sustainable environments. There are various methods for grading buildings that are required according to regulations in different places for green building certification. However, in new buildings, these rating systems are usually implemented at late design stages due to their complexity and lack of integration in the architectural design process, thus limiting the available options for improving their performance. In this paper, the model ENERGYui used for design and rating buildings in Israel is presented. One of its main advantages is that it can be used at any design stage, including the early ones. It requires information that is available at each stage only, as the additional necessary information is supplemented by the model. In this way, architects can design buildings in a way where they are aware of each design decision and its impact on their energy performance, while testing different design directions. ENERGYui rates the energy performance of each basic unit, as well as the entire building. The use of the model is demonstrated in two different scenarios: an office building in which basic architectural features such as form and orientation are tested from the very beginning, and a residential building in which the intervention focuses on its envelope, highlighting the possibilities of improving their design during the whole design process.

scholarly journals Evaluation of Urban-Scale Building Energy-Use Models and Tools—Application for the City of Fribourg, Switzerland

2021 ◽  
Vol 13 (4) ◽  
pp. 1595
Author(s):  
Valeria Todeschi ◽  
Roberto Boghetti ◽  
Jérôme H. Kämpf ◽  
Guglielmina Mutani
Keyword(s):  
Machine Learning ◽  
Energy Use ◽  
Residential Buildings ◽  
Building Energy ◽  
Energy Performance ◽  
Space Heating ◽  
Engineering Model ◽  
Building Energy Use ◽  
The Impact ◽  
The City

Building energy-use models and tools can simulate and represent the distribution of energy consumption of buildings located in an urban area. The aim of these models is to simulate the energy performance of buildings at multiple temporal and spatial scales, taking into account both the building shape and the surrounding urban context. This paper investigates existing models by simulating the hourly space heating consumption of residential buildings in an urban environment. Existing bottom-up urban-energy models were applied to the city of Fribourg in order to evaluate the accuracy and flexibility of energy simulations. Two common energy-use models—a machine learning model and a GIS-based engineering model—were compared and evaluated against anonymized monitoring data. The study shows that the simulations were quite precise with an annual mean absolute percentage error of 12.8 and 19.3% for the machine learning and the GIS-based engineering model, respectively, on residential buildings built in different periods of construction. Moreover, a sensitivity analysis using the Morris method was carried out on the GIS-based engineering model in order to assess the impact of input variables on space heating consumption and to identify possible optimization opportunities of the existing model.

scholarly journals Impact of Window to Wall Ratio on Energy Loads in Hot Regions: A Study of Building Energy Performance

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1080
Author(s):  
Mamdooh Alwetaishi ◽  
Omrane Benjeddou
Keyword(s):  
Saudi Arabia ◽  
Building Materials ◽  
Building Design ◽  
Building Energy ◽  
Energy Performance ◽  
Design Stage ◽  
Design Solution ◽  
Building Energy Efficiency ◽  
Climatic Regions ◽  
Heating And Cooling

The concern regarding local responsive building design has gained more attention globally as of late. This is due to the issue of the rapid increase in energy consumption in buildings for the purpose of heating and cooling. This has become a crucial issue in educational buildings and especially in schools. The major issue in school buildings in Saudi Arabia is that they are a form of prototype school building design (PSBD). As a result, if there is any concern in the design stage and in relation to the selection of building materials, this will spread throughout the region. In addition to that, the design is repeated regardless of the climate variation within the kingdom of Saudi Arabia. This research will focus on the influence of the window to wall ratio on the energy load in various orientations and different climatic regions. The research will use the energy computer tool TAS Environmental Design Solution Limited (EDSL) to calculate the energy load as well as solar gain. During the visit to the sample schools, a globe thermometer will be used to monitor the globe temperature in the classrooms. This research introduces a framework to assist architects and engineers in selecting the proper window to wall ratio (WWR) in each direction within the same building based on adequate natural light with a minimum reliance on energy load. For ultimate WWR for energy performance and daylight, the WWR should range from 20% to 30%, depending on orientation, in order to provide the optimal daylight factor combined with building energy efficiency. This ratio can be slightly greater in higher altitude locations.

scholarly journals Managing energy performance in buildings from design to operation using modelling and calibration

2021 ◽  
pp. 014362442110083
Author(s):  
Nishesh Jain ◽  
Esfand Burman ◽  
Dejan Mumovic ◽  
Mike Davies
Keyword(s):  
Best Practice ◽  
Good Practice ◽  
Energy Performance ◽  
Operating Conditions ◽  
Design Stage ◽  
Performance Gap ◽  
Actual Performance ◽  
Simulation Tools ◽  
Calibration Protocol ◽  
Covering Design

To manage the concerns regarding the energy performance gap in buildings, a structured and longitudinal performance assessment of buildings, covering design through to operation, is necessary. Modelling can form an integral part of this process by ensuring that a good practice design stage modelling is followed by an ongoing evaluation of operational stage performance using a robust calibration protocol. In this paper, we demonstrate, via a case study of an office building, how a good practice design stage model can be fine-tuned for operational stage using a new framework that helps validate the causes for deviations of actual performance from design intents. This paper maps the modelling based process of tracking building performance from design to operation, identifying the various types of performance gaps. Further, during the operational stage, the framework provides a systematic way to separate the effect of (i) operating conditions that are driven by the building’s actual function and occupancy as compared with the design assumptions, and (ii) the effect of potential technical issues that cause underperformance. As the identification of issues is based on energy modelling, the process requires use of advanced and well-documented simulation tools. The paper concludes with providing an outline of the software platform requirements needed to generate robust design models and their calibration for operational performance assessments. Practical application The paper’s findings are a useful guide for building industry professionals to manage the performance gap with appropriate accuracy through a robust methodology in an easy to use workflow. The methodological framework to analyse building energy performance in-use links best practice design stage modelling guidance with a robust operational stage investigation. It helps designers, contractors, building managers and other stakeholders with an understanding of procedures to follow to undertake an effective measurement and verification exercise.

Sign in / Sign up

Export Citation Format

Share Document