Personal Blog

Abstract: The urban population increases continuously since the industrial revolution, and the residential buildings have the primary responsibility for the total energy demand. There is a need for the analysis of the residential building stock for energy efficiency and sustainable planning. However, energy modeling and simulation in urban scale is expensive in computational complexity and time, due to various building geometries and occupancy types. This research proposes a method to increase the efficiency of the simulation process by reorganizing the building geometries with functional clustering and radiation analysis scaling. In order to accelerate the urban building energy modeling (UBEM) process, the building geometries are modified based on energy simulation standards, then, clustering is determined based on radiation analysis and outside boundary conditions. The candidates are selected according to the selection percentage that has been identified before the process to simul

Abstract: The changing weather conditions due to global climate change is expected to have a direct impact on buildings' energy demand and occupant comfort. These conditions are estimated to become more challenging for educational facilities due to their high occupant density and the students' sensitivity to heat. This study aims to present an approach for a comparative analysis for multi-objective optimization results that are projected under different climate change conditions. Two separate optimization processes were performed using NSGA-II for an existing educational building, with the goal of minimizing occupant discomfort and energy use. The differences between the resulting Pareto-sets were analyzed based on the hypervolume difference and statistical evaluations, including the T-test and the distribution of properties. The results of the two optimization processes showed that future weather conditions should be considered on the retrofit process as two Pareto-set have

Abstract: In non-residential buildings, space lighting accounts for 17 % of the total energy consumption. Effective use of daylighting has great potential to reduce lighting energy use in buildings. The amount of daylighting through the building windows is influenced by shading devices (i.e. curtains) that limit the visible light being introduced to the space. Therefore, there is a strong relationship between artificial lighting and shading. In this work, artificial lighting state prediction and curtain openness ratio prediction from the visual data is studied. For lighting state prediction, local and global approaches have been proposed and the performances are improved with the addition of background modeling and light sensor information. For the curtain openness prediction, a method with background modeling, binarization and morphology have been proposed. The performance of the proposed methods is evaluated with video datasets captured during one week in Decem-ber 2018 and one wee

Abstract: Improving the energy efficiency of existing buildings requires energy models that accurately represent the building and quantify various performance measures. Manual energy modeling has been proven to be inefficient, labor-intensive, and error-prone. Therefore, the automation of energy modeling is critical. Existing approaches for 3D geometry extraction using 3D laser scanning are promising, but their high cost and high level of operational expertise prevent their widespread use. Computer vision methods, particularly 3D reconstruction can effectively support the creation of 3D building models. An additional component of energy models is the building envelope's thermal characteristics. IR thermography can be used to determine the thermal transmittance of the external walls with data collection in both visible and thermal bands. This paper presents a method for the semi-automated energy modeling of existing buildings. A conventional structure-from-motion (SfM) pipeline is

Abstract: The information on occupant presence plays a critical role in building energy modeling for spaces with a high number of occupants. A thorough understanding of occupant behavior is key to precise Building Energy Modeling (BEM) and to increase the precision of the simulation results. Capturing occupant-related information is difficult due to its stochastic and temporally uncertain nature. In this paper, we propose a robust video content analytical approach for the fast and accurate analysis of temporal and spatial video content. This approach counts the number of occupants in a classroom in an existing building by processing the recordings of video cameras. Two novel counting methods were implemented. The first, namely the Average Counting Method, uses cameras installed in the room directed in different angles, This method relies on detecting and counting occupant heads using a deep convolutional network, namely YOLOv2, that we trained on an existing head dataset. The second

Abstract: Architectural decisions and designs are built with investment and energy costs in mind. Evaluating all possibilities and reaching optimum results seems impossible within a limited time frame, but nowadays it is possible to reach convincing results with computational computer-aided design methods. This research aims at defining the optimum window-to-wall ratio and achieving the optimum wall thickness, at the same time identifying the ideal glass and insulation material from defined glass material and clusters of insulation material. So, the goal is to increase the percentage of between UDI 100lux-2000lux annually, while trying to reduce the total energy demand and investment costs as a function of the Net Present Value by mathematical calculation. The heating and cooling demands on the buildings correspond to 60% of the total energy expenditures. At this time when climate changes are starting to feel violently, they will not be able to be ignored and they are confronted as a

Abstract: Renovation        works        introduce        numerous        complexities that can only be addressed by those who excel in this specific  design  task.  Such  issues  as  energy  consumption,  which  requires  examination  of  excessive  alternatives,  is  not  of  primary  concern  through  the  design  process  due  further  time  limitations.  However,   computational   intelligence   methods   prove   to   be   valuable  decision  support  tools.  To  this  end,  the  current  study  aims  to  determine  optimum  wall  insulation  material  parameters  while     minimizing     optimization targets,     namely     energy     consumption  and  investment  costs.  To  accomplish,  first,  energy  model  of  an  actual  case,  located  in  the  province  of  Selçuk,  was  developed   using   OpenStudio   cross   platform.   Following,   54   simulations  were  run  to  generate  the  data  base  for  the  given  parameters   of   selected   insulation   alternatives.   S