Browsing by Author "Sariyildiz, Sevil"

Now showing 1 - 19 of 19

Citation - WoS: 11
Citation - Scopus: 12
A multi-objective self-adaptive differential evolution algorithm for conceptual high-rise building design
(Institute of Electrical and Electronics Engineers Inc., 2016) Berk Ekici; Ioannis Chatzikonstantinou; I. Sevil Sariyildiz; M. Fatih Tasgetiren; Quanke Pan; Ekici, Berk; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Tasgetiren, M. Fatih; Pan, Quan-Ke
This paper presents a multi-objective self-adaptive differential evolution algorithm to solve the form-finding problem of high-rise building design in the conceptual phase. The aim of the research is to reach suitable high-rise design alternatives for hard and soft objectives which are construction cost per square meter structural displacement and visual perception of the spaces from the inside out subject to several constraints that are related with both high-rise construction regulations and profitability of the spaces. We formulate the problem as a multi-objective realparameter constrained optimization problem for three objectives that are inherently conflicting. To tackle this problem we developed two different optimization algorithms namely a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and a Self-Adaptive Differential Evolution Algorithm (jDE) in order to obtain Pareto fronts with diversified non-dominated solutions. The extensive computational results show that the jDE algorithm yields much more desirable Pareto front than the NSGA-II algorithm. © 2017 Elsevier B.V. All rights reserved.
Citation - WoS: 30
Citation - Scopus: 42
Approximation of simulation-derived visual comfort indicators in office spaces: a comparative study in machine learning
(TAYLOR & FRANCIS LTD, 2016) Ioannis Chatzikonstantinou; Sevil Sariyildiz; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis
In performance-oriented architectural design the use of advanced computational simulation tools may provide valuable insight during design. However the use of such tools is often a bottleneck in the design process given that computational requirements are usually high. This is a fact that mostly affects the early conceptual stage of design where crucial decisions mainly occur and available time is limited. In order to deal with this decision-makers frequently resort to drawing conclusions from experience and as such valuable insight that advanced computational methods have to offer is lost. This paper explores an alternative approach which builds on machine-learning algorithms that inductively learn from simulation-derived data yielding models that approximate to a good degree and are orders of magnitude faster. We focus on visual comfort of office spaces. This is a type of space that specifically requires visual comfort more than others. Three machine-learning methods are compared with respect to applicability in approximating daylight autonomy and daylight glare probability. The comparison focuses on accuracy and time cost of training and estimation. Results demonstrate that machine-learning-based approaches achieve a favourable trade-off between accuracy and computational cost and provide a worthwhile alternative for performance evaluations during architectural conceptual design.
Citation - WoS: 6
Citation - Scopus: 7
Conceptual Airport Terminal Design using Evolutionary Computation
(IEEE, 2015) Ioannis Chatzikonstantinou; Sevil Sariyildiz; Michael S. Bittermann; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Bittermann, Michael S.
Passenger terminals are very complex buildings not only in their function form and structure but also in infrastructure security comfort energy which deal with huge investments both in terms of capital as well as in terms of resources and environmental impact. As such it is expected that they are designed to fulfill their purpose while minimizing their negative aspects to the environment. Identifying design solutions that satisfy these goals is a challenging task due to the complexity involved. The design task is characterized by excessive number of solutions conflicting goals and complex relations between design decision variables objectives and constraints. As such appropriate informed decisions that integrate as many design aspects as possible should be ensured as early as the conceptual stage of the design. In this study the problem of conceptual airport terminal design is addressed by means of computational decision support methodologies. The proposed method is based on the integration of the following components: i. a parametric modeling approach for enabling the instantaneous generation of a wide variety of designs ii. a multi-faceted evaluation scheme which integrates functional energy and architectural aspects iii. a Multi-Objective Genetic Algorithm namely the NSGA-II to identify well performing solutions. A computational model implementing the method is outlined and validation of the method is performed based on two different scenarios corresponding to commonly occurring airport configurations. The performance of two optimization runs with different population sizes as well as qualitative aspects of the resulting solutions is discussed.
Citation - WoS: 9
Citation - Scopus: 13
Designing Self-Sufficient Floating Neighborhoods Using Computational Decision Support
(IEEE, 2015) Ayca Kirimtat; Ioannis Chatzikonstantinou; Sevil Sariyildiz; Ayca Tartar; Sariyildiz, Sevil; Tartar, Ayca; Chatzikonstantinou, Ioannis; Kirimtat, Ayca
Floating settlements which introduce further design complexities over traditional developments have become an alternative for urban development due to climate change and shortage of land. This study aims to develop a floating settlement concept that presents an approach to the design of floating neighborhoods using parametric modelling techniques in combination with Intelligent Decision Support tools and optimization methods. Optimization results of two algorithms namely NSGA-II and DE are compared regarding to objectives. The objectives considered in this study are walkability within the neighborhoods scenic view and cost-effectiveness. Results suggest that DE performs better than NSGA-II in this problem. An application of the method is presented focusing on the design of floating neighborhoods in the project area namely Urla which is a seaside place along the coastline of Izmir Turkey.
Engineering Performance Simulations in Architectural Design Conception Atrium in Shenyang: a case study on thermal mass
(Education and research in Computer Aided Architectural Design in Europe, 2013) Michela Turrin; Ioannis Chatzikonstantinou; Martin J. Tenpierik; I. Sevil Sariyildiz; Turrin, Michela; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Tenpierik, Martin; R. Stouffs , S. Sariyildiz
The paper tackles the integration of engineering performance simulations in the conceptual phase of architectural design with specific focus on parametric design processes. A general framework is exemplified in which the use of performance simulations and the learning process of the designer are discussed in relation to the parameterization process. A specific case study is presented more in details regarding the design of an atrium for the reuse of an existing building in Shenyang-China. Performance simulations concerning the thermal comfort in the atrium are presented and discussed in relation to the general framework. © 2022 Elsevier B.V. All rights reserved.
Citation - WoS: 4
Citation - Scopus: 7
Evolutionary Computation for Architectural Design of Restaurant Layouts
(IEEE, 2015) Cemre Ugurlu; Ioannis Chatzikonstantinou; Sevil Sariyildiz; M. Fatih Tasgetiren; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Tasgetiren, M. Fatih; Ugurlu, Cemre
This paper presents the results obtained by NSGA-II and DE on a restaurant layout optimization problem trying to maximize total profit while minimizing investment. The problem entails the configuration of restaurant functions the decisions regarding the restaurant shell composition (fraction and position of windows dimensions) and how to shape and place the kitchen and service areas. The NSGA-II and DE algorithms are implemented in a Parametric Design Environment that is familiar in the architectural practice. We demonstrate that the DE algorithm achieves slightly better performance in terms of hypervolume calculation and achieve promising results when the Pareto front approximation is examined. To the best of our knowledge this is the first application of multi-objective approach for restaurant design.
Citation - WoS: 5
Citation - Scopus: 7
Identification of Sustainable Designs for Floating Settlements Using Computational Design Techniques
(IEEE, 2015) Cemre Ugurlu; Ioannis Chatzikonstantinou; Sevil Sariyildiz; Mehmet Fatih Tasgetiren; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Tasgetiren, M. Fatih; Ugurlu, Cemre
This paper focuses on the conceptual design and the development of a floating neighborhood by taking advantage of computational methods. An application to a concept design of a floating neighborhood in the region of Urla - a coastal town close to Izmir in Turkey has been studied. The scenario that has been addressed concerns the development of an efficient floating settlement between four islands that are local to the study region. The whole study revolves around two issues first one is about configuration of the functions (accommodation marine yacht club public area) in order to maximize accessibility wind protection and visibility subject to both technical and nontechnical constraints. Second issue is to find a suitable form generated by shortest walk algorithm that decides how to create roads between functions where their places are gathered from optimization solutions. For the configuration of the functions since wind protection and visibility objectives as well as accessibility and visibility are conflicting with each other we make use of multi-objective evolutionary algorithms. The NSGA-II and DE algorithms are implemented in a Parametric Design Environment that is familiar in the architectural practice. We demonstrate that the NSGA-II performs slightly better in terms of hyper volume calculation and achieves promising results when the Pareto front approximation is examined.
Citation - WoS: 9
Citation - Scopus: 16
Impacts of problem scale and sampling strategy on surrogate model accuracy: An application of surrogate-based optimization in building design
(Institute of Electrical and Electronics Engineers Inc., 2016) Ding Yang; Yimin Sun; Danilo Di Stefano; Michela Turrin; I. Sevil Sariyildiz; di Stefano, Danilo; Turrin, Michela; Sariyildiz, Sevil; Sun, Yimin; Yang, Ding
Surrogate-based Optimization is a useful approach when the objective function is computationally expensive to evaluate compared to Simulation-based Optimization. In the surrogate-based method analytically tractable 'surrogate models' (also known as 'Response Surface Models - RSMs' or 'metamodels') are constructed and validated for each optimization objective and constraint at relatively low computational cost. They are useful for replacing the time-consuming simulations during the optimization, quickly locating the area where the optimum is expected to be for further search, and gaining insight into the global behavior of the system. Nevertheless there are still concerns about the surrogate model accuracy and the number of simulations necessary to get a reasonably accurate surrogate model. This paper aims to unveil: 1) the possible impacts of problem scale and sampling strategy on the surrogate model accuracy, and 2) the potential of Surrogatebased Optimization in finding high quality solutions for building envelope design optimization problems. For this purpose a series of multi-objective optimization test cases that mainly consider daylight and energy performance were conducted within the same time frame. Then the results were compared in pair based on which discussions were made. Finally the corresponding conclusions were obtained after the comparative study. © 2017 Elsevier B.V. All rights reserved.
Citation - WoS: 1
Citation - Scopus: 1
Is architectural design a science?
(Taylor and Francis, 2018) I. Sevil Sariyildiz; Sariyildiz, Sevil
[No abstract available]
Citation - WoS: 8
Citation - Scopus: 14
Multi-Objective Optimization For Shading Devices in Buildings By Using Evolutionary Algorithms
(IEEE, 2016) Ayca Kirimtat; Basak Kundakci Koyunbaba; Ioannis Chatzikonstantinou; Sevil Sariyildiz; Ponnuthurai Nagaratnam Suganthan; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Suganthan, Ponnuthurai Nagaratnam; Koyunbaba, Basak Kundakci; Kirimtat, Ayca
The reduction of energy consumption is a major challenge around the world. Architectural aspects have a significant place to minimize energy consumption to the maximum level. The use of large glazed facades causes overheating problems in certain climatic regions. Shading elements must be considered at an early stage in the design process to overcome this problem. An application of the method is presented focusing on the horizontal louvers integrated to a building in Izmir Turkey. The contributions of the paper can be summarized as follows. We show that most architectural design problems are basically real-parameter multi-objective constrained optimization problems. So any type of evolutionary and swarm optimization methods can be used in this field. A multi-objective self-adaptive differential evolution algorithm (jDEMO) inspired from the DEMO algorithm from the literature with some modifications is developed and compared to the well-known fast and nondominated sorting genetic algorithm so called NSGA-II in order to solve this complex problem and identify alternative design solutions to decision makers. Through the experimental results we show that the proposed algorithm generated slightly better results when comparing to the NSGA-II algorithm.
Citation - WoS: 7
Citation - Scopus: 9
Multi-Objective Optimization Through Differential Evolution for Restaurant Design
(IEEE, 2016) Cemre Cubukcuoglu; Ioannis Chatzikonstantinou; Berk Ekici; Sevil Sariyildiz; M. Fatih Tasgetiren; Ekici, Berk; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Tasgetiren, M. Fatih; Cubukcuoglu, Cemre
This paper presents the results obtained by NSGA-II and jDEMO on a restaurant design optimization in the conceptual phase. A multi-objective problem is formulated by considering the minimization of investment and the maximization of customer count and maximization of visual perception subject to several constraints. The main problem requires the configuration of restaurant spaces with different seating groups decisions regarding the customer capacity fraction and position of the windows. The contributions of the paper can be summarized as follows. We show that most architectural design problems are basically real-parameter multi-objective constrained optimization problems. So any type of evolutionary and swarm optimization methods can be used in this field. A multi-objective self-adaptive differential evolution algorithm (jDEMO) inspired from the DEMO algorithm from the literature with some modifications is developed and compared to the well-known fast and non-dominated sorting genetic algorithm so called NSGA-II in order to solve this complex problem and identify alternative design solutions to decision makers. Through the experimental results we show that the proposed algorithm is competitive with the NSGA-II algorithm.
Citation - WoS: 33
Citation - Scopus: 42
OPTIMUS: Self-Adaptive Differential Evolution with Ensemble of Mutation Strategies for Grasshopper Algorithmic Modeling
(MDPI, 2019) Cemre Cubukcuoglu; Berk Ekici; Mehmet Fatih Tasgetiren; Sevil Sariyildiz; Ekici, Berk; Sariyildiz, Sevil; Tasgetiren, Mehmet Fatih; Cubukcuoglu, Cemre
Most of the architectural design problems are basically real-parameter optimization problems. So any type of evolutionary and swarm algorithms can be used in this field. However there is a little attention on using optimization methods within the computer aided design (CAD) programs. In this paper we present Optimus which is a new optimization tool for grasshopper algorithmic modeling in Rhinoceros CAD software. Optimus implements self-adaptive differential evolution algorithm with ensemble of mutation strategies (jEDE). We made an experiment using standard test problems in the literature and some of the test problems proposed in IEEE CEC 2005. We reported minimum maximum average standard deviations and number of function evaluations of five replications for each function. Experimental results on the benchmark suite showed that Optimus (jEDE) outperforms other optimization tools namely Galapagos (genetic algorithm) SilverEye (particle swarm optimization) and Opossum (RbfOpt) by finding better results for 19 out of 20 problems. For only one function Galapagos presented slightly better result than Optimus. Ultimately we presented an architectural design problem and compared the tools for testing Optimus in the design domain. We reported minimum maximum average and number of function evaluations of one replication for each tool. Galapagos and Silvereye presented infeasible results whereas Optimus and Opossum found feasible solutions. However Optimus discovered a much better fitness result than Opossum. As a conclusion we discuss advantages and limitations of Optimus in comparison to other tools. The target audience of this paper is frequent users of parametric design modelling e.g. architects engineers designers. The main contribution of this paper is summarized as follows. Optimus showed that near-optimal solutions of architectural design problems can be improved by testing different types of algorithms with respect to no-free lunch theorem. Moreover Optimus facilitates implementing different type of algorithms due to its modular system.
Citation - Scopus: 2
Performance-based parameterization strategies
(2013) Michela Turrin; Rudi Stouffs; I. Sevil Sariyildiz; Turrin, Michela; Sariyildiz, Sevil; Stouffs, Rudi
In this paper alternative approaches to structure the parametric geometry in relation to information on various performances are described and exemplified. They relate to different levels of knowledge that concern the performances considered in the process and which are available to the designer while the parametric model is being set. Atheoretic framework embeds the different approaches for which the use of parametric modelling is structured in three phases: strategy-definition, model-building, and solution-assessment. The phases and their interrelations are discussed. Finally four case studies are presented focusing on the relation between the knowledge available in strategy-definition and the exploration occurring in solution-assessment. © 2013 The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA) Hong Kong and Center for Advanced Studies in Architecture (CASA) Department of Architecture-NUS Singapore. © 2014 Elsevier B.V. All rights reserved.
Citation - WoS: 1
PERFORMANCE-BASED PARAMETERIZATION STRATEGIES A theoretic framework and case studies
(CAADRIA-ASSOC COMPUTER-AIDED ARCHITECTURAL DESIGN RESEARCH ASIA, 2013) Michela Turrin; Rudi Stouffs; Sevil Sariyildiz; Turrin, Michela; Sariyildiz, Sevil; Stouffs, Rudi; R Stouffs; P Janssen; S Roudavski; B Tuncer
In this paper alternative approaches to structure the parametric geometry in relation to information on various performances are described and exemplified. They relate to different levels of knowledge that concern the performances considered in the process and which are available to the designer while the parametric model is being set. Atheoretic framework embeds the different approaches for which the use of parametric modelling is structured in three phases: strategy-definition, model-building, and solution-assessment. The phases and their interrelations are discussed. Finally four case studies are presented focusing on the relation between the knowledge available in strategy-definition and the exploration occurring in solution-assessment.
Citation - WoS: 258
Citation - Scopus: 318
Review of simulation modeling for shading devices in buildings
(PERGAMON-ELSEVIER SCIENCE LTD, 2016) Ayca Kirimtat; Basak Kundakci Koyunbaba; Ioannis Chatzikonstantinou; Sevil Sariyildiz; Sariyildiz, Sevil; Chatzikonstantinou, Ioannis; Koyunbaba, Basak Kundakci; Kirimtat, Ayca
Many countries around the world are confronted with the challenge of decreasing energy consumption while the use of electrical appliances is continuously increasing in buildings. The requirement to minimize the energy consumption can be fulfilled by revaluating architectural aspects. One of these aspects is related to overheating problems caused by facades with large glazed portions. In such designs shading elements must carefully be integrated and considered at an early-design stage in the design process. Shading of buildings is crucial especially in climates with hot summer. It is significant to protect the window from solar radiation in summer while allowing maximum solar radiation in winter. For this reason precise figures of their performance are needed. As such simulation tools are often used for identifying the most suitable shading element that suits the building. In literature there are many studies that have been done to designate the energy performance of shading devices in buildings by using simulation tools. This study focuses both on the shading device types used in the building sector and the previous studies done for designating the performance aspects of different shading devices types. Numerous studies for different building types located in different climatic regions have been reviewed in order to underline the importance of simulation modeling for shading devices in buildings. (C) 2015 Elsevier Ltd. All rights reserved.
Citation - Scopus: 14
Sports building envelope optimization using Multi-objective Multidisciplinary Design Optimization (M-MDO) techniques
(Institute of Electrical and Electronics Engineers Inc., 2015) Ding Yang; Michela Turrin; I. Sevil Sariyildiz; Yimin Sun; Turrin, Michela; Sariyildiz, Sevil; Sun, Yimin; Yang, Ding
Sports building envelopes are complex systems involving multiple architectural and engineering performance requirements that are sometimes in conflict with each other. Typically daylight usage and energy efficiency as two primary concerns in building envelope design are of those conflicting aspects. To improve overall performance (including daylight and energy performance) by changing the geometries of the envelope windows and shading elements as well as the selection of construction materials Multi-objective Optimization (MOO) is a natural choice. Based on the generated Pareto front trade-off decisions between competing performance objectives can be made. However as the number of design variables from different disciplines increases the huge design space and the specialization of disciplines make the optimization process less efficient. Therefore two possible Multidisciplinary Design Optimization (MDO) frameworks namely Individual Disciplinary Feasible (i.e. IDF a single-level MDO framework) and Collaborative Optimization (i.e. CO a bi-level MDO framework) are investigated to combine with MOO. Resorting to the capability of MDO in decomposition and coordination between different disciplines parallel disciplinary simulations and/or bi-level optimizations can be realized which compresses design cycle time and achieves better overall performance. Through the combination of MOO and MDO Multi-objective Multidisciplinary Design Optimization (M-MDO or multi-objective MDO) problems are expected to be solved more effectively and efficiently. The whole process of the proposed method consists of three phases (i.e. preprocessing solution and post-processing phases) in which variable screening multi-objective MDO solving and Pareto front comparison are performed respectively. An ongoing real project located in China is used as a case study to test the proposed method. For now the research work is in the preprocessing phase. Preliminary observations and results are obtained and future research is discussed. © 2017 Elsevier B.V. All rights reserved.
Citation - WoS: 6
Sports Building Envelope Optimization Using Multi-objective Multidisciplinary Design Optimization (M-MDO) Techniques Case of Indoor Sports Building Project in China
(IEEE, 2015) Ding Yang; Michela Turrin; Sevil Sariyildiz; Yimin Sun; Turrin, Michela; Sariyildiz, Sevil; Sun, Yimin; Yang, Ding
Sports building envelopes are complex systems involving multiple architectural and engineering performance requirements that are sometimes in conflict with each other. Typically daylight usage and energy efficiency as two primary concerns in building envelope design are of those conflicting aspects. To improve overall performance (including daylight and energy performance) by changing the geometries of the envelope windows and shading elements as well as the selection of construction materials Multi-objective Optimization (MOO) is a natural choice. Based on the generated Pareto front trade-off decisions between competing performance objectives can be made. However as the number of design variables from different disciplines increases the huge design space and the specialization of disciplines make the optimization process less efficient. Therefore two possible Multidisciplinary Design Optimization (MDO) frameworks namely Individual Disciplinary Feasible (i.e. IDF a single-level MDO framework) and Collaborative Optimization (i.e. CO a bi-level MDO framework) are investigated to combine with MOO. Resorting to the capability of MDO in decomposition and coordination between different disciplines parallel disciplinary simulations and/or bi-level optimizations can be realized which compresses design cycle time and achieves better overall performance. Through the combination of MOO and MDO Multi-objective Multidisciplinary Design Optimization (M-MDO or multi-objective MDO) problems are expected to be solved more effectively and efficiently. The whole process of the proposed method consists of three phases (i.e. preprocessing solution and post-processing phases) in which variable screening multi-objective MDO solving and Pareto front comparison are performed respectively. An ongoing real project located in China is used as a case study to test the proposed method. For now the research work is in the preprocessing phase. Preliminary observations and results are obtained and future research is discussed.
Citation - Scopus: 8
Time-cost optimization at the conceptual design stage using differential evolution
(Institute of Electrical and Electronics Engineers Inc., 2015) Onur Dursun; Berk Ekici; I. Sevil Sariyildiz; Ekici, Berk; Sariyildiz, Sevil; Dursun, Onur
Concurrent minimization of construction cost and duration is a challenging task for architects through conceptual design. Using differential evolution (DE) this study aims to obtain optimum design solutions that minimize unit cost of construction and construction duration. Single family housing projects in Germany is sampled with the intent of developing objective functions with regression analysis. The results suggests that DE is able to converge a set of optimum design solutions after adequate number of generations. Resemblance between descriptive statistics of the sampled observations and DE results underpins that regression models can be employed to develop objective functions in the presence of reliable and structured data. In addition results by the formal test of hypothesis based on hypervolume indicator offers DE/rand/1/bin outperforms DE/rand/2/bin irrespective of building standard. Last but not least solutions offered by DE allows us to discuss insights regarding design economics. © 2017 Elsevier B.V. All rights reserved.
Citation - WoS: 7
Time-Cost Optimization at the Conceptual Design Stage Using Differential Evolution Case of Single Family Housing Projects in Germany
(IEEE, 2015) Onur Dursun; Berk Ekici; Sevil Sariyildiz; Ekici, Berk; Sariyildiz, Sevil; Dursun, Onur
Concurrent minimization of construction cost and duration is a challenging task for architects through conceptual design. Using differential evolution (DE) this study aims to obtain optimum design solutions that minimize unit cost of construction and construction duration. Single family housing projects in Germany is sampled with the intent of developing objective functions with regression analysis. The results suggests that DE is able to converge a set of optimum design solutions after adequate number of generations. Resemblance between descriptive statistics of the sampled observations and DE results underpins that regression models can be employed to develop objective functions in the presence of reliable and structured data. In addition results by the formal test of hypothesis based on hypervolume indicator offers DE/rand/1/bin outperforms DE/rand/2/bin irrespective of building standard. Last but not least solutions offered by DE allows us to discuss insights regarding design economics.