Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5679082
Warren R. Scott, Warrren B Powell, H. Simão
We describe an adaptation of the knowledge gradient, originally developed for discrete ranking and selection problems, to the problem of calibrating continuous parameters for the purpose of tuning a simulator. The knowledge gradient for continuous parameters uses a continuous approximation of the expected value of a single measurement to guide the choice of where to collect information next. We show how to find the parameter setting that maximizes the expected value of a measurement by optimizing a continuous but nonconcave surface. We compare the method to sequential kriging for a series of test surfaces, and then demonstrate its performance in the calibration of an expensive industrial simulator.
{"title":"Calibrating simulation models using the knowledge gradient with continuous parameters","authors":"Warren R. Scott, Warrren B Powell, H. Simão","doi":"10.1109/WSC.2010.5679082","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679082","url":null,"abstract":"We describe an adaptation of the knowledge gradient, originally developed for discrete ranking and selection problems, to the problem of calibrating continuous parameters for the purpose of tuning a simulator. The knowledge gradient for continuous parameters uses a continuous approximation of the expected value of a single measurement to guide the choice of where to collect information next. We show how to find the parameter setting that maximizes the expected value of a measurement by optimizing a continuous but nonconcave surface. We compare the method to sequential kriging for a series of test surfaces, and then demonstrate its performance in the calibration of an expensive industrial simulator.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116817435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5679159
T. Allen, David N. Vuckovich
This paper proposes an open-source algorithm for simulation optimization. The intent is to permit many who use a variety of simulation software codes to be able to apply the proposed methods using an MS Excel-Visual Basic interface. First, we review selected literature on simulation optimization and its usefulness. Then, we briefly discuss methods that are commonly used for simulation optimization. Next, we present the proposed Population Indifference Zone (PIZ) algorithm and related software code. Also, we discuss the properties of the proposed method and present the code that runs the Visual Basic program. Finally, we discuss the functionality of the Population Indifference Zone method with examples of problems to which it might be applied and conclude with topics for future research.
{"title":"An open-source Population Indifference Zone-based algorithm for simulation optimization","authors":"T. Allen, David N. Vuckovich","doi":"10.1109/WSC.2010.5679159","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679159","url":null,"abstract":"This paper proposes an open-source algorithm for simulation optimization. The intent is to permit many who use a variety of simulation software codes to be able to apply the proposed methods using an MS Excel-Visual Basic interface. First, we review selected literature on simulation optimization and its usefulness. Then, we briefly discuss methods that are commonly used for simulation optimization. Next, we present the proposed Population Indifference Zone (PIZ) algorithm and related software code. Also, we discuss the properties of the proposed method and present the code that runs the Visual Basic program. Finally, we discuss the functionality of the Population Indifference Zone method with examples of problems to which it might be applied and conclude with topics for future research.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121284719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5678996
A. Kandil, A. Ezeldin, S. Farghal, Tarek Mahfouz
Construction planning methods have been in continuous evolution due to the increasing complexity of construction projects. Construction simulation modeling is one of the later stages of this evolution that has received much attention in research. Many simulation based construction planning methods developed modeling methods that attempt to cluster project activities into smaller sub-models that enhance model reusability. Many of these modeling methods, however, create new modeling elements that are not familiar to traditional construction simulation modelers. Therefore, the objective of this paper is to develop a method for clustering activities of large and repetitive construction projects for enhancing the reusability of those simulation models. The developed method does not create any new modeling elements and is called Clustered Simulation Modeling (CSM). CSM was evaluated in modeling an actual large-scale repetitive construction projects, and the results have illustrated the effectiveness of the method and the proposed clustering scheme.
{"title":"Clustered simulation for the simulation of large repetitive construction projects","authors":"A. Kandil, A. Ezeldin, S. Farghal, Tarek Mahfouz","doi":"10.1109/WSC.2010.5678996","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678996","url":null,"abstract":"Construction planning methods have been in continuous evolution due to the increasing complexity of construction projects. Construction simulation modeling is one of the later stages of this evolution that has received much attention in research. Many simulation based construction planning methods developed modeling methods that attempt to cluster project activities into smaller sub-models that enhance model reusability. Many of these modeling methods, however, create new modeling elements that are not familiar to traditional construction simulation modelers. Therefore, the objective of this paper is to develop a method for clustering activities of large and repetitive construction projects for enhancing the reusability of those simulation models. The developed method does not create any new modeling elements and is called Clustered Simulation Modeling (CSM). CSM was evaluated in modeling an actual large-scale repetitive construction projects, and the results have illustrated the effectiveness of the method and the proposed clustering scheme.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123538326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5679056
Nick Brown
The idea of simulation model “re-use” is a novel term that in theory will allow for quick turn-around times where budgetary constraints can hold back the development of a new model. The intention of this paper is not to examine a specific example of how a simulation was developed and utilized for “re-use”, but rather explain the process of developing a computer simulation flexible enough that will allow for “reuse”. The overall outcome of this type of development is a data-driven simulation model that is flexible enough to expand to many similar systems without significantly altering the code of the simulation. As a result of this data-driven simulation, companies/organizations are able to reap the benefits of reducing future development time, utilizing the model for other similar systems, achieve quick turn-around, and the ability to perform large scale sensitivity analysis.
{"title":"Model flexibility: Development of a generic data-driven simulation","authors":"Nick Brown","doi":"10.1109/WSC.2010.5679056","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679056","url":null,"abstract":"The idea of simulation model “re-use” is a novel term that in theory will allow for quick turn-around times where budgetary constraints can hold back the development of a new model. The intention of this paper is not to examine a specific example of how a simulation was developed and utilized for “re-use”, but rather explain the process of developing a computer simulation flexible enough that will allow for “reuse”. The overall outcome of this type of development is a data-driven simulation model that is flexible enough to expand to many similar systems without significantly altering the code of the simulation. As a result of this data-driven simulation, companies/organizations are able to reap the benefits of reducing future development time, utilizing the model for other similar systems, achieve quick turn-around, and the ability to perform large scale sensitivity analysis.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"373 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123409302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5679126
Allan Clark, J. Hillston, S. Gilmore, P. Kemper
Simulation modeling in systems biology embarks on discrete event simulation only for cases of small cardinalities of entities and uses continuous simulation otherwise. Modern modeling environments like Bio-PEPA support both types of simulation within a single modeling formalism. Developing models for complex dynamic phenomena is not trivial in practice and requires careful verification and testing. In this paper, we describe relevant steps in the verification and testing of a TNFα-mediated NF-κB signal transduction pathway model and discuss to what extent automated techniques help a practitioner to derive a suitable model.
{"title":"VERIFICATION AND TESTING OF BIOLOGICAL MODELS","authors":"Allan Clark, J. Hillston, S. Gilmore, P. Kemper","doi":"10.1109/WSC.2010.5679126","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679126","url":null,"abstract":"Simulation modeling in systems biology embarks on discrete event simulation only for cases of small cardinalities of entities and uses continuous simulation otherwise. Modern modeling environments like Bio-PEPA support both types of simulation within a single modeling formalism. Developing models for complex dynamic phenomena is not trivial in practice and requires careful verification and testing. In this paper, we describe relevant steps in the verification and testing of a TNFα-mediated NF-κB signal transduction pathway model and discuss to what extent automated techniques help a practitioner to derive a suitable model.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128891760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5679071
R. Barton, B. Nelson, Wei Xie
We consider the problem of producing confidence intervals for the mean response of a system represented by a stochastic simulation that is driven by input models that have been estimated from “real-world” data. Therefore, we want the confidence interval to account for both uncertainty about the input models and stochastic noise in the simulation output; standard practice only accounts for the stochastic noise. To achieve this goal we introduce metamodel-assisted bootstrapping, and illustrate its performance relative to other proposals for dealing with input uncertainty on two queueing examples.
{"title":"A framework for input uncertainty analysis","authors":"R. Barton, B. Nelson, Wei Xie","doi":"10.1109/WSC.2010.5679071","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679071","url":null,"abstract":"We consider the problem of producing confidence intervals for the mean response of a system represented by a stochastic simulation that is driven by input models that have been estimated from “real-world” data. Therefore, we want the confidence interval to account for both uncertainty about the input models and stochastic noise in the simulation output; standard practice only accounts for the stochastic noise. To achieve this goal we introduce metamodel-assisted bootstrapping, and illustrate its performance relative to other proposals for dealing with input uncertainty on two queueing examples.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128903072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5678863
Yan Liu, S. Takakuwa
To ensure just-in-time shipments from a general non-automated retail-cross-docking center, different items must be handled efficiently by different processes despite the many inbound shipments and frequent demand orders from retail stores. In this paper, a systematic and flexible procedure is proposed that efficiently provides critical decision-making support to logistics managers to help them understand and validate the material handling operation at a real retail-cross-docking center. The proposed procedure considers dynamic logistics operation information, such as inbound schedules of suppliers, demand data from retail-chain stores, and individual operator schedules. This detailed data is required for the performance of simulation. In addition, the procedure is applied to an actual non-automated retail-cross-docking center to confirm its effectiveness. Furthermore, the proposed method was found to be both practical and powerful in assisting logistics managers with their continuous decision-making efforts.
{"title":"Enhancing simulation as a decision-making support tool for a crossdocking center in a dynamic retail-distribution environment","authors":"Yan Liu, S. Takakuwa","doi":"10.1109/WSC.2010.5678863","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678863","url":null,"abstract":"To ensure just-in-time shipments from a general non-automated retail-cross-docking center, different items must be handled efficiently by different processes despite the many inbound shipments and frequent demand orders from retail stores. In this paper, a systematic and flexible procedure is proposed that efficiently provides critical decision-making support to logistics managers to help them understand and validate the material handling operation at a real retail-cross-docking center. The proposed procedure considers dynamic logistics operation information, such as inbound schedules of suppliers, demand data from retail-chain stores, and individual operator schedules. This detailed data is required for the performance of simulation. In addition, the procedure is applied to an actual non-automated retail-cross-docking center to confirm its effectiveness. Furthermore, the proposed method was found to be both practical and powerful in assisting logistics managers with their continuous decision-making efforts.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"98-100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128488100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5679059
T. Highley, Ross Gore, Cameron Snapp
AggPro predicts baseball statistics by utilizing a weighted average of predictions provided by several other statistics projection systems. The aggregate projection that is generated is more accurate than any of the constituent systems individually. We explored the granularity at which weights should be assigned by considering four possibilities: a single weight for each projection system, one weight per category per system, one weight per player per system, and one weight per player per category per system. We found that assigning one weight per category per system provides better results than the other options. Additionally, we projected raw statistics directly and compared the results to projecting rate statistics scaled by predicted player usage. We found that predicting rate statistics and scaling by predicted player usage produces better results. We also discuss implementation challenges that we faced in producing the AggPro projections.
{"title":"Granularity of weighted averages and use of rate statistics in AggPro","authors":"T. Highley, Ross Gore, Cameron Snapp","doi":"10.1109/WSC.2010.5679059","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679059","url":null,"abstract":"AggPro predicts baseball statistics by utilizing a weighted average of predictions provided by several other statistics projection systems. The aggregate projection that is generated is more accurate than any of the constituent systems individually. We explored the granularity at which weights should be assigned by considering four possibilities: a single weight for each projection system, one weight per category per system, one weight per player per system, and one weight per player per category per system. We found that assigning one weight per category per system provides better results than the other options. Additionally, we projected raw statistics directly and compared the results to projecting rate statistics scaled by predicted player usage. We found that predicting rate statistics and scaling by predicted player usage produces better results. We also discuss implementation challenges that we faced in producing the AggPro projections.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126931692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5678905
Catherine Brickner, Dennis Indrawan, Derrick Williams, S. Chakravarthy
In this paper we simulate a queueing model useful in a service system with the help of ARENA simulation software. The service calls (henceforth referred to as customers) arrive to a processing center according to a Markovian arrival process (MAP). There is a buffer of finite size to hold the customers. Any customer finding the buffer is considered lost. An arriving customer belongs to one of three types, and the admitted customer is served by one of many dedicated servers (exclusively set aside for each of the three types of customers) or by one of many flexible servers who are capable of servicing all types of customers. The flexible servers are used only when the respective dedicated servers are all busy. A priority scheme is used to select the type of customer from the buffer when a flexible server is called for servicing the waiting customers. The processing times are assumed to be of phase type. Simulated results are discussed.
{"title":"Simulation of a stochastic model for a service system","authors":"Catherine Brickner, Dennis Indrawan, Derrick Williams, S. Chakravarthy","doi":"10.1109/WSC.2010.5678905","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678905","url":null,"abstract":"In this paper we simulate a queueing model useful in a service system with the help of ARENA simulation software. The service calls (henceforth referred to as customers) arrive to a processing center according to a Markovian arrival process (MAP). There is a buffer of finite size to hold the customers. Any customer finding the buffer is considered lost. An arriving customer belongs to one of three types, and the admitted customer is served by one of many dedicated servers (exclusively set aside for each of the three types of customers) or by one of many flexible servers who are capable of servicing all types of customers. The flexible servers are used only when the respective dedicated servers are all busy. A priority scheme is used to select the type of customer from the buffer when a flexible server is called for servicing the waiting customers. The processing times are assumed to be of phase type. Simulated results are discussed.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127129750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5679180
Hong Chen, Emily K. Lada
We present an overview of resource management in SAS Simulation Studio, an object-oriented, Java-based application for building and analyzing discrete-event simulation models. In Simulation Studio, resources are modeled as special types of hierarchical entities that can be assigned attributes and flow through the model. Furthermore, resource entities can be seized and released by other entities to fulfill resource demands. Flexible resource entity rules are used to specify these demands, as well as the requirements of other resource operations, such as state and capacity changes. The hierarchical, entity-based approach in Simulation Studio allows the user more control over resource behavior and provides many advantages over alternative resource management techniques, especially in the areas of resource scheduling and preemption.
{"title":"Resource management in SAS Simulation Studio","authors":"Hong Chen, Emily K. Lada","doi":"10.1109/WSC.2010.5679180","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679180","url":null,"abstract":"We present an overview of resource management in SAS Simulation Studio, an object-oriented, Java-based application for building and analyzing discrete-event simulation models. In Simulation Studio, resources are modeled as special types of hierarchical entities that can be assigned attributes and flow through the model. Furthermore, resource entities can be seized and released by other entities to fulfill resource demands. Flexible resource entity rules are used to specify these demands, as well as the requirements of other resource operations, such as state and capacity changes. The hierarchical, entity-based approach in Simulation Studio allows the user more control over resource behavior and provides many advantages over alternative resource management techniques, especially in the areas of resource scheduling and preemption.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114367789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：