Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5678973
Ming Liu, B. Nelson, J. Staum
We develop a sequential experiment design procedure to construct multiple metamodels based on a single stochastic simulation model. We apply the procedure to approximate many securities' prices as functions of a financial scenario. We propose a cross-validation method that adds design points and simulation effort at the design points to target all metamodels' relative prediction errors. To improve the expected quality of the metamodels given randomness of the scenario that is an input to the simulation model, we also propose a way to choose design points so that the scenario is likely to fall inside their convex hull.
{"title":"Simulation on demand for pricing many securities","authors":"Ming Liu, B. Nelson, J. Staum","doi":"10.1109/WSC.2010.5678973","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678973","url":null,"abstract":"We develop a sequential experiment design procedure to construct multiple metamodels based on a single stochastic simulation model. We apply the procedure to approximate many securities' prices as functions of a financial scenario. We propose a cross-validation method that adds design points and simulation effort at the design points to target all metamodels' relative prediction errors. To improve the expected quality of the metamodels given randomness of the scenario that is an input to the simulation model, we also propose a way to choose design points so that the scenario is likely to fall inside their convex hull.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"16 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":"132214763","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.2010.5678952
W. Scholl, Boon-Ping Gan, Ming Li Peh, P. Lendermann, Daniel Noack, O. Rose, P. Preuss
Discrete Event Simulation (DES) has widely been used for mid and long term forecasting in wafer fabrication plants. But the use of DES for short term forecasting has been limited due to the perceived modelling and computation complexity as well as the non-steady state nature of today's wafer fab operations. In this paper, we discuss some important modelling issues associated with building an online simulation model. Key elements considered are actual process routes, process and throughput modelling as a function of equipment behavior, lot size, and available processing modules, process dedication at equipment level, equipment downs at mainframe level, estimated lot release strategy, send ahead wafers, dispatch rules, and setup. Typical application areas are proactive dedication management, preventive maintenance scheduling and WIP based sampling optimization.
{"title":"Towards realization of a high-fidelity simulation model for short-term horizon forecasting in wafer fabrication facilities","authors":"W. Scholl, Boon-Ping Gan, Ming Li Peh, P. Lendermann, Daniel Noack, O. Rose, P. Preuss","doi":"10.1109/WSC.2010.5678952","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678952","url":null,"abstract":"Discrete Event Simulation (DES) has widely been used for mid and long term forecasting in wafer fabrication plants. But the use of DES for short term forecasting has been limited due to the perceived modelling and computation complexity as well as the non-steady state nature of today's wafer fab operations. In this paper, we discuss some important modelling issues associated with building an online simulation model. Key elements considered are actual process routes, process and throughput modelling as a function of equipment behavior, lot size, and available processing modules, process dedication at equipment level, equipment downs at mainframe level, estimated lot release strategy, send ahead wafers, dispatch rules, and setup. Typical application areas are proactive dedication management, preventive maintenance scheduling and WIP based sampling optimization.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"36 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":"134308982","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}
Pub Date : 2010-12-05DOI: 10.1109/WSC.2010.5678865
R. Andriansyah, L. Etman, J. Rooda
An aggregate modeling methodology is proposed to predict flow time distributions of an end-of-aisle order picking workstation in parts-to-picker automated warehouses with overtaking. The proposed aggregate model uses as input an aggregated process time referred to as the effective process time in combination with overtaking distributions and decision probabilities, which we measure directly from product arrival and departure data. Experimental results show that the predicted flow time distributions are accurate, with prediction errors of the flow time mean and squared coefficient of variation less than 4% and 9%, respectively. As a case study, we use data collected from a real, operating warehouse and show that the predicted flow time distributions resemble the flow time distributions measured from the data.
{"title":"Aggregate modeling for flow time prediction of an end-of-aisle order picking workstation with overtaking","authors":"R. Andriansyah, L. Etman, J. Rooda","doi":"10.1109/WSC.2010.5678865","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678865","url":null,"abstract":"An aggregate modeling methodology is proposed to predict flow time distributions of an end-of-aisle order picking workstation in parts-to-picker automated warehouses with overtaking. The proposed aggregate model uses as input an aggregated process time referred to as the effective process time in combination with overtaking distributions and decision probabilities, which we measure directly from product arrival and departure data. Experimental results show that the predicted flow time distributions are accurate, with prediction errors of the flow time mean and squared coefficient of variation less than 4% and 9%, respectively. As a case study, we use data collected from a real, operating warehouse and show that the predicted flow time distributions resemble the flow time distributions measured from the data.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"59 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":"114392983","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.2010.5678860
Yilin Huang, M. Seck, A. Verbraeck
The increasing complexity of railway systems and the high costs incurred by design and operational errors make modeling and simulation a popular methodology in the domain of railway transportation. To successfully support detailed design and operation, a microscopic rail network model is often deemed not only suitable but also mandatory. However, the simulation of large-scale microscopic models is computationally intensive, making it unsuitable for real-time applications. In this paper, a railway simulation library, LIBROS-II, is introduced which offers high performance rail simulation at the microscopic level. The library is specified with the DEVS formalism. Its major components and their specifications are presented. Its performance is assessed through a simple example and contrasted with a typical model using a continuous modeling abstraction of train movement. The result shows that with comparable model detail and accuracy the LIBROS-II model yields a higher performance than the model using differential equations.
{"title":"LIBROS-II: Railway modeling with DEVS","authors":"Yilin Huang, M. Seck, A. Verbraeck","doi":"10.1109/WSC.2010.5678860","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678860","url":null,"abstract":"The increasing complexity of railway systems and the high costs incurred by design and operational errors make modeling and simulation a popular methodology in the domain of railway transportation. To successfully support detailed design and operation, a microscopic rail network model is often deemed not only suitable but also mandatory. However, the simulation of large-scale microscopic models is computationally intensive, making it unsuitable for real-time applications. In this paper, a railway simulation library, LIBROS-II, is introduced which offers high performance rail simulation at the microscopic level. The library is specified with the DEVS formalism. Its major components and their specifications are presented. Its performance is assessed through a simple example and contrasted with a typical model using a continuous modeling abstraction of train movement. The result shows that with comparable model detail and accuracy the LIBROS-II model yields a higher performance than the model using differential equations.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"4 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":"114461744","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.2010.5678924
B. Pearce, Narges Hosseini, K. Taaffe, N. Huynh, S. Harris
Late starting surgeries at a Greenville Memorial Hospital have been shown to cause process and scheduling disruptions, and are a major contributor to dissatisfaction among patients and hospital staff. The preoperative system requires the preparation of a high volume of patients, each with an individual set of characteristics and array of required tasks before surgery. Staff resources do not have a prescribed sequence of activities nor mutually exclusive duties. A novel discrete event modeling paradigm has been adopted for simulating the complex behavior of the preoperative system, identifying the underlying causes of process inefficiencies, and testing mitigating strategies. Current investigations are underway to shift the prescriptive approach of resource decision-making towards an agent-based approach, allowing resources to select their workload in such a way that achieves maximum utility for the agent.
格林维尔纪念医院(Greenville Memorial Hospital)的手术开始时间过晚已被证明会导致手术流程和日程安排中断，这是导致患者和医院工作人员不满的主要原因。术前系统需要准备大量的患者，每个患者在手术前都有自己的一套特征和一系列所需的任务。工作人员资源没有规定的活动顺序，也没有相互排斥的职责。采用了一种新的离散事件建模范式来模拟术前系统的复杂行为，确定流程效率低下的潜在原因，并测试缓解策略。目前正在进行调查，以将资源决策的规定性方法转向基于代理的方法，允许资源以实现代理最大效用的方式选择其工作量。
{"title":"Modeling interruptions and patient flow in a preoperative hospital environment","authors":"B. Pearce, Narges Hosseini, K. Taaffe, N. Huynh, S. Harris","doi":"10.1109/WSC.2010.5678924","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678924","url":null,"abstract":"Late starting surgeries at a Greenville Memorial Hospital have been shown to cause process and scheduling disruptions, and are a major contributor to dissatisfaction among patients and hospital staff. The preoperative system requires the preparation of a high volume of patients, each with an individual set of characteristics and array of required tasks before surgery. Staff resources do not have a prescribed sequence of activities nor mutually exclusive duties. A novel discrete event modeling paradigm has been adopted for simulating the complex behavior of the preoperative system, identifying the underlying causes of process inefficiencies, and testing mitigating strategies. Current investigations are underway to shift the prescriptive approach of resource decision-making towards an agent-based approach, allowing resources to select their workload in such a way that achieves maximum utility for the agent.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"25 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":"114488871","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.2010.5679164
J. Mela, R. V. Osuna, A. Riitahuhta, Timo Lehtonen
Advanced design support solutions such as 3D simulations have enabled improved management of design information for years. The challenge, however, is that acquiring these type of design support solutions does not necessarily create a visible business value for the company in a short run. Moreover, the organization surrounding the simulation solution should support its use by providing the conditions and resources needed for utilizing it. Vice versa, design support solutions have to support the prevailing organizational conditions. Especially the interaction between the planned design-support solution, existing process structures and human related issues have to be understood to create the basis for business efficient design information management. Understanding the chain effects of employing different types of design support solutions has on organizational “ecosystem”, creates basis for forming business-effective sustainable communication and design support structures. The Company Strategic Landscape introduced will form the framework for recognizing these chain effects in business environment.
{"title":"Landscape for analysing the business effects of utilizing design support simulations","authors":"J. Mela, R. V. Osuna, A. Riitahuhta, Timo Lehtonen","doi":"10.1109/WSC.2010.5679164","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679164","url":null,"abstract":"Advanced design support solutions such as 3D simulations have enabled improved management of design information for years. The challenge, however, is that acquiring these type of design support solutions does not necessarily create a visible business value for the company in a short run. Moreover, the organization surrounding the simulation solution should support its use by providing the conditions and resources needed for utilizing it. Vice versa, design support solutions have to support the prevailing organizational conditions. Especially the interaction between the planned design-support solution, existing process structures and human related issues have to be understood to create the basis for business efficient design information management. Understanding the chain effects of employing different types of design support solutions has on organizational “ecosystem”, creates basis for forming business-effective sustainable communication and design support structures. The Company Strategic Landscape introduced will form the framework for recognizing these chain effects in business environment.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"59 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":"114570072","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.2010.5679081
I. Ryzhov, Martin Valdez-Vivas, Warrren B Powell
We examine a newsvendor problem with two agents: a requesting agent that observes private demand information, and an oversight agent that must determine how to allocate resources upon receiving a bid from the requesting agent. Because the two agents have different cost structures, the requesting agent tends to bid higher than the amount that is actually needed. As a result, the allocating agent needs to adaptively learn how to interpret the bids and estimate the requesting agent's biases. Learning must occur as quickly as possible, because each suboptimal resource allocation incurs an economic cost. We present a mathematical model that casts the problem as a Markov decision process with unknown transition probabilities. We then perform a simulation study comparing four different techniques for optimal learning of transition probabilities. The best technique is shown to be a knowledge gradient algorithm, based on a one-period look-ahead approach.
{"title":"Optimal learning of transition probabilities in the two-agent newsvendor problem","authors":"I. Ryzhov, Martin Valdez-Vivas, Warrren B Powell","doi":"10.1109/WSC.2010.5679081","DOIUrl":"https://doi.org/10.1109/WSC.2010.5679081","url":null,"abstract":"We examine a newsvendor problem with two agents: a requesting agent that observes private demand information, and an oversight agent that must determine how to allocate resources upon receiving a bid from the requesting agent. Because the two agents have different cost structures, the requesting agent tends to bid higher than the amount that is actually needed. As a result, the allocating agent needs to adaptively learn how to interpret the bids and estimate the requesting agent's biases. Learning must occur as quickly as possible, because each suboptimal resource allocation incurs an economic cost. We present a mathematical model that casts the problem as a Markov decision process with unknown transition probabilities. We then perform a simulation study comparing four different techniques for optimal learning of transition probabilities. The best technique is shown to be a knowledge gradient algorithm, based on a one-period look-ahead approach.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"516 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":"123093120","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.2010.5678879
K. Miwa, S. Takakuwa
In this study, a simulation modeling procedure for a retail store was proposed to find the optimal number of clerks based on operation types, operation frequency, and staffing schedule. First, all required data for staffing problems were collected and work loading was performed during each 24-hour period. Then, integer programming was used to obtain an initial feasible solution. Finally, simulation experiments were performed together using OptQuest, and optimal solutions were obtained. The proposed procedure was applied to the actual case. It was found that the staffing problems can be solved easily and effectively.
{"title":"Optimization and analysis of staffing problems at a retail store","authors":"K. Miwa, S. Takakuwa","doi":"10.1109/WSC.2010.5678879","DOIUrl":"https://doi.org/10.1109/WSC.2010.5678879","url":null,"abstract":"In this study, a simulation modeling procedure for a retail store was proposed to find the optimal number of clerks based on operation types, operation frequency, and staffing schedule. First, all required data for staffing problems were collected and work loading was performed during each 24-hour period. Then, integer programming was used to obtain an initial feasible solution. Finally, simulation experiments were performed together using OptQuest, and optimal solutions were obtained. The proposed procedure was applied to the actual case. It was found that the staffing problems can be solved easily and effectively.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"22 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":"122962459","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}
Proxies are caches of information maintained by one simulation object about other simulation objects. Though proxies can require significant overhead to maintain consistency, their judicious use can improve parallel performance by increasing speedup. This paper discusses three cases where careful use of proxies has improved speedup in a parallel discrete event simulator implemented using threaded worker pools.
{"title":"Employing proxies to improve parallel discrete event simulation performance","authors":"David W. Mutschler","doi":"10.5555/2433508.2433693","DOIUrl":"https://doi.org/10.5555/2433508.2433693","url":null,"abstract":"Proxies are caches of information maintained by one simulation object about other simulation objects. Though proxies can require significant overhead to maintain consistency, their judicious use can improve parallel performance by increasing speedup. This paper discusses three cases where careful use of proxies has improved speedup in a parallel discrete event simulator implemented using threaded worker pools.","PeriodicalId":272260,"journal":{"name":"Proceedings of the 2010 Winter Simulation Conference","volume":"97 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":"123021813","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：