{"title":"Output analysis for simulation","authors":"A. F. Seila","doi":"10.1109/WSC.1991.185588","DOIUrl":"https://doi.org/10.1109/WSC.1991.185588","url":null,"abstract":"Methods are reviewed for analyzing data produced by simulations. The author discusses the objectives of output analysis and examines the need to apply statistical methods. Methods for estimating parameters from terminating and steady-state simulations are presented. For steady-state simulations, methods for computing estimates of the mean as well as proportions and percentiles are presented. Multivariate estimation techniques are discussed, and some practical advice is provided concerning output analysis in practice.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126487248","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}
{"title":"Parallel instance discrete-event simulation using a vector uniprocessor","authors":"James F. Ohi, B. R. Preiss","doi":"10.1109/WSC.1991.185663","DOIUrl":"https://doi.org/10.1109/WSC.1991.185663","url":null,"abstract":"The authors examine the possibility of running simulations in parallel on a vector processor. In such a system each instance of execution runs identical code but with a different input data set. The main problem addressed is the choice of block selection policy, that is, the choice of which indivisible block of code to execute next. The authors investigate four block selection policies by simulating the execution of such a system. A stochastic flow-graph representation was chosen to model the execution of a simulation. A two-level block selection policy was found to have the best potential speedup of the four block selection policies. The speedup levels achieved were not large, and decreased when there are a large number of unique event types (and therefore handlers) in the simulated system.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125914370","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}
{"title":"Interactive experiment planning to control knowledge-based simulation","authors":"R. Frederking","doi":"10.1109/WSC.1991.185745","DOIUrl":"https://doi.org/10.1109/WSC.1991.185745","url":null,"abstract":"The author presents an initial attempt to facilitate the design and execution of simulation experiments through the use of an interactive, opportunistic, hierarchical planner. The planner provides an orderly way to control the planning and execution of simulation experiments without overly restricting the user to a preestablished routine. In addition to planning the simulation and keeping track of its current state, the planner, through its graphical interface, can provide the simulator with a natural, coherent framework for its user interface. Examples are presented of the planner's graphical interface.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125799432","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}
{"title":"The cost of terminating synchronous parallel discrete-event simulations","authors":"V. Sanjeevan, M. Abrams","doi":"10.1109/WSC.1991.185669","DOIUrl":"https://doi.org/10.1109/WSC.1991.185669","url":null,"abstract":"The authors propose seven algorithms by which an arbitrary termination condition can be mechanically added to a nonterminating parallel simulation using a conservative-synchronous protocol. Informal arguments about the performance of each algorithm are made, and the arguments are confirmed through measurement of the bounded lag protocol using torus networks on a shared memory multiprocessor. Conservative-synchronous protocols are shown to be inherently efficient in the experiments considered; adding a termination algorithm requires limited additional memory and increases the wall clock time required for simulation by at most an amount proportional to the number of logical processes. Furthermore, a simulation model with any stable termination condition requires negligible overhead for the termination algorithm, a property that appears to be unique to synchronous protocols.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128154083","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}
{"title":"A survey of varied production systems and different aspects using computer simulation","authors":"K. Weigl","doi":"10.1109/WSC.1991.185648","DOIUrl":"https://doi.org/10.1109/WSC.1991.185648","url":null,"abstract":"The author presents different problems associated with conducting simulation projects of a wide range of production systems. He provides some insight into the variety of initial conditions and illustrates different situations for the modeler. It is pointed out that historically grown systems, e.g., in the metal industry with a very low level of automation and poorly controlled material flow, are very difficult to analyze and to develop the functional specification for. The author points out unpredictable benefits for the production engineer during the simulation process. AGV (automatic guided vehicle) modeling in the automotive industry and a flexible manufacturing system are among the examples considered. All finished projects described used SIMAN/CINEMA for model development.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134064390","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}
{"title":"A projected stochastic approximation algorithm","authors":"S. Andradóttir","doi":"10.1109/WSC.1991.185710","DOIUrl":"https://doi.org/10.1109/WSC.1991.185710","url":null,"abstract":"It is noted that classical stochastic approximation algorithms often diverge because of boundedness problems. The standard approach to preventing this is to project the sequence generated by the algorithm onto a predetermined compact set K. However, in the typical application, the approximate location of the solution is not known. To minimize the probability that the solution lies outside the set K, it is therefore necessary to let K be large. This can seriously curtail the efficiency of the algorithm. The author proposes a stochastic approximation algorithm which bounds the sequence of estimates of the solution to an increasing sequence of sets. This eliminates the possibility of bounding the algorithm to a set which does not contain the solution. Furthermore, it is possible to let the initial set be small, which can result in improved empirical performance.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132776204","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}
{"title":"Interconnected ring networks: a performance study","authors":"S. Ramakrishnan, Pratap Thondapu","doi":"10.1109/WSC.1991.185678","DOIUrl":"https://doi.org/10.1109/WSC.1991.185678","url":null,"abstract":"The authors investigate the performance of multiple ring networks interconnected via bridges to a backbone ring. The networks use the IEEE 802.5 protocol. The model characterizes the behavior of the IEEE 802.2 protocol used at the logical link control layer. The primary performance measures are throughput and delay. The network carries only interring traffic. The model considers homogeneous traffic environments. It is shown that the protocol throughput is critically dependent on the window size and the buffer size at the intervening bridges.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132622001","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}
{"title":"The effects of batching on the power of the test for frequency domain methodology","authors":"D. Morrice","doi":"10.1109/WSC.1991.185718","DOIUrl":"https://doi.org/10.1109/WSC.1991.185718","url":null,"abstract":"The author considers an implementation of frequency domain methodology (FDM) where input factor levels are held fixed in batches. In addition, the simulation output series is batched and the corresponding batch means are used as observations in the FDM factor screening analysis. For a certain class of metamodels, steady-state results are provided. Results are also provided for batch sizes chosen to reduce serial correlation in output series, but not necessarily to achieve steady state. An example is presented which illustrates cases where fixed factor batching (FFB) improves the power of the FDM hypothesis test and cases where it does not. For cases where FFB is beneficial with respect to the power of the test, it is shown that batching to an intermediate batch size may be better than batching to achieve steady state.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123559260","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}
{"title":"Integrating GIS, simulation and animation","authors":"E. Lieberman","doi":"10.1109/WSC.1991.185684","DOIUrl":"https://doi.org/10.1109/WSC.1991.185684","url":null,"abstract":"The author describes techniques for combining the strengths of geographical information systems (GISs), microscopic simulation, and computer animation. A simulation system integrated with an existing GIS to provide the user with the capability of accessing and managing the information transfer between the GIS and the simulation models is described. This integrated system need not be limited to simulation alone; other calculations which are essential for the traffic engineer can be integrated as well. For example, the calculation of highway capacity is a basic need of all traffic engineers. The software to perform these calculations can, itself, be integrated with the GIS system, traffic simulation, and animation. Such a system offers the engineer a capability that goes beyond analysis: the engineer can now perform designs of a system exploring alternative treatments to identify the most effective technique for improving traffic operations.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115165941","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}
T. Aoki, S. Nakayama, M. Yamamoto, M. Hashimoto, J. Tanaka
{"title":"Combinatorial scheduler: simulation and optimization algorithm","authors":"T. Aoki, S. Nakayama, M. Yamamoto, M. Hashimoto, J. Tanaka","doi":"10.1109/WSC.1991.185625","DOIUrl":"https://doi.org/10.1109/WSC.1991.185625","url":null,"abstract":"Describes a novel job shop scheduler based on a heuristic optimization algorithm and discrete event simulation. One of the features of this scheduler is high-speed scheduling, which depends on the configuration of this system. The optimization algorithm determines the product sequence to be used in the shop. Then, a simulator determines each product flow based on the shop floor model and simple dispatching rules. The key point for high-speed scheduling is to reduce the complexity of simulation rules. The simulator has responsibility only for local optimization. A second feature of this scheduler is the scheduling algorithm which can handle multiobjectives. In a real factory, the due date has top priority for scheduling, but the lead time and machine utilization can be changed by production circumstances. In this scheduler, machine load leveling is used for shortening the lead time, and a higher load at a later process is used for increasing the machine utilization. An operator can assign the balance of lead time and machine utilization by setting a parameter. An application to a real shop floor is discussed.<<ETX>>","PeriodicalId":448258,"journal":{"name":"1991 Winter Simulation Conference Proceedings.","volume":"40 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122807912","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}