《社会系统仿真ppt课件.ppt》由会员分享，可在线阅读，更多相关《社会系统仿真ppt课件.ppt（28页珍藏版）》请在taowenge.com淘文阁网|工程机械CAD图纸|机械工程制图|CAD装配图下载|SolidWorks_CaTia_CAD_UG_PROE_设计图分享下载上搜索。
1、I.IntroductionM.Peter JurkatCS452/Mgt532 Simulation for Managerial DecisionsThe Robert O.Anderson Schools of ManagementUniversity of New Mexico 1/6/20231MPJ/UNM CS452/Mgt 532 I.IntroductionDefinitionslSimulation:process of experimenting with a model of a dynamic systems(e.g.,process)to study or test
2、 the behavior of the system improve,problem solvedesign and/or select new systems,and/ortrain operators on a model of an existing systemslSystem:purposeful,interrelated components with interdependencies and complexitylBehavior:purposeful,interrelated sequences of activitieslDynamic:time varying(stat
3、ic systems are dull!)1/6/20232MPJ/UNM CS452/Mgt 532 I.IntroductionExampleslService Systems:Traffic on Networks:messages to/from computers,cars on roads/rails,airplanes to/from airports/gates,ships to/from harbors/piers,elevatorsRetail/Service:stores selling goods,service/repair shops,logistics/inven
4、tory/distribution/MRPlManufacturing Systems:Materials,Chemicals,BiologicalsAppliances,Automobiles/Trucks,Toys,ClothingElectronics,Weapons SystemslComputations using models from other disciplinesMacroeconomic:taxation/interest rate cost/benefitsPollution:environmental intervention cost/benefitsProjec
5、t Management:completion time vs resources1/6/20233MPJ/UNM CS452/Mgt 532 I.IntroductionWhy Simulate?lTo overcome human limitations inPhysical capability:avoid injury and death;be able to control systems whose dynamics are not yet known,Mental capability:attention,memory,processing,lAnalysis:allows us
6、 to study systems too complex for analytic description and/or too dangerous for human safety gain knowledgelDesign:attempt changes in IVs to drive one or more DVs toward an“optimal”value or combination of values for design,improvement,and/or problem solving1/6/20234MPJ/UNM CS452/Mgt 532 I.Introducti
7、onWhen not to Simulate!lWhen theory can determine sufficient resultslWhen it will cost more to simulate than the return on the knowledge gainedlWhen there is incomplete information about the system(can handle imprecise but not missing pieces)Need at least inputs and related outputs for“black boxes”C
8、an assume missing information and check against known results if agreement,support for assumptionslWhen it is not possible to develop a representative,tractable simplification of the system1/6/20235MPJ/UNM CS452/Mgt 532 I.IntroductionDefinitions(cont.)lModel:representation of a system three phases:1
9、.Verbal always included in any representation2.Graphical see pages 22,39,50,54,367,and 536 3.Algorithm and/or computer programlExperimentation:purposeful,structured,and controlled change of the inputs factors(independent variables IVs,exogenous,)of a product and/or process to observe resulting chang
10、es in outputs(dependent variables-DVs,responses,results,outcomes,)lBoth IVs,DVs also called measures or metricslIn simulation literature a run is one execution of the simulation program at one combination of input variable values also called a replication1/6/20236MPJ/UNM CS452/Mgt 532 I.Introduction
11、Graphical Representation:Logical SymbolslBCNN 4th Ed.,Figure 2.1,page 22:Single Server Queuing System1/6/20237MPJ/UNM CS452/Mgt 532 I.IntroductionGraphical Representation:State Variable TrackinglBCNN 4th Ed.,Example 2.2,Figure 2.11,page 391/6/20238MPJ/UNM CS452/Mgt 532 I.IntroductionGraphical Repres
12、entation:Physical LayoutlBCNN 4th Ed.,Example 2.6,Figure 2.15,page 501/6/20239MPJ/UNM CS452/Mgt 532 I.IntroductionGraphical Representation:Network ModellBCNN 4th Ed.,Example 2.8,Figure 2.18,page 541/6/202310MPJ/UNM CS452/Mgt 532 I.IntroductionGraphical Representation:“Black Box”lBCNN 4th Ed.,Figure
13、10.5,page 3671/6/202311MPJ/UNM CS452/Mgt 532 I.IntroductionGraphical Representation:Component RelationshiplBCNN 4th Ed.,Example 14.4,Figure 14.10,page536:Website configuration1/6/202312MPJ/UNM CS452/Mgt 532 I.IntroductionSimulation Study Representation(after Banks et al,Figure 1.3,Page 15)Problem Fo
14、rmulationSet Objectives and Project Plan(Re)Conceptualize Model&Collect DataTranslate ModelCan Model be Verified?NoCan Model be Validated?YesNoDOE-Design ExperimentsRuns and ReplicationsAnalysisResults Clear and Able to be Described?NoDocument,Report and RecommendYesYes1/6/202313MPJ/UNM CS452/Mgt 53
15、2 I.IntroductionSimulation Study1.Identify problem(s),improvement(s),and/or plan new capabilities2.Specify the system select boundaries,identify inputs,entities,attributes,events,activities,processes,and state variables-specify output(s)and their desired values3.Build a conceptual and operational mo
16、del of the system build a representation of inputs,entities,1/6/202314MPJ/UNM CS452/Mgt 532 I.IntroductionSimulation Study(cont.)4.Verify and Validate(as best you can)the operational model against existing system only partial model verification/validation may be possible for new systems5.Perform scr
17、eening experiment(s)to identify IVs with significant effect on desired output(s)proceed with only these IVs6.Select ranges of IVs which reduce variability to acceptable levels,if necessary(Critical Step!)7.Experiment with model to identify values of inputs which“optimize”output or“achieve”goal8.Buil
18、d system or prototype to test results of study1/6/202315MPJ/UNM CS452/Mgt 532 I.IntroductionSystem Description,Problem,Objectives,Project PlanlVerbal description/linguistic analysislIdentify problems and/or(re)design objectiveslIdentifying relevantEntitiesAttributesEventsActivities/processes,andstat
19、e variablesto address problem(s)and/or objectiveslDevelop project plan may follow STEPS FOR EXPERIMENTAL DESIGN in Schmidt and Launsby on pages I-26 and I-271/6/202316MPJ/UNM CS452/Mgt 532 I.IntroductionSimulation Model ComponentslEntities:named physical/conceptual objects(improper nouns used for UM
20、L classes,proper nouns for UML objects)Attributes:named characteristic or property(adjectives)Methods:named activities or operations the entity can perform(predicates=verb+direct/indirect object(s)lStates:named set of conditions,standings,circumstances,and positions describing an entity at a particu
21、lar time(adjectives,verbal nouns=gerunds)lProcesses:named groups of activitieslEvents:named noteworthy occurrences,often at the beginning or completion of one or more activities and/or processes1/6/202317MPJ/UNM CS452/Mgt 532 I.IntroductionIdentify VariableslOutput(dependent)variables whose values w
22、ill be the problem solution/design improvementOperational definitionsRange of valuesAppropriate output analysisTransient vs.steady stateStatistical tools(confidence intervals,t-tests,ANOVA,regression/model building)1/6/202318MPJ/UNM CS452/Mgt 532 I.IntroductionIdentify Variables(cont.)lFactors among
23、 whose combination of values will provide the problem solution of optimum designThese will be varied by the investigator according to some experimental design(DOE)Operational definitions,range of values,level values,potential interactions(for eventual assignment to DOE columns)Factor model:relates f
24、actors to output variables developed in modeling experiments1/6/202319MPJ/UNM CS452/Mgt 532 I.IntroductionIdentify Variables(cont.)lState variables whose change of values determine the eventslOther variables necessary for a complete modellIdentify stochastic variables and collect data to specify the
25、ir distributionsIf close to known mathematical distributions then identify their parametersElse use as empirical distributionslCollect data for constants these may have to be fitted from the data1/6/202320MPJ/UNM CS452/Mgt 532 I.Introduction(Re)Conceptualize Simulation Model and Collect DatalSimulat
26、ion model:relates all variables to output variableslRepresentation tools:natural or domain specific language/jargonmathematical notationcode(e.g.,Java,GPSS)and pseudo-code(primitive action,choice,iteration)flow chartsUMLPERT/CPM diagramspictorial imagesstoryboards/movieslBuild Simulation Model and t
27、he Simulation itself1/6/202321MPJ/UNM CS452/Mgt 532 I.IntroductionVerify and ValidatelVerify that calculations in implementation are correctlValidate the results against output known to be an accurate reflection of realityMay only be possible for parts of the model or highly restricted situationsIf
28、not make“reasonableness checks”1/6/202322MPJ/UNM CS452/Mgt 532 I.IntroductionDesign and Conduct Experimental RunslDo experimentsScreen:experimental runs(2-level?)to find the significant few factorsModel:further or new set of experimental runs(3 or 5 levels)to develop factor model equationsfit equati
29、ons by regressionOptimize:solve equations for optimum ormake experimental runs to drill down to best combinations of factorsCheck:local optimum(simulate all neighbors)1/6/202323MPJ/UNM CS452/Mgt 532 I.IntroductionSolutions/Design Identification and ReportlFrom simulation runs identify the solution t
30、o the problem and/or the optimum designlWrite ReportAbstract(may only be needed for research or archive reports)Executive Summary:non-technical problem statement,solution/design,justification(not usually in research reports)Technical Report:complete details so that entire project could be repeated b
31、y others including equations,code,distributions,run resultsTechnical Appendix1/6/202324MPJ/UNM CS452/Mgt 532 I.IntroductionSimulation ReportSee SimulationStudy&ReportOutline.doc for details of each section1.Abstract 2.Executive Summary3.Full Technical Reporta)Situation,Problems,Opportunities,Goals,a
32、nd Objectivesb)Backgroundc)System Specification1)Performance Measures2)Input Factors3)System Representation/Modeld)Project Activitiesa)Input Specification and Model Implementationb)Verification and Validationc)Experiments and Results of the Simulation Runse)Analysis and Resultsf)Conclusion and Recom
33、mendations4.Technical Appendix1/6/202325MPJ/UNM CS452/Mgt 532 I.IntroductionAssignments1.Choose one application from Banks 1.1 or your selection for a DESS project:write sections 3.a)-c)of the report(specify the entities&make a symbolic representation using flow charts,UML,or).This can be a group ex
34、ercise.2.Individual exercises,Banks 1.6a)Prepare a brief written report(include copy of papers if possible)andb)Prepare an even briefer set of slides for presentation to the class(unless the subject of your paper is particularly interesting you may not be asked to actually make the presentation in a
35、ny case the presentation will be informal)1/6/202326MPJ/UNM CS452/Mgt 532 I.IntroductionModel ClassificationlDoes system evolve over time?Static:one time period or steady stateDynamic:changes occur over time period of interestlHow often do we have to specify changes?Discrete Event:changes only occur
36、 at instances separated in timeContinuous Event:changes occur constantlylHow predictable is the system?Deterministic:we assume we can model the system as if we know all that needs to be known about the systemStochastic(Stochs):we know certain aspects of the system only as a probability distributionT
37、otally Unpredictable:cannot model1/6/202327MPJ/UNM CS452/Mgt 532 I.IntroductionHow Various Models are Studied*Course ContentsDeterministicStochasticStaticLogical/algebraic analysis*Monte Carlo MethodsDynamic:Discrete Event Systems(DES)Mechanistic and Algorithmic*Queuing Theory and Discrete Event SimulationDynamic:Continuous Event Systems(CS or CES)*Numerical Solution of Difference and/or Differential Equations(DEs)Stochastic DEs Advanced Topic 1/6/202328MPJ/UNM CS452/Mgt 532 I.Introduction