Intermediate Modeling and

Steady-State Statistical
Analysis

Chapter 7

Last revision August 26, 2006

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 1 of 37
What We’ll Do ...
• Model 7-1: A small manufacturing system
 Entity-dependent Sequences
 Data requirements and availability
 Verification (debugging)
• Statistical analysis of steady-state simulations
 Warmup and run length
 Truncated replications
 Batching
 Other methods and goals

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 2 of 37
Model 7-1:
A Small Manufacturing System

• Part arrivals, four cells, part departures

• Cells 1, 2, and 4: single machine each
• Cell 3: two machines — newer one 20% faster
 Need: way to model non-identical resource units
• Circular layout of cells
• Parts enter at left, exit at right, travel only
clockwise, all transfer times = 2 min. (realistic?)
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 3 of 37
A Small Manufacturing System (cont’d.)
• Three separate part types
 Interarrivals (all types merged) ~ expo(13) minutes
 26% type 1, 48% type 2, 26% type 3
• Different part types follow different routes, have
different (triangular) processing times:

At Cell 3,
parameters
are for slow
machine

• Observe utilizations, time/number in queues, cycle

times (times in system) by part type
• Run for 32 hours
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 4 of 37
New Arena Concepts
• Non-identical machines at Cell 3
• Different entity types follow different process
plans
 Previous models – all entities went through same sequence
of stations, maybe with Decides for branching
 Now, need process plan with automatic routing by entity
type – different Sequence assigned to each entity (like an
attribute), and entity follows its own sequence
 Won’t use direct Connect or Routes … instead, tell entities
departing from modules to follow their own Sequence
 Arena internally keeps track of where entity is, where it will
go next

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 5 of 37
The Modeling Approach
• Usually there are many ways to build a (correct)
Arena model
 And also many ways to do so incorrectly …
• Important to think about data structures
 What data are available?
 How will they be stored in the model?
• For this model …
 Use Sequence for part transfer (described below)
 As part of Sequence definition, can define Attributes
– Do for processing times at all cells but Cell 1
 Use an Expression for processing times at Cell 1
 Use Variables for new-machine speedup at Cell 3, part
transfer times
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 6 of 37
Sequence Data Module
• Advanced Transfer panel
• Double-click for new row for each process plan
 Name for each Sequence
 Open Steps column for subdialog
– Define ordered sequence of Stations to be visited in the Sequence
… must have Station Names already defined
– Double-click to add a new Station to the bottom of the Sequence list;
right-click to insert/delete a row
– Name for each step
– Possible Assignments of Attribute, Variable, Pictures, etc. at each
station in the Sequence … this is done before transferring the entity
to this step in the sequence
– In this model, Attribute assignment used to attach Process Time
Attribute to entity for the next Cell (except for Cell 1)
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 7 of 37
Sequence Data Module (cont’d.)
• Assign Sequence Name to entities that follow it
• In Route modules, select Sequence as Destination
Type (rather than Station)
 Departing entity looks in its own sequence to know where to
go next
• Arena tracks Sequence-following entities via
automatic attributes
 Sequence name, NS (or Entity.Sequence)
 Station (where entity is or is going to), M (or Entity.Station)
 JobStep along the sequence, IS (or Entity.JobStep)
• Normally, entity is assigned a Sequence, travels
its route, then exits
 Can interrupt this sequence, jump forward/backward (tricky)
• Remember to define the “exit” station
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 8 of 37
Expression Data Module
• Advanced Process panel
• Use for processing times at Cell 1
 Could have done in Sequences, as for other Cells … done
this way mostly to illustrate its use
• Three different part types at Cell 1, so use a
vector-valued Expression with three rows
 Name for the expression, Cell 1 Times
 Rows, 3
 Expression Values subdialog
– Cell 1 processing times for the three part types
– Order matters, since index is part type … will reference as
Cell 1 Times(Part Index) in model
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 9 of 37
Variable Data Module
• Basic Process panel
• Factor variable
 Speed factor at Cell 3 – need a two-row vector
– Assume new (faster) machine is #1, old (slower) machine is #2
– Set to 0.8 for index 1; set to 1.0 for index 2
• Transfer Time variable
 Holds transfer-time constant of 2 minutes between stations
 Just a scalar, not a vector or matrix
 Used for model generality – if all transfer times changed,
this makes it easy to implement this change
• These are the Initial Values of variables … any
entity can change them
 But they’re constant in this model
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 10 of 37
Set Data Module
• Basic Process panel
• Define three sets
 Resource set, Cell 3 Machines
– For new and old machine (in that order) at Cell 3
– Resource Names – could have already defined them in Resource
data module, or can define them here
 Entity Picture set, Part Pictures
– To attach to entities once their part type is determined
– Picture Names – could have already defined them elsewhere
(Edit > Entity Pictures), or can define them here
 Entity Type set, Entity Types
– To attach to entities once their part type is determined
– Entity Types – define them here
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 11 of 37
Advanced Set Data Module
• On Advanced Process panel
• Needed since Set data module does not have
“Other” category for Type
 Need to form a set of Sequences to attach the right one to
arriving entities once their part type is determined
 Define Name of set to be Part Sequences
 Set Type is “Other”
 Members subdialog – Add rows, type in names in “Other”
column (have to remember or look up the Sequence
names)

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 12 of 37
Run > Setup and Edit > Entity Pictures
• Run > Setup Dialog
 Replication Parameters Tab
– Replication Length = 32 Hours
– 24 Hours/Day
– Base Time Units = Minutes
• Edit > Entity Pictures
 Create three custom pictures – Picture.Part 1,
Picture.Part 2, Picture.Part 3
 Copy blue, red, and green ball pictures
 Rename them
 Picture Editor to put white numbers inside via Text object

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 13 of 37
Part Arrivals
• Create module for arrival of one part
 One-at-a-time, Time Between Arrivals is exponential with
mean 13 minutes
 Don’t know the part type yet …
• Assign module for part attributes
 Part Index = draw from DISC probability distribution
– Pairs cumulative probability, value
– Here, we need to assign Part Index first, as it’s used below
 Entity.Sequence = Part Sequences(Part Index)
– Part Index attribute already assigned … order matters
– Index into Part Sequences (Advanced) Set
 Entity.Type = Entity Types(Part Index)
 Entity.Picture = Part Picture(Part Index)

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 14 of 37
Release Arriving Entity into System
• Use previously defined Sequences, assigned to
entity via (Advanced) Set of Sequences
• Send arriving entity through a Station module to
define its current station location
 Station Name = Order Release
 Other five station names already defined via Sequences
• Route module to start it on its way
 Route Time = Transfer Time (a Variable previously
defined) Minutes
 Destination Type = By Sequence
– Arena will direct this entity according to its own sequence
– It just arrived so Arena initializes its JobStep attribute
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 15 of 37
Logic for Cell 1
• Station module to define the station location
 Station Name = Cell 1, on pull-down list for stations since
it was previously defined in Sequences
• Cell 1 Process module
 Action = Seize Delay Release
 Resources subdialog
– Type = Resource (not Set … yet)
– Resource Name = Cell 1 Machine, Quantity to seize = 1
 Delay Type = Expression
– Expression = Cell 1 Times(Part Index) Minutes, using the
previously-defined Expression Cell 1 Times
• Route module from Cell 1
 Destination Type = By Sequence
 Station already defined (on incoming side)
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 16 of 37
Logic for Cells 2 and 4
• Incoming Station module – similar to Cell 1
 Except for names of Module and Station
• Process module
 Action, Resources, Delay Type – similar to Cell 1
 Expression for Delay time = Process Time
– Attribute defined in Sequence module for each job type at this point
in its sequence for Cells 2 and 4
– Note that Part Type 2 visits Cell 2 twice in its sequence, with
different delay-time distributions … this data structure is general
enough to handle this
• Outgoing Route module – similar to Cell 1
 Except for name of Module

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 17 of 37
Logic for Cell 3
• Station, Route modules – similar to Cells 1, 2, 4
• Process module
 Action, Delay Type – similar to Cells 1, 2, 4
 Resources subdialog
– Type = Set, Set Name = Cell 3 Machines
– Selection Rule for set = Cyclical
Maybe Preferred Order would have been better???
– Save Attribute = Machine Index (will be 1 or 2)
 Expression for Delay time =
Process Time * Factor(Machine Index)
to multiply by 0.8 if entity gets the new machine (#1), using
the preciously-defined vector variable Factor
 See book for alternative (cute) expression that avoids the
need for the vector variable Factor
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 18 of 37
Digression: Data Structures
• Why an Expression for processing times at Cell 1
rather than entity Attribute assigned in Sequences
as for the other cells?
 Frank answer: Just to show the use of Expression
 Could easily have treated Cell 1 like the others
• Conversely, could have used Expression for
processing times at Cells 3 and 4
 But there would be a problem with Cell 2
– Part 2 visits it twice with different processing-time distributions, so
would have to indicate which visit somehow
 Moreover, this is a very small model
• Moral: Think carefully about data structure!
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 19 of 37
Logic for Exiting the System
• Station module to define this location
 Station Name = Exit System
• Dispose module
 Record Entity Statistics box is checked
 Will generate one of the outputs we want, cycle time (time in
system) separated out by part type, since they map onto the
entity types for this model
 So don’t need separate Record modules here to collect
cycle times
• Model would run at this point, give correct output
results … but develop animation to show queues,
resources, and movement …
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 20 of 37
Animation
• Pull animation away from logic, data modules
• Move, resize, reorient queues for realism
• Animate Routes (all movement possibilities)
 Thick “bundles” of routes — Shift key, Snap to Grid
 Heed clockwise direction
 Draw lines to define route “lanes”
• Import, modify AutoCAD .dxf file for backdrop
and resource pictures (see text)
• Fine-tune resource pictures
 Layers for seize point
• In animation, note that entities travel at very
different rates, pass each other … realistic???
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 21 of 37
Verification
• System  Model  “Code”
• Validation: Is Model = System?
• Verification: Is “Code” = Model? (debugging)
• The Truth: Can probably never completely verify,
especially for large models

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 22 of 37
Verification (cont’d.)
• Some techniques to attempt verification
 Eliminate error messages (obviously)
 Single entity release, Step through logic
– Set Max Batches = 1 in Arrive
– Replace part-type distribution with a constant
 “Stress” model under extreme conditions
 Performance estimation — like slide-rule decimal
placement
 Look at generated SIMAN .mod and .exp files
– Run > SIMAN > View

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 23 of 37
Statistical Analysis of Output from
Steady-State Simulations
• Recall: Difference between terminating, steady-
state simulations
 Which is appropriate depends on goal of study, and not so
much on the model structure
– Most models could be used for terminating or steady-state analysis
• Now, assume steady-state is desired
 Be sure this is so, since running and analysis is a lot harder
than for terminating simulations
• Naturally, simulation run lengths can be long
 Opportunity for different internal computation order
 Can change numerical results
 Underscores need for statistical analysis of output
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 24 of 37
Warm Up and Run Length
• Most models start empty and idle
 Empty: No entities are present at time 0
 Idle: All resources are idle at time 0
 In a terminating simulation this is OK if realistic
 In a steady-state simulation, though, this can bias the
output for a while after startup
– Bias can go either way
– Usually downward (results are biased low) in queueing-type models
that eventually get congested
– Depending on model, parameters, and run length, the bias can be
very severe

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 25 of 37
Warm Up and Run Length (cont’d.)
• Remedies for initialization bias
 Better starting state, more typical of steady state
– Throw some entities around the model
– Can be inconvenient to do this in the model
– How do you know how many to throw and where?
This is what you’re trying to estimate in the first place!
 Make the run so long that bias is overwhelmed
– Might work if initial bias is weak or dissipates quickly
 Let model warm up, still starting empty and idle
– Run > Setup > Replication Parameters: Warm-up Period
Time units!
– “Clears” all statistics at that point for summary report, any Outputs-
type saved data from Statistic module of results across replications

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 26 of 37
Warm Up and Run Length (cont’d.)
• Warm-up and run length times?
 Most practical idea: preliminary runs, plots
 Simply “eyeball” them
 Be careful about variability — make multiple replications,
superimpose plots
 Also, be careful to note “explosions”
• Possibility – different Warm-up Periods for
different output processes
 To be conservative, take the max
 Must specify a single Warm-up Period for the whole model

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 27 of 37
Warm Up and Run Length (cont’d.)
• Create a single overall output performance
measure for Model 7-1 … modify it into Model 7-2
 Measure is time-average total number of parts in system
 Statistic module
– Time-Persistent type, Name and Report Label Total WIP
– Expression (via Expression Builder … details in book)
EntitiesWIP(Part 1) + EntitiesWIP(Part 2) + EntitiesWIP(Part 3)
– Output File Total WIP History.dat to save within-run data
Animated plots disappear, can’t overlay plots from multiple
replications … will use Output Analyzer to plot the saved data
 Speed up the run
– Check Run > Run Control > Batch Run (No Animation)
– Uncheck boxes in Run > Setup > Project Parameters
– Lengthen Replications to 5 days, do 10 Replications

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 28 of 37
Warm Up and Run Length (cont’d.)
• In Output Analyzer
 New data group, Add the file Total WIP History.dat
 Graph > Plot or
 Add Total WIP History.dat, Replications = All, enter
Title, axis labels

 No apparent explosion
 Warm-up about 2000 min.; round up to 2 days (2880 min.)
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 29 of 37
Truncated Replications
• If you can identify appropriate warm-up and run-
length times, just make replications as for
terminating simulations
 Only difference: Specify Warm-up Period in
Run > Setup > Replication Parameters
 Proceed with confidence intervals, comparisons, all
statistical analysis as in terminating case
• Model 7-3: modify Model 7-2
 Warm-Up period = 2 Days
 Stick with (total) replication length of 5 Days
 Stick with 10 replications
 Delete Output File in Statistic module
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 30 of 37
Truncated Replications (cont’d.)
• Get cross-replications 95% confidence-interval
Half Widths in Reports
 For average Total WIP, got 16.39  6.51
 Without the Warm-up, this was 15.35  4.42
 To sharpen the comparison of the effect of the Warm-up,
did 100 (rather than 10) replications with and without it:
– With Warm-up: 15.45  1.21
– Without Warm-up: 14.42  0.88
 Half Widths with Warm-up are larger since each replication
is based on the last 3 days, not all 5 days
• Smaller confidence intervals? Have a choice:
 More replications, same length
 Same number of replications, each one longer
– This might be the safer choice to guard against initialization bias
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 31 of 37
Batching in a Single Run
• If model warms up very slowly, truncated
replications can be costly
 Have to “pay” warm-up on each replication
• Alternative: Just one R E A L L Y long run
 Only have to “pay” warm-up once
 Problem: Have only one “replication” and you need more
than that to form a variance estimate (the basic quantity
needed for statistical analysis)
– Big no-no: Use the individual points within the run as “data” for
variance estimate
– Usually correlated (not indep.), variance estimate biased

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 32 of 37
Batching in a Single Run (cont’d.)
• Break each output record from the run into a few
large batches
 Tally (discrete-time) outputs: Observation-based
 Time-Persistent (continuous-time): Time-based
• Take averages over batches as “basic” statistics
for estimation: Batch means
 Tally outputs: Simple arithmetic averages
 Time-Persistent: Continuous-time averages
• Treat batch means as IID
 Key: batch size must be big enough for low correlation
between successive batches (details in text)
 Still might want to truncate (once, time-based)
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 33 of 37
Batching in a Single Run (cont’d.)
• Modify Model 7-3 into Model 7-4
 One replication of 50 days (about the same effort as 10
replications of 5 days each)
 A single 2-day Warm-up Period
 Statistic module, save WIP data once again for plot
How to choose batch size?

Equivalently, how to
choose the number of
batches for a fixed run
length?

Want batches big enough

so that batch means
appear uncorrelated.

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 34 of 37
Batching in a Single Run (cont’d.)
• Arena attempts to form 95% batch-means
confidence intervals on steady-state output
measures from within the single replication
 “Half Width” column in reports from one replication
– In Category Overview report if you just have one replication
– In Category by Replication report if you have multiple replications
 Uses internal rules for batch sizes (details in text)
 Won’t report anything if your run is not long enough
– “(Insufficient)” if you don’t have the minimum amount of data Arena
requires even to form a c.i.
– “(Correlated)” if you don’t have enough data to form nearly-
uncorrelated batch means, required to be valid
 If you’re doing a terminating simulation, you should be doing
multiple replications, in which case Arena reports cross-
replication half widths, not batch-means half widths
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 35 of 37
Batching in a Single Run (cont’d.)
• Results from Model 7-4:
 Category Overview report, average total WIP: 13.64  1.38
 Half Width considerably smaller than for truncated
replications (10 replications, 5 days each, 2-day Warm-ups)
– Here we spend only a total of 2 days warming up, and with
truncated replications we spent 10  2 = 20 days warming up
• Can check batch-means half widths during run
 Arena variables THALF(Tally ID), DHALF(Dstat ID)
• Can decide on your own batch sizes, form batch
means and c.i.’s “by hand” with Output Analyzer
 Why? Use in statistical comparison procedures
 More information in book
Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 36 of 37
What To Do?
• Several approaches, methods for steady-state
statistical analysis … many more exist
• Opinion:
 Avoid steady-state simulation … look at goal of project
 If you really do want steady-state
– First try Warm-up, truncated replications
– If model warms up slowly, making truncated replications inefficient,
consider Arena’s batch-means methods in a single long run with a
single Warm-up Period at its beginning … can’t use statistical
methods in PAN or OptQuest, though
• Other methods, goals in steady-state statistical
analysis – references in text

Simulation with Arena, 4th ed. Chapter 7 – Intermediate Modeling & Steady-State Stat. Slide 37 of 37