Anda di halaman 1dari 20

System Simulation

Modeling and Analysis

Jurusan Manajemen Logistik – STIMLOG


BANDUNG – 2018
References

1. Banks, J., J.S. Carson II, B.L. Nelson, & D.M. Nicol:
Discrete-Event System Simulation, 4th ed., Prentice-
Hall (2005).
2. Law, A.M., & W.D. Kelton: Simulation Modeling and
Analysis, 3rd ed., McGraw-Hill (2000).
3. Kelton, W.D., R.P. Sadowski, & D.T. Sturrock:
Simulation with Arena, 3rd ed., McGraw-Hill (2004).
System and model

MODEL

SYSTEM
Model types

 Based on the purpose of the model:


– Descriptive model
– Predictive model
– Prescriptive (normative) model

 Based on the representation method:


– Iconic model
– Analog model
– Symbolic model
What is simulation?

•the imitation of the operation of a real-world process or


system over time. [Ref.1]
•a computer model to evaluate a model numerically,
and data are gathered in order to estimate the desired
true characteristics of the model. [Ref.2]
•a broad collection of methods and applications to mimic
the behavior of real systems, usually on a computer with
appropriate software. [Ref.3]
Simulation model

 Simulation model is a descriptive/predictive model.


 If simulation model is integrated with “best” solution
searching procedure, then it will become normative
model.
 Alternatives for “best” solution searching procedure:
– Trial and error with intuition
– Design of experiment
– Metaheuristic optimal searching procedure
Ways to study system
Reason to use simulation model

 It’s way too costly to experiment with the real


system.
 The real system itself doesn’t exist.
 System complexity that cannot be solved by
analytical model.
Reason to use simulation model
(Example): Queuing System

Simple queuing system, e.g.


- Single queuing line (even with
multiple servers)
- No jockeying
- No balking, no reneging
- Queuing network without complex
feedback Use Queuing
- Poisson process arrival and Theory!!
service
(No need to use
simulation)
Reason to use simulation model
(Example): Queuing System

Complex queuing system, e.g.


- Multiple servers with multiple
queuing lines
- Jockeying phenomena
- Customers balking and/or reneging
- Queuing network with complex
rules and feedback
- Complex servers schedule and
downtimes Use Simulation!!
Simulation as an industrial engineering tool

 Simulation has become the most widely


used tool among industrial and systems
engineers. [Turner, et al: Introduction to
Industrial and Systems Engineering, 1993]
 Simulation is one of the most widely used
operations-research and management-
science techniques, if not the most widely
used. [Ref.2]
Areas of application
 Designing and analyzing manufacturing systems
 Evaluating military weapons systems or their logistics
requirements
 Determining hardware requirements or protocols for
communications networks
 Determining hardware and software requirements for a
computer system
 Designing and operating transportation systems such as
airports, freeways, ports, and subways
 Evaluating designs for service organizations such as call
centers, fast-food restaurants, hospitals, and post offices
 Reengineering of business processes
 Determining ordering policies for an inventory system
 Analyzing financial or economic systems
Tools for simulation modeling

 Manual (simulation by-hand)


 Spreadsheet (e.g.: Excel)
 General-purpose programming language: (e.g.:
Visual Basic, C/C++, Java, C#)
 Simulation software:
– Simulation language (e.g.: SIMAN, GPSS,
SLAM)
– Simulation package (e.g.: Arena, AweSim/Visual
SLAM, ProModel, Powersim)
Simulation tools for this course

 Microsoft Excel with Visual Basic for


Application (VBA) macro
 Rockwell Software’s Arena
Classification of Simulation

 Based on time role in the model: Static vs.


Dynamic
 Based on probabilistic (i.e., random)
contents: Deterministic vs. Stochastic
(Probabilistic)
 Based on the state of the system: Discrete
vs. Continuous (see the following explanation of the
state of a system)
State of a System

 State of a system: collection of variables necessary


to describe a system at a particular time, relative to
the objectives of a study.
 E.g.: in a study of a bank, possible state variables:
– the number of busy tellers
– the number of customers in the bank
 System category based on the system state:
– Discrete system vs. Continuous system
State of a System
Discrete-Event Simulation

 This course will introduce the fundamental


concept of discrete-event simulation:
– Discrete system state
– Probabilistic elements

 Discrete event simulation is frequently used


in the modeling, analysis, and design of
manufacturing systems and service systems.
Other popular simulation term

 Monte Carlo simulation: a static simulation; utilizing


random-number to solve deterministic or probabilistic
system.
 System dynamics simulation: a continuous
simulation model (all state variables are assumed or
modeled as continuous), most widely used to study
behavior of complex system where feedbacks occur
among the components.
 Agent-based modeling and simulation: a relatively
new approach in simulation modeling, where the
system comprises many interacting entities by some
complex rules of interaction
Organization for Simulation Expertise
and Practicioners

 Society on Modeling and Simulation


International (SCS, formerly Society for
Computer Simulation)
 Association for Computing
Machinery/Special Interest Group on
Simulation (ACM/SIGSIM)

Anda mungkin juga menyukai