Introduction to Simulation Methods PowerPoint Presentation, PPT - DocSlides

Introduction to Simulation Methods

Professor Stewart Robinson

Stewart Robinson

Loughborough University

1

Session Outline

What is simulation?

Why use simulation?Four simulation approaches

Stewart Robinson

Loughborough University

2

Stewart Robinson

Loughborough University

3

How did British Airways Decide on the Design of Terminal 5?

How many check-in desks?

How many departure gates?

Configuration of security screening

Design of baggage handling system

Size of passport control area?

Flight schedule capacity

Workforce rosters

Terminal 5 Simulation

Stewart Robinson

Loughborough University

4

Source: Beck, A. (2011). Journal of Simulation 5, 69–76

Stewart Robinson

Loughborough University

5

What is Simulation?

Experimentation with a simplified imitation (on a computer) of a ... system as it progresses through time, for the purpose of better understanding and/or improving that system.

(Robinson,

2014

)

Simulation is: an

imitation

of a system

Simulation video

Stewart Robinson

Loughborough University

6

What is Simulation?

A simulation model enables a manager to experiment with alternative courses of action, the simulation providing predictions about the likely outcome. As a result, the manager obtains a better understanding of reality and is able to identify ‘good’ courses of action.

Simulation

model

Inputs

Outputs

Experimentation

Examples of SimulationFord Motor Company

. Simulation was widely used to aid the planning and design of their Zetec engine plants in South Wales. These represented an investment of $750m.

The simulations helped improve output by around 30%.

Stewart Robinson

Loughborough University

7

Examples of SimulationEmptying a waste pond and processing the waste to make it safe.

Achievement of waste removal to a specified timeline.

Nuclear Industry

Stewart Robinson

Loughborough University

8

Examples of SimulationOutpatients Department Rebuild

: investigation of number of consulting rooms required.

Stewart Robinson

Loughborough University

9

Why Use Simulation?Because systems are subject to

variability, are interconnected

and complex.1. Variability:Predictable variability e.g. shift changeovers, preventative maintenanceUnpredictable variability e.g. customer arrivals, breakdown

Stewart Robinson

Loughborough University

10

Why Use Simulation?2. Interconnectedness

Variability does not occur in isolation, but is connected to other sources of variability.

Service 1Service 2Service 3

CustomerarrivalsTime: 10 minsTime: 9 mins

Time: 9 mins

Time: 9 mins

What is the mean time a customer spends in the system?

Stewart Robinson

Loughborough University

11

Why Use Simulation?3. Complexity

Combinatorial complexity: the number of combinations of system components that are possible.

20 interconnections

2 interconnections

Combinatorial complexity

is related to the size of a system.

Stewart Robinson

Loughborough University

12

Why Use Simulation?3. Complexity

Dynamic complexity: related to the interaction of components in a system over time.

It is normally associated with feedback e.g. a kanban system:

M1B1Parts

Information

It is not necessarily related to the size of a system.

Stewart Robinson

Loughborough University

13

Simulation Approaches

Monte Carlo Simulation (not strictly business dynamics)

Stewart Robinson

Loughborough University

14

f (a, b, c)

Random sampling process (hence ‘Monte Carlo’)

Not always dynamic (time-based) models

Typical used in finance applications for portfolio management

Simulation Approaches

Discrete-Event Simulation

Stewart Robinson

Loughborough University

15

World represented as Queues and Activities

Variable time step to represent changes in state of the system

Used for modelling queuing systems e.g. airports, banks, manufacturing plant, call centres, ports, computer systems,...

Simulation Approaches

Continuous Simulation (e.g. system dynamics)

Stewart Robinson

Loughborough University

16

World represented by Stocks and Flows

Constant (small) time step (

Δ

t

) to approximate continuous time

Typical used in business strategy/policy and more general continuous simulation in science and engineering

Simulation Approaches

Agent Based Simulation

Stewart Robinson

Loughborough University

17

World represented by (intelligent) interacting agents

Constant time step (

Δ

t

) but can be discrete-event

Used for exploring emergent behaviour in organisations as well as other

contexts: e

vacuation

, traffic

flow, stock markets, diffusion

of

innovation, spread of infectious diseases

Boids simulation

Reading

Discrete-Event Simulation 

Robinson, S. (2014). Simulation: The Practice of Model Development and Use, 2nd ed. Palgrave, London. Law, A.M. (2014). Simulation Modeling and Analysis, 5th ed. McGraw-Hill, New York.

  System Dynamics Morecroft, J. (2007). Strategic Modelling and Business Dynamics: A Feedback Systems Approach. Wiley, Chichester. Sterman, J.D. (2000).

Business Dynamics: Systems Thinking and

Modeling

for a Complex World

. McGraw-Hill, New York.

Stewart Robinson

Loughborough University

18

Reading

 Agent Based Modelling

 Robertson, D.A. and Caldart, A.A. (2009). The Dynamics of Strategy: Mastering Strategic Landscapes of the Firm. Oxford University Press. Axelrod, R. (1997). The Complexity of Cooperation: Agent-Based Models of Competition and Collaboration

. Princeton University Press. North, M.J. and Macal, C.M. (2007). Managing Business Complexity: Discovering Strategic Solutions with Agent-Based Modeling and Simulation. Oxford University Press.

Stewart Robinson

Loughborough University

19