Walter Onkoba Ogega

SIMULATION

TERM PAPER

Presented

By

Walter Onkoba Ogega

wogega@hotmail.com <Nairobi, Kenya> Page | 1

Walter Onkoba Ogega

TABLE OF CONTENTS Page 1 Definition.. 2 Introduction.. 3 Use of models in simulation. 4 When to use simulation. 5 Types of simulation.. 6 How to perform simulation... 7 computer simulation.... 8 Role of computer in simulation... 9 Monte Carlo method.. 10 Monte Carlo sampling technique.. 11 Advantages of simulation... 12 Disadvantages of simulation.... 13 Reference 1 1 1 1 2 2 2 3 3 4 4 5 6

wogega@hotmail.com <Nairobi, Kenya> Page | 2

Walter Onkoba Ogega

Simulation

Definition. Simulation is a quantitative technique which describes a process by developing a model of that process and then conducting a series of organized trial and experiments to predict the behavior of the process through time often with the aid of a computer. Simulation can be used to solve problems in many areas such as inventory, quieng problems project management it is used when the number of assumption in modeling exercise is large so that many could be violated Simulation is not an analytical technique neither is it an optimization tool an experiment is run and with the result statistical inferences are drawn about the general characteristic of the population. In operations research the imitation is a computer model of the simulated reality. A flight simulator on a PC is a computer model simulation of some aspects of a flight: it shows on the screen, the controls, and what the "pilot" (the person who operates it) is supposed to see from the "cockpit" (his armchair). Why to use models? To fly a simulator is safer and cheaper than the real airplane. For precisely this reason models are used in industry, commerce, and the military. It is very costly, dangerous, or often impossible to make experiments with real systems (nuclear explosions). Simulation may be an effective alternative provided that the models are adequate descriptions of reality, and experimenting with them can save money, suffering and even time. When to use simulations Systems which change with time such as a gas station where cars come and go (called dynamic systems) and involve randomness (nobody can guess at exactly which time the next car should arrive at the station) are good candidates to simulation. Modeling some complex dynamic systems mathematically may require too many simplifications and the emerging models may not be valid. Simulation of the system may not require that many simplifying assumptions, making it one of the few tools available.
wogega@hotmail.com <Nairobi, Kenya> Page | 3

Walter Onkoba Ogega Other situations include, 1 2 3 4 When there are untenable or unrealistic assumptions When the system takes long to observe i.e. population or demographics issues time compression The danger of experimenting with the real world situations Difficult of observation of the real world systems e.g. space research and molecular particles research

Types of simulations: A. Discrete event simulations. This attempt to describe systems that are assumed to change instantaneously in response to certain discrete occurrences. Arrivals and departures of cars at a toll booth is an example of discrete events. B. Continuous. In some systems the state changes all the time, not just at time of some discrete events. For example water level in a reservoir with a given inflow and outflow may change all the time. In such cases continuous simulation is more appropriate, although discrete event simulation can serve as an approximation. How simulations are performed Simulations may be performed manually. More often, however, the system model is written either as a computer code or as some kind of input into simulator software. General steps in simulation 1 2 define the problem you require to solve identify the decision variables i.e. the unknowns i.e. for inventory management this could be order quantity and reorder level .For profit planning this could be demand levels, prices and costs specify values of the decision variables to be tasted and collect the relevant data formulate the model you intend to use Test the model by comparing its behavior with the actual problem environment ie run simulation trials

3 4 5

This process is repeated until the result is approximately reality as possible or until some other objective is achieved ie weekly profits is maximized or daily costs is minimized
wogega@hotmail.com <Nairobi, Kenya> Page | 4

Walter Onkoba Ogega Computer software for simulation Simulation may be carried out on a spreadsheet, by running a computer program written in some general language (such as C++), by running a computer program written in some special language for simulations, or by running specially built simulators with appropriate input. Simulation with spreadsheets is the most primitive form. Spreadsheets can be used for small simulations quite effectively. They are laborious and slow however. Their usefulness can be improved considerably by including macros and Visual Basic code. The use of macros will be introduced in this course. Simulation written in some general language. This is the most flexible method and according to some authors the most often chosen, too. This is probably the best method if the simulation is just one component of a larger system or when there is a considerable amount of data processing involved. The problem here is that writing a simulation from scratch may be a lengthy undertaking. However, with a good simulation library and a skeleton program the necessary investment can be reduced to minimal. Simulation written in some special language for simulations. There are many special languages for simulations. The disadvantage is that if the problem does not fall exactly in the category that these languages were designed for, it is very difficult, if not impossible, to write a suitable program. Special purpose simulators are the most inflexible programs: They work only for a narrow field and even there they cannot deal with all tasks, but only those for which they are destined. Role of computer in simulation 1 2 3 4 5 It generate random numbers It simulate thousands of trials It is extremely first accurate and reliable It has a huge storage capacity A computer simulate several combination of decision variables i.e. order quantity and reorder point in a matter of seconds Provide management wit reports which are used for decision making

Monte Carlo Method

wogega@hotmail.com <Nairobi, Kenya> Page | 5

Walter Onkoba Ogega The expression "Monte Carlo method" is actually very general. Monte Carlo (MC) methods are stochastic techniques--meaning they are based on the use of random numbers and probability statistics to investigate problems. You can find MC methods used in everything from economics to nuclear physics to regulating the flow of traffic. Of course the way they are applied varies widely from field to field, and there are dozens of subsets of MC even within a single field. But, strictly speaking, to call something a "Monte Carlo" experiment, all you need to do is use random numbers to examine some problem. The use of MC methods to model physical problems allows us to examine more complex systems than we could otherwise. Solving equations which describe the interactions between two atoms is fairly simple; solving the same equations for hundreds or thousands of atoms is impossible. With MC methods, a large system can be sampled in a number of random configurations, and that data can be used to describe the system as a whole. The first real use of a Monte Carlo calculation was probably during the Manhattan Project where very complex equations that could not be attacked with traditional methods had to be solved. The Monte Carlo technique is now used in virtually all areas of science and engineering where problems are too difficult or complex to be addressed with other methods. Some of the problems in the assignments will require the use of random numbers, hence, the Monte Carlo Method Monte Carlo sampling technique This is a way of allocating random numbers when a system containing elements or variables that exhibit chance in their behavior. The basisof his experimentation on the chance or probabilistic elements through sampling Steps to perform Monte Carlo sampling technique 1 2 3 Set a probability distribution for the relevant random variables Build cumulative probability distribution for each variable in step one. Establish the intervals of random numbers for each variable and allocate random number range. Obtain the random numbers from one of the following ie a random number tables, calculators or from computers Perform the simulation. Simulation Pros and Cons Advantages of simulation.
wogega@hotmail.com <Nairobi, Kenya> Page | 6

Walter Onkoba Ogega 1 Cost of Designing, building, testing, redesigning, rebuilding, retesting,... for anything can be an expensive project. Simulations take the building/rebuilding phase out of the loop by using the model already created in the design phase. Most of the time the simulation testing is cheaper and faster than performing the multiple tests of the design each time. Simulation is well suited to problem that are difficult or impossible to solve analytically and where many assumption are not realistic eg inventory control, quieng problem capital budgeting Simulation allows analyst to experiment with system behavior in controlled environment instead of real life setting which can be risky Simulation enables a decision maker to compress time in order to evaluate long-term effects of various alternatives Simulation can serve as a mode of training decision maker by enabling them to observe the behavior of a system under different condition without experimenting with the actual system Level of detail simulation can give you results that are not experimentally measurable with our current level of technology. Results such as surface interactions on an atomic level, flow at the exit of a micro electric thruster, or molecular flow inside of a star are not measurable by any current devices. A simulation can give these results when problems such as it are too small to measure, and is result is skewed

Disadvantages of simulation 1 Simulation is not precise it is not an optimization process and does not necessarily yield an optimal answer but merely provides asset off the system responses to different operating conditions in many times this lack decision i is difficult to measure A good simulation model may be expensive in terms of design personnel and consultancy computing devices particularly appropriate software Each simulation model is unique its solution and inferences are not usually transferable to other problem this further increase the cost of simulation Simulation can take time in terms of data collection, design of the model this could delay decision making which is costly Simulation errors. Any incorrect key stroke has the potential to alter the results of the simulation and give you the wrong results. Also usually we are programming using theories of the way things work not laws and theories are not often 100% correct. Provided that you can get your simulation to give

wogega@hotmail.com <Nairobi, Kenya> Page | 7

Walter Onkoba Ogega you accurate results you must first run a base line to prove that it works. In order for the simulation to be accepted in the general community you have to take experimental results and simulate them. If the two data sets compare, then any simulation you do of your own design will have some credibility. 7 Many people do not consider what they do engineering unless they can see, hear, feel, and taste the project. If you are designing a light saber a typical engineer needs to be able to hold the light saber in their hand in order to consider the project worth his or her time. If you are capable of moving your craft into the virtual world of simulations you are no longer restricted by little things like reality. If you want to design a light saber in the virtual world it is not a problem, but in reality that is another matter all together. The virtual world is difficult to get use to the first time you use it for design.

wogega@hotmail.com <Nairobi, Kenya> Page | 8

Walter Onkoba Ogega

REFERENCE Durry Collins Management and cost Accounting, international Thomson press 6th Edition,2004 Hirisch, M,L Advanced management Accounting , 2nd Edition, South West Publishing co , 1994 Dominiak G.F. and Lounderback J.G. Management Accounting, 5th Edition, Kent Publishing Co Boston. Quantitative techniques by T. lucey Operation research by Thierauf Mr. Micheal Chirchir execrative Director / senior lecturer Management Accounting Vission Institute of Professionals class reading Material Mr Cliff Otieno execrative Director / senior lecturer Management Accounting Pinnacle school of business class reading Material

wogega@hotmail.com <Nairobi, Kenya> Page | 9