You are on page 1of 15

SECOND REVIEW REPORT

MONTE CARLO SIMULATION Monte Carlo methods are a class of computational algorithms that rely on repeated random sampling to compute their results. Monte Carlo methods are often used in simulating physical and mathematical systems. Because of their reliance on repeated computation of random or pseudo-random numbers, these methods are most suited to calculation by a computer and tend to be used when it is infeasible or impossible to compute an exact result with a deterministic algorithm Monte Carlo simulation methods are especially useful in studying systems with a large number of coupled degrees of freedom, such as fluids, disordered materials, strongly coupled solids, and cellular structures (see cellular Potts model). More broadly, Monte Carlo methods are useful for modeling phenomena with significant uncertainty in inputs, such as the calculation of risk in business. These methods are also widely used in mathematics: a classic use is for the evaluation of definite integrals, particularly multidimensional integrals with complicated boundary conditions. It is a widely successful method in risk analysis when compared with alternative methods or human intuition. When Monte Carlo simulations have been applied in space exploration and oil exploration, actual observations of failures, cost overruns and schedule overruns are routinely better predicted by the simulations than by human intuition or alternative "soft" methods. There is no single Monte Carlo method; instead, the term describes a large and widelyused class of approaches. However, these approaches tend to follow a particular pattern: 1. Define a domain of possible inputs. 2. Generate inputs randomly from the domain using a certain specified probability distribution. 3. Perform a deterministic computation using the inputs. 4. Aggregate the results of the individual computations into the final result.

An approximation will also be poor if only a few grains are randomly dropped into the whole square.For example. the ratio of the area of an inscribed circle to that of the surrounding square is π / 4. If grains are purposefully dropped into only. From plane geometry. the approximation of π. we aggregate the results into our final result. and so our approximation will be poor. the objects should fall in the areas in approximately the same ratio. the approximation of π will become more accurate both as the grains are dropped more uniformly and as more are dropped. we define a domain of inputs: in this case. for example. two other common properties of Monte Carlo methods: the computation's reliance on good random numbers. they will not be uniformly distributed. Since the two areas are in the ratio π / 4. and its slow convergence to a better approximation as more data points are sampled. also. Thus. Notice how the π approximation follows the general pattern of Monte Carlo algorithms. Note. then perform a computation on each input (test whether it falls within the circle). then inscribe a circle within it. Draw a square on the ground. Uniformly scatter some objects of uniform size throughout the square. At the end. the center of the circle. For example. Multiplying the result by 4 will then yield an approximation for π itself. grains of rice or sand. Thus. 2. Next. we generate inputs randomly (scatter individual grains within the square). the value of π can be approximated using a Monte Carlo method: 1. . it's the square which circumscribes our circle. 3. First. counting the number of objects in the circle and dividing by the total number of objects in the square will yield an approximation for π / 4.

a little word about uncertainty propagation: The Monte Carlo method is just one of many methods for analyzing uncertainty propagation. and confidence intervals. we used simple uniform random numbers as the inputs to the model. The data generated from the simulation can be represented as probability distributions (or histograms) or converted to error bars. By using random inputs. . performance. you are essentially turning the deterministic model into a stochastic model. lack of knowledge. Monte Carlo simulation is categorized as a sampling method because the inputs are randomly generated from probability distributions to simulate the process of sampling from an actual population. or error affects the sensitivity. a uniform distribution is not the only way to represent uncertainty. Monte Carlo simulation is a method for iteratively evaluating a deterministic model using sets of random numbers as inputs. a task which in the past was only practical using super computers. or reliability of the system that is being modeled. So. we try to choose a distribution for the inputs that most closely matches data we already have. or best represents our current state of knowledge. However. In Example 2. where the goal is to determine how random variation. Before describing the steps of the general MC simulation in detail.000 evaluations of the model. (See Figure 2). Example 2 demonstrates this concept with a very simple problem. nonlinear. tolerance zones. A simulation can typically involve over 10. This method is often used when the model is complex.Figure 1: A parametric deterministic model maps a set of input variables to a set of output variables. reliability predictions. or involves more than just a couple uncertain parameters.

etc. All we need to do is follow the five simple steps listed below: Step 1: Create a parametric model..) If you have made it this far.. . and can be easily implemented in Excel for simple models. Step 2: Generate a set of random inputs.. xq). (The basic principle behind Monte Carlo simulation. summary statistics. y = f(x1.. confidence intervals. Step 5: Analyze the results using histograms. Step 3: Evaluate the model and store the results as yi. Step 4: Repeat steps 2 and 3 for i = 1 to n. congratulations! Now for the fun part! The steps in Monte Carlo simulation corresponding to the uncertainty propagation shown in Figure 2 are fairly simple.Uncertainty Propagation Figure 2: Schematic showing the principal of stochastic uncertainty propagation.. . xi1. xi2. xiq. . x2..

animation. etc.Some Advantages of Simulation • Often the only type of model possible for complex systems – • Analytical models frequently infeasible Process of building simulation can clarify understanding of real system – Sometimes more useful than actual application of final simulation • Allows for sensitivity analysis and optimization of real system without need to operate real system • • Can maintain better control over experimental conditions than real system Time compression/expansion: Can evaluate system on slower or faster time scale than real system Some Disadvantages of Simulation • • May be very expensive and time consuming to build simulation Easy to misuse simulation by “stretching” it beyond the limits of credibility – Problem especially apparent when using commercial simulation packages due to ease of use and lack of familiarity with underlying assumptions and restrictions – Slick graphics. tables. may tempt user to assign unwarranted credibility to output • Monte Carlo simulation usually requires several (perhaps many) runs at given input values .

quantization. For instance. If this is not the case. . and amplifier nonlinearities must precede the effects of noise in the actual channel being modeled. but not for others. • The noiseless simulation has no errors in the received signal constellation. then the calculated BER will be too low. The semi analytic technique is applicable if a system has all of these characteristics: • Any effects of multi path fading. Distortions from sources other than noise should be mild enough to keep each signal point in its correct decision region. if the modeled system has a phase rotation that places the received signal points outside their proper decision regions. they reduce the applicability of the semi analytic technique to a communication system. Because phase noise and timing jitter are slow processes. then the semianalytic technique is not suitable to predict system performance.– Contrast: analytical solution provides exact values WHEN TO USE THE SEMIANALYTIC TECHNIQUE • The semi analytic technique works well for certain types of communication systems. and timing jitter is negligible. • The receiver is perfectly synchronized with the carrier.

Bessel. elliptic. If you use a square-root raised cosine filter. which makes the distribution of ones and zeros equal. but you can also use a Butterworth.PROCEDURE FOR THE SEMIANALYTIC TECHNIQUE The procedure below describes how you would typically implement the semi analytic technique using the semi analytic function: Generate a message signal containing at least ML symbols. or more general FIR or IIR filter. An augmented PN sequence is a PN sequence with an extra zero appended. Modulate a carrier with the message signal using base band modulation. where M is the alphabet size of the modulation and L is the length of the impulse response of the channel. A common approach is to start with an augmented binary pseudo noise (PN) sequence of total length (log2M)ML. Filter the modulated signal with a transmit filter. . Chebyshev type 1 or 2. This filter is often a square-root raised cosine filter. use it on the non-oversampled modulated signal and specify the oversampling factor in the filtering function. Supported modulation types are listed on the reference page for semi analytic. Shape the resultant signal with rectangular pulse shaping. If you use another filter type. you can apply it to the rectangular pulse shaped signal. in symbols. using the oversampling factor that you will later use to filter the modulated signal. Store the result of this step as txsig for later use.