# Can Simulations Model Chaos?

Can chaotic systems be predicted? I guess we first need to agree on exactly what a chaotic system is.

“Complex system that shows sensitivity to initial conditions, such as an economy, a stockmarket, or weather. In such systems any uncertainty (no matter how small) in the beginning will produce rapidly escalating and compounding errors in the prediction of the system’s future behavior.”

It is hard to imagine a complex system that does not show sensitivity to initial conditions. If the follow-on statement is true, then there is little point to ever trying to model or predict the behavior of such a system because it is not predictable. But it is not hard to find counter-examples, even to the examples they provided. Meteorologists do a reasonable job predicting the weather; it depends on your standards of accuracy. Certainly they can predict fairly accurately the likelihood of a 90 degree day in January in Canada or anticipating the path of a tropical storm for the next 12 hours.

A less technical but perhaps more useful definition comes from membrane.com:
“A chaotic system is one in which a tiny change can have a huge effect.”
That leads us toward a more practical definition for our purposes.

For the types of systems we normally model, I would propose yet another definition.
A chaotic system is one in which it is likely that seemingly trivial changes in the initial conditions would cause significant changes in the predicted results, over the time frame being considered.

This definition, while not technically rigorous, acknowledges that most of us rarely have the opportunity or the need to deal in absolutes. We live in a world where the majority of decisions are made subjectively (“Joe has 20 years experience and he says…”) or with gross simplification (“Of course I can model that in a spreadsheet…”). In this world, being able to base a decision on a simulation model with better accuracy and objectivity can help realize tremendous savings, even if it is still only an approximation and only useful within specified parameters.

Can we accurately predict true chaotic systems? By strict definition clearly not. And even by my definition, there will be some systems that are just too chaotic to allow any predictions to be useful.

But can we provide useful predictions of most common systems, even those with some chaotic aspects? Absolutely yes. Every model is an approximation of a real or intended system. Part of our job as modelers is to ensure that the model is close enough to provide useful insight. A touch of chaos just makes that more interesting. 🙂

Dave Sturrock
VP Products – Simio LLC

# Professional Development

The annual Winter Simulation Conference (WSC) starts two weeks from today. Initially as a practitioner and then later as a vendor I have attended over 20 of these conferences in addition to dozens of other similar events. WSC is just one of many events that you could choose to attend. But why should you attend any of them?

All such events are not identical, but here are a few attributes of WSC that are often found in other events as well:

Basic tutorials – If you are new to simulation, this is a good place to learn the basics from experienced people.

Advanced tutorials – If you already have some experience, these sessions can extend your skills into new areas.

Practitioner papers – There is no better way to find out how simulation can be applied to your applications than to explore a case study in your industry and talk to someone who may have already faced the problems you might face.

Research – Catch up on state-of-the-art research through presentations by faculty and graduate students on what they have recently accomplished.

Networking – The chance to meet with your peers and make contacts is invaluable.

Software exhibits and tutorials – If you have not yet selected a product or you want to explore new options, it is extremely convenient to have many major vendors in one place, many of whom also provide scheduled product tutorials.

Supplemental sessions – Some half and full day sessions are offered before and after the conference to enhance your skill set in a particular area.

Proceedings – A quick way to preview a session, or explore a session that you could not attend. This serves as valuable reference material that you may find yourself reaching for throughout the year.

I think every professional involved in simulation should attend WSC or an equivalent conference at least once early in your career, and then periodically every 2-3 years, perhaps rotating between other similar conferences. If you want to be successful you have to keep your skills and knowledge up to date. And in today’s economy, a strong personal network can be valuable when you least expect it.

I hope to see you at WSC in Miami!

Dave Sturrock
VP Products – Simio LLC

I read a lot, both for business and pleasure. But it seems I never have enough time. So when I sit down with a magazine, for example, most articles probably get less than a couple seconds of attention. Unless an article immediately captures my attention, I quickly move on to the next one. I know that I occasionally miss out on good content, but it is a way to cope with the volume of information that I need to process each day. Consider the implications when you are writing a project report for others to read…

We are all busy. When we are presented with information to read or review, we often don’t have time to wade through the details to see if the content merits our time.

Tell me the most important thing first! Give me the summary! How many times have you asked (or wished) for that?

At one point, it was common to give presentations by starting with an introduction, building the content, and ending with the conclusion – “the big finish”. While this is appropriate for some audiences, many people don’t want to take the time to follow such a presentation. Instead, they want to be presented with a quick overview and a concise summary first. They will then decide to read on if the overview has captured their interest and they need more information.

Think about your own experiences. When you have a document to read and you are not sure it is worth your time, what do you do? If you are like most people you will probably consider most, if not all of the following:
• Does the title look interesting?
• Do you know/respect the author?
• Scan the major headings or callouts for content of interest.
• Scan any pictures/diagrams for content of interest.
• Evaluate the summary or abstract.
While the order and details might differ slightly, at each stage of the above process if you are not convinced of the value of continuing, you will put the document aside. Only after the document has passed this gauntlet of tests, will you spend the time to seriously read the content.

What can we learn from this?

Content is not enough. The best content in the world is of little value unless it is read.

Write each report so everyone, including your busy stakeholders, will take the time to read it. Keeping these simple suggestions in mind will help you succeed at getting your message across.

Dave Sturrock
VP Products – Simio LLC

# Predicting Process Variability

Systems rarely perform exactly as predicted. A person doing a task may take six minutes one time and eight minutes the next. Sometimes variability is due to outside forces, like materials that behave differently based on ambient humidity. Some variability is fairly predictable such as tool that cuts slower as it gets dull with use. Others seem much more random, such as a machine that fails every now and then. Collectively we will refer to these as process variability.

How good are you are predicting the impact of process variability? Most people feel that they are fairly good at it.

For example, if someone asked you what is the probability of rolling a three in one role of a common six-sided die, you could probably correctly answer one in six (17%). Likewise, you could probably answer the likelihood of flipping a coin twice and having it come up heads both times, one in four (25%).

But what about even slightly more complex systems? Say you have a single teller at a bank who always serves customers in exactly 55 seconds and customers come in exactly 60 seconds apart. Can you predict the average customer waiting time? I am always surprised at how many professionals get even this simple prediction wrong. (If you want to check your answer, look to the comment attached to this article.)

But let’s say that those times above are variable as they might be in a more typical system. Assume that they are average processing times (using exponential distributions for simplicity). Does that make a difference? Does that change your answer? Do you think the average customer would wait at all? Would he wait less than a minute? Less than 2 minutes? Less than 5 minutes? Less than 10 minutes? I have posed this problem many times to many groups and in an average group of 40 professionals, it is rare for even one person to answer these questions correctly.

This is not a tough problem. In fact this problem is trivial compared to even the smallest, simplest manufacturing system. And yet those same people will look at a work group or line containing five machines and feel confident that they can predict how a random downtime will impact overall system performance. Now extend that out to a typical system with all its variability in processing times, equipment failures, repair times, material arrivals, and all the other common variability. Can anyone predict its performance? Can anyone predict the impact of a change?

With the help of simulation, you can.

This simple problem can be easily solved with either queuing theory or a simple model in your favorite simulation program. More complex problems will require simulation. After using your intuition to guess the answer, I’d suggest that you determine the correct answer for yourself. If you want to check your answer look at the comment attached to this article.

And the next time you or someone you know is tempted to predict system performance, I hope you will remember how well you did at predicting performance of a trivial system. Then use simulation for an accurate answer.

Dave Sturrock
VP Products – Simio LLC

# Simulation in Healthcare

Over the years, I have had several occasions to use medical facilities for myself and my family. Some visits were routine, such as for a diagnostic tests or images. Others were for much more critical visits to an emergency department. As my visits spanned many facilities and many time periods, I observed a dramatic difference in the service provided. In the case of bad service I just had to wonder “Didn’t anyone ever study this operation? Did anyone ever simulate it?”

Simulation can bring significant benefits to healthcare, just as it does in other types of systems. Some of those benefits come from the simulation’s ability to:
• Account for variability in human behavior
• Account for variability in demand
• Capture complexities and interdependencies
• Capture system performance over a period of time
• Support continuous process improvement and evaluation of new scenarios
• Provide an objective basis for evaluating policies and strategies

Here are a few possible applications to illustrate how simulation is often used in the healthcare industry:

New Facility Design – Evaluate design to assure that present and future objectives will be met. Reduce capital costs by “running” the facility under various scenarios and identifying excess capacity . Reduce operating costs by supporting lean and six sigma analyses. Increase throughput through process flow optimization and identification of bottlenecks and capacity constraints.

Emergency Department (ED) – Decrease LOS (Length of Stay) and LWBS (Leave Without Being Seen) yielding higher patient satisfaction. Improve staff efficiency and improve room and resource utilization resulting in lower costs.

Outpatient Lab and Surgery – Determine optimal staff and resource allocation. Balance scheduled demand with the often-critical unscheduled demand. Decrease lab and diagnostic turn-around time. Identify non-value-added and redundant processes.

Ambulance Service – Evaluate operational scenarios for both road and air-based vehicles. Evaluate new technology to determine their effect on the entire system. Pre-plan dynamic utilization-based response guidelines to optimize performance during major ED demand periods.

Vaccine Distribution – Evaluate regional material stocking strategies, distribution strategies, and staffing.

Often the benefits from these studies are reported in the millions of dollars so they are well worth the undertaking.

One source of additional information is the Society for Simulation in Healthcare which is having their annual conference in January. Another source is the Society for Health Systems which offers the latest in process analytics, tools, techniques and methodologies for performance improvement.

Dave Sturrock
VP Products – Simio LLC

# Data Collection Basics Part 2

Last week in Data Collection Basics (Part 1) I discussed data collection, introducing the topics of identifying required data and then locating or creating that data. Once you have some data, you typically need to do some analysis on it before you can effectively use that data.

Select Distribution. Typically input data to a simulation model is specified as a distribution. If you have estimated data you must select the most appropriate distribution (for example a minimum time, typical time, and maximum time may be represented as a Triangular distribution). If you have actual data, then you will need to run a statistical analysis on it. Many software products (some generic and some simulation-specific) are available to help you with selecting (fitting) a distribution and its shape parameters, and even with cleaning the data to eliminate bad observations.

Analyze Sensitivity. Once you have some data you can build it into your model and start making trial runs. Particularly if you have relied on an estimate, you might want to run your model with values above and below the estimated values to determine system sensitivity to that parameter. If you find that the system is sensitive to an estimated value (e.g. the results change significantly with a change to the input parameter), then you can determine if it is worth a greater investment to obtain a more reliable value. This is one potential solution to the problems of bias and inaccuracy discussed in the initial article. But more than that, it is also a good way to iteratively determine how much time to spend on your input data.

Adjust Detail. Sometimes the quality of the available data can help you determine the appropriate level of detail for a model. If the data you intend to use is not very good, then there is little point to building a highly detailed model. This is not to imply that such a model is of no value, after all every model is just a representation or estimate of reality – no model will be perfect. But it is important to represent to your stakeholders the relative accuracy of the model and its underlying data.

This was a quick overview of some steps to data collection. Whole textbook chapters have been written about each of these, so be sure to look for greater detail when you are ready.

Dave Sturrock
VP Products – Simio LLC

# Data Collection Basics

Even though the people responsible for building models are often the “data collection people”, I know very few associates who think this is a particularly enjoyable part of their job. But data collection is a necessary part of most simulation projects. An early task in each simulation project should be to identify what data will be needed and how that data will be obtained.

Identify Data. There are many different types of data that you will potentially need. Like other aspects of simulation, the identifying required data is best done iteratively. Start by looking at the major areas of your model: arrival sections, processing sections, storage areas, departure areas, internal movement and similar aspects. For each area, then consider the key parameters necessary to describe it. For example, in an arrival area: What is arriving? Are there many different types of entities? Do they each have descriptive attributes that are important? Do you expect the arrivals to follow some type of a time-based pattern? Considering questions such as these will also help you define the model and modeling approach and iteratively, more detail on the exact data required.

Locate Data. With the current level of automation and electronic tracking, the availability of data has become more prevalent. If it’s an existing system, there may already be data that is routinely collected. If it is a new system, the vendor may have access to data collected on similar systems. In either case, the existence of data does not necessarily make your job easy. For example, perhaps you are interested in a processing time on an operation, and that processing time is automatically captured. But what may not be obvious is exactly what that number represents. Does it (sometimes) include time when the process was failed (perhaps short failures are imbedded but long failures are not)? Does it (sometimes) include time when an operator went on break and forgot to properly log out? Detecting and cleaning such situations can be a tedious and frustrating part of using existing data.

Create Data. If the data you need does not exist or cannot be appropriately cleaned, you must often create it. On an existing system, the most accurate method is to electronically capture the data or have manual studies done to determine it. Either of these can be very expensive. An alternate approach is to get estimates from people who know – people running or managing the operation. Although fast and inexpensive, this may introduce bias and inaccuracy. Likewise on a system that does not yet exist, you may need to rely on specifications provided by a vendor, again possibly introducing bias and inaccuracy. More on dealing with this situation later.

This was a quick overview of some initial steps to consider in data collection. Next week I will discuss some additional steps on what to do next with that data. Until then, Happy Modeling!

Dave Sturrock
VP Products – Simio LLC

# Simulation and Disaster Management

While the last couple months have been pretty dry where I live here in the Northeastern part of the U.S., in the Southeastern part several severe hurricanes have already hit and it looks like more are coming. While every severe storm can have serious consequences, often the major difference between a severe storm and an outright disaster is the level of preparation.

Of course weather is just one of many potential causes of disasters. We have all seen floods, fires, earthquakes, and other disasters around the world that have been made much worse through inadequate planning and poor execution. Simulation can play a major role in preparing communities to avoid or at least reduce the impact of such disasters.

More accurate weather prediction is due in part to simulation. Combining advanced detection technology with sophisticated simulations has allowed us to become much better at predicting storm paths and severity. This allows for improved warnings and appropriate responses.

Simulation use in evacuation planning has a very high potential, but is not used as much as it could be. Communities should be able to examine various scenarios and evaluate the best ways to move people to safety, well before a dangerous situation actually occurs.

First-responder rescue efforts can also be pre-planned and evaluated. Where should various types of equipment be stored? How can it be moved? Who will staff it? What procedures should be used for various types of disasters?

As for relief scenarios, they too could be planned ahead of time with the assistance of simulation. What equipment and supplies should be stockpiled and where? How can it be quickly relocated? Who will staff it? The logistics of a large scale disaster-relief effort, including health care provisions, security at all levels, and even communications, (all of which often involve multi-organization coordination) is a great opportunity to showcase the true benefits of using simulation.

Large corporations and other organizations can also do their own simulation-based planning. Contingency plans for various scenarios can minimize the impact of a local or regional event and help ensure that a single event does not cripple the entire organization.

Louisiana State University has a relatively new center for disaster management and has organized a conference November 16-18 dealing with some of these issues.

Be Prepared” is a motto that anyone planning for a disaster should live by; Simulation helps make that a bit easier.

Dave Sturrock
VP Products – Simio LLC

# Keep Simulation Projects Simple Too

We all have stories about company decisions that make us shake our head. If you have ever worked for a large organization, it may have seemed that some of their decisions were, shall we say, sub-optimal.

For example, one particular organization was using a “home grown” time reporting system that was simple, efficient, and worked well. However upper management felt the need to buy a more sophisticated “name brand” system. Unfortunately it was poorly designed and overly complicated. Rollout required extensive training and retraining to learn the simplest tasks. It was so difficult to use that many employees simply stopped using it in favor of informal arrangements with their managers (who also found it difficult to use). As a result, the company spent a lot of money and wasted a lot of employee time, and in the end they had a system that produced inferior results.

If this was an isolated case, it could be easily forgiven. But I expect most people working for large organizations could cite similar situations. Large organizations often tend to replace simplicity with complexity.

Last week in Keep Simulation Simple I talked about KIS; the Keep It Simple concept of doing just enough to do it well and no more!

I discussed how KIS could be applied to model building, but you can also extend the KIS principle to many other aspects of simulation, especially the tools you routinely use.

For time tracking, you can buy expensive highly integrated software systems like the organization above, or for desk- bound employees you can buy software that will sense or periodically ask and record what you are working on. But the cheaper, simpler and more effective solution is simply using a spreadsheet or paper form and having the employee take two minutes at the end of each day and record time against their tasks for that day. Sure there can sometimes be reason for other methods, but for the majority of us the spread sheet solution is superior.

For project management, choose the simplest tool that will meet your needs. Some projects are complex enough that they need project management software like Microsoft Project or something even better. But in many cases, such software results in a waste of time when a simple spreadsheet could meet your needs. In my experience project management software is often overkill for the types of projects we usually encounter.

In simulation software there is some inclination to buy the most comprehensive software that you can afford. But it is often better just to buy the simplest software that is likely to meet your short to intermediate-term needs. An important caution here – make sure that your software has an adequate upgrade path so that as your needs evolve you can migrate into more feature-rich software without losing your initial investment in software, training, and models.

Stay vigilant for time wasters – they often come disguised as “cool technology” and “time savers”.
Keep It Simple.

Dave Sturrock
VP Products – Simio LLC

# Keep Simulation Simple

I mentioned a while back that I am a Boy Scout. OK, maybe my boyhood days are long gone, but I still consider myself to be a Scout. I learned many lessons as a Scout; lessons that continue to serve me well today. One of those is KIS or Keep It Simple.

I remember learning primitive camping skills. Many novice campers would bring too much gear, requiring hauling and storing it, and just in general complicating camp life. The simple (KIS) approach is to bring only what you absolutely need. Many novice campers would also select poor camp sites and then spend time dealing with dampness, bugs, discomfort, safety issues and more. The simple approach is to avoid those issues by selecting a good camp site. Then in both cases, you spend all that saved time enjoying the camp and doing what you came to do. KIS pays off.

KIS applies equally well to many aspects of simulation. When things go wrong, it can often be traced back to too much complexity.

• How many people are subjected to overly complex management procedures?
• Are the procedures used for planning and tracking your work making the most effective use of everyone’s time?
• Is every aspect of your work done effectively?
• The basic concept of KIS is to do just enough to do it well and no more! Does this mean you should not do your best? No. But it does mean that you should segment your work into small phases and KIS on each phase.

In model-building for example, let’s say a stakeholder expresses desire for a detailed model for the 10 areas of his system. One common approach is to go off and create exactly what the stakeholder asked for. Unfortunately, this will probably be wrong. A better approach is to pick one representative area, and do a very high-level model of that one area. Then review that model and results with the stakeholder. In most cases, you will both learn a lot and you may jointly decide on a different approach. Then perhaps do a detailed model of that same area or perhaps extend that high-level model to a few more areas. Again you will probably learn something that will change your approach or objectives. For each phase, you want to do the simplest thing (KIS) that will meet the objectives for that phase. In this way, you will minimize any wasted effort and come much more quickly to exactly what the stakeholder needs.

Let’s consider model-building at a much more detailed level. A common mistake by novices is to build a large section of a model (perhaps even an entire system) all at once. And then you hit “Go” and it does not work. Why doesn’t it work? There are perhaps a thousand possible reasons to investigate. Even worse, there are most likely dozens of small or large problems, each potentially obscuring the others. Verifying and validating such a model is a daunting task. A much better approach is to start by selecting a very small (KIS) portion of the model to build and verify that it works. Then repeat. When a problem is discovered in any new section, it is generally easy to find it because you know it is a result of that latest section just added. Again, “Keep It Simple”.

Remember, Keep It Simple. Work effectively and exceed your stakeholder expectations one simple step at a time.

Dave Sturrock
VP Products – Simio LLC