How to deal with the simulation assignment
One of your key course requirements is a submission of simulation. You choose your topic yourself, the same as a method and a tool that you will use. It could be any of the development environments we have used (Excel, Simprocess, Netlogo, or Vensim).
Until the deadline you have to propose your assignments into assignment page on this website. You can also send us an email to speed up the process, but the record in the discussion page is mandatory. The assignment should contain:
- What you will simulate
- The goal of the simulation (what you analyze - i.e. not "to simulate balloon factory", but what problem should the simulation solve).
- What method and simulation environment you plan to use.
We will accept your assignment (or not). Please, take into consideration this task is deemed accomplished no sooner than the assignment is accepted from us. Every semester there is somebody with problems to find an acceptable assignment, so please think about it well before the deadline to avoid unnecessary penalization.
Generally, the simulation has to make sense (if it was perfect somebody would actually use it) and its results have to be comparable with the reality. This, in most cases, requires one to have real world data in order to have something to base the simulation logic on.
Because of differing complexity of the particular simulation environments, the requirements vary depending on the software you use. In case of Simprocess and Monte Carlo a simulation of real problems with real parameters (e.g. an existing business) is required. In case of agent-based models it is possible to elaborate the works that are not essentially a simulation, but an implementation of certain agent phenomenon (e.g. utility-based agents, etc.).
Please, note that due to certain similarities of this course with some other courses we are in a contact with our colleagues whe teach them (namely with Dr. Burian and Doc. Mildeova, etc.). It is not possible to submit a simulation that was already submitted in any other course (nor the adjusted one). If such behavior will be revealed, it will be considered cheating and lead to failure in this course. Unfortunately, not everyone of you had an opportunity to attend these courses and it would not be fair conditions. If you want to follow up with your certain former work, let us know and we will try to find an acceptable and fair mode how to do it. If such cases, there must be such ample new contribution that it takes at least the same time and effort as a new topic.
The resulting paper will be in the form of research report. Bear in mind that the sole code of the simulation is of course a part of your work, but not the only result. The goal of the simulation is to solve the problem and you have to write the research report about. The simulation itself is just an instrument to reach the goal (and a part of the report).
Recommended work outline:
- Problem definition - a description of the situation you solve (i.e. the task)
- Method - the discussion of possible solutions, the selection of method and tools for the solution, reasons for such choice (why the selected methods and tools are the best for the problem)
- Detailed description of the method, including parameters, ranges, schemes, model limitations, etc. The description must be detailed enough that anybody could replicate the experiment event without your model source codes.
- Results - list of results, their analysis, interpretation and evaluation.
- Conclusion - how the problem was solved
- Model source code (xls, spm, nlogo, mdl, etc. file)
You have to submit the work using this web. There is a subpage for the particular term in Simulations section. You should create your own page with the same title as your simulation. Then add there the link to your page. For your convenience and to keep a uniform look of the individual chapters it is recommended to copy the following code to the created page and put it in the editor of a new page. Your paper should contain roughly the following items. Of course, it is expected that you will add your own structure of the lower levels.
Introduction =Problem definition= =Method= =Model= =Results= =Conclusion= =Code=