This is a graduate-level course in performance evaluation. Performance
evaluation is a "tool kit" for investigating computer systems including
computer networks and telecommunications systems. The course covers
measurement, queueing theory, traffic characterization, analytical modeling,
and simulation modeling. This course will use the CSIM19 simulation engine.
At the completion of this course, a student will be able to model a system
and predict its performance.
Class will be held in Cooper 353 on Monday and Wednesday from 9:30 to 10:45.
Office hours:
My office hours are Monday through Thursday, 5:00pm to 6:00pm. Generally,
my door is always open and you are very much welcome to stop by. I respond to
email very quickly - but, I ask you to include the text string "CIS6930:" in
the beginning of the subject line to make sure that I do not accidentally
spam-purge your email.
The TA office hours are Tuesday and Thursday, 10am to 11am.
Textbook and other course material:
The textbook for this course is Fundamentals of Performance Modeling
by Michael Molloy. Additional readings will be made available via the Internet.
Several useful books will be placed on reserve at the university library
for short-term checkout and use.
It is assumed that a graduate student in our program has completed an
undergraduate program in computer science. For this course, the student must
have knowledge of how computer systems and networks operate, be able to
program well in C, and understand basic probability theory and statistics.
Grades:
Biweekly homeworks - - - - - - -
Project - - - - - - - - - - - - - - - - -
Exam #1 - - - - - - - - - - - - - - - -
Exam #2 - - - - - - - - - - - - - - - -
18%
30%
26%
26%
Final letter grades will be no "worse" than:
A = 90% through 100%
B = 80% through 84%
C = 70% through 79%
D = 60% through 69%
F = Less than 60%
The legal stuff...
All the stuff I have to say (but hate to say since it should all be
obvious)...
Submission of late work:
If you must submit work late you need to talk to me at least one-week
before the due date in questions. Otherwise, late work will not be
accepted except in cases of verifiable emergencies.
Getting an incomplete:
Incomplete ("I") grades will only be given in the case of severe hardship
including verifiable medical or legal troubles. Simply being
"overloaded" and unable to complete your work is not grounds for an "I"
grade.
Academic honesty:
The concept of academic honesty is not a difficult one. When in doubt,
ask... ignorance is not an excuse. Standard department rules
hold. If you cheat you get kicked-out of the department and I have no leeway
on this by department rules. Copying of code and failing to attribute the source
is very much a breach of academic honesty. For anything you submit, it must
be clear what you did and what someone else did. This especially applies
to software source code.
Standard note from the Provost regarding religious observances:
"Students who anticipate the necessity of being absent from class due to
the observation of a major religious observance must provide notice of the
date(s) to the instructor, in writing, by the second class meeting."