unni@sdcrdcf.UUCP (Unni Warrier) (07/25/87)
This is to announce the start of a new mailing-list devoted to network modeling
and simulation. Sorry for the cross-postings to many groups, but we aim to
reach as wide an audience as possible. We expect to cover the following broad
areas:
Networks modeling, Queueing theory as applied to networks
Simulation, Distributed simulation
These topics are furthur described at the end of this article.
Please send in your requests to be included in this list, because if I get a
large enough number, we can get our own newsgroup.
All requests for inclusion in the mailing list should be sent to
..!sdcrdcf!sdcjove!modsim-request OR
"modsim-request@cam.unisys.com"
All articles for inclusion should be sent to
..!isdcrdcf!sdcjove!modsim OR
"modsim@cam.unisys.com"
Any private correspondence regarding the list should be sent to me at
..!sdcrdcf!sdcjove!unni OR
"unni@cam.unisys.com"
TOPICS FOR DISCUSSION:
a. Networks modeling
There is a lot of work in the literature on modeling networks, typically as
a network of queues. However, for large networks, the computations become
intractable and we are forced to move to even more approximte models.
* An example is the ARPANET, where the congestion problem has not been
satisfactorily analyzed.
* Some groups are working on providing network
management mechanisms. Will these include performance "hooks"?
* A new generation of high-speed fibre-optic based networks is coming into
being. What are the models available for these networks?
* What do we know about interconnection structures like the hypercube? What
is the experience of people in the field?
* A lot of work has been done on applying queueing theory to networks.
What is the practical experience of net-people in applying these results
to real-life network problems?
b. Simulation of networks
* What is the experience of net-people on simulation of networks?
* What are your opinions on simulation vs closed-form solutions?
* How well does simulation agree with real measurements?
* What are the tools people are using for simulation? Do object-oriented
languages provide any better simulation environments than "ordinary"
simulation tools like Simscript, GPSS, PAWS?
* What are the experiences of net.people with specific tools?
* Does distributed simulation offer improved performance over uni-processor
simulation? Does anyone have any experiences they wish to communicate?
I fully realize that the areas outlined above are very large in scope, but the
idea is to get a discussion going. As the group expands, we can spin off
more selective areas into new newsgroups. I will "moderate" this list
until someone more qualified volunteers, or we get a real newsgroup going.
If I get enough responses, I will try to push the net.gods into giving us our
own newsgroup.
unni
UUCP: ..!sdcrdcf!sdcjove!unni
ARPA: unni@cam.unisys.com
Ma Bell (may she rest in peace!): (213) 829-7511 X 5694
US mail: Unni Warrier, Unisys, MS 41-02,
2400 Colorado Ave, Santa Monica CA 90406