Quality of service is commonly used to shape network traffic
to meet specified criteria. The various scenarios include
limiting and reserving bandwidth for a particular application,
host or user, prioritizing latency sensitive traffic or equal
distribution of unreserved bandwidth. The DynShaper software
distributes and controls a traffic quota by more
sophisticated means than fixed per user limits and simple
disconnection after the user reaches the limit.
It distributes the quota on a daily basis, where
each day receives the same share. The users are
sorted into predefined groups with different bandwidths depending on
their recent consumption. This classification is periodically updated
to ensure the sorting order is maintained. The bandwidths of these
groups is dynamically adjusted depending on the actual consumption to
provide an efficient utilization.
This thesis presents another distribution model using a case-based
reasoning approach, a method for machine learning which is classified
as conventional artificial intelligence. Case-based reasoning tries
to solve new problems based on the solutions of similar problems from the past.
Controlling the network traffic to remain within a fixed quota can be
modeled as such a problem if the traffic patterns are recurring.
Possible solutions can be derived from statistical data and altered to
suit the new problems. When an untested solution is applied, the
software supervises the execution and revises the solution accordingly,
if the actual results deviate from the precalculated schedule.
| Identifer | oai:union.ndltd.org:DRESDEN/oai:qucosa.de:bsz:ch1-200701572 |
| Date | 30 September 2007 |
| Creators | Schade, Markus |
| Contributors | TU Chemnitz, Fakultät für Informatik, Dr. Markus Borschbach, Prof. Dr. Wolfram Hardt, Dr. Markus Borschbach |
| Publisher | Universitätsbibliothek Chemnitz |
| Source Sets | Hochschulschriftenserver (HSSS) der SLUB Dresden |
| Language | English |
| Detected Language | English |
| Type | doc-type:masterThesis |
| Format | text/html, application/pdf, application/postscript, application/pdf, text/plain, application/zip |
| Rights | Dokument ist für Print on Demand freigegeben |
Page generated in 0.0131 seconds