Type of Document Master's Thesis Author Hager, Creighton Tsuan-Ren Author's Email Address email@example.com URN etd-01142000-14500030 Title Statistical Analysis of ATM Call Detail Records Degree Master of Science Department Electrical and Computer Engineering Advisory Committee
Advisor Name Title Midkiff, Scott F. Committee Chair DaSilva, Luiz A. Committee Member Davis, Nathaniel J. IV Committee Member Gaylord, Clark K. Committee Member Keywords
- Quality of Service
- Cluster Analysis
- Service Level Agreements
Date of Defense 1999-12-16 Availability unrestricted AbstractNetwork management is a problem that faces designers and operators of any type of network. Conventional methods of capacity planning or configuration management are difficult to apply directly to networks that dynamically allocate resources, such as Asynchronous Transfer Mode (ATM) networks and emerging Internet Protocol (IP) networks employing Differentiated Services (DiffServ). This work shows a method to generically classify traffic in an ATM network such that capacity planning may be possible. These methods are generally applicable to other networks that support dynamically allocated resources.
In this research, Call Detail Records (CDRs) captured from a ¡§live¡¨ ATM network were successfully classified into three traffic categories. The traffic categories correspond to three different video speeds (1152 kbps, 768 kbps, and 384 kbps) in the network. Further statistical analysis was used to characterize these traffic categories and found them to fit deterministic distributions. The statistical analysis methods were also applied to several different network planning and management functions. Three specific potential applications related to network management were examined: capacity planning, traffic modeling, and configuration management.
Filename Size Approximate Download Time (Hours:Minutes:Seconds)
28.8 Modem 56K Modem ISDN (64 Kb) ISDN (128 Kb) Higher-speed Access chager.pdf 217.86 Kb 00:01:00 00:00:31 00:00:27 00:00:13 00:00:01
If you have questions or technical problems, please Contact DLA.