|
Activity Number:
|
474
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Physical and Engineering Sciences
|
| Abstract - #306170 |
|
Title:
|
A Bayes/Empirical Bayes Approach for Service Level Network Reliability/Survivability Measure
|
|
Author(s):
|
Cheng Chen*+ and Margaret F. Land and Rajat Sethi
|
|
Companies:
|
Texas A&M University and TeXas Environmental Studies and Analysis, LLC and Texas A&M University-Kingsville
|
|
Address:
|
Math Department, 7MSC172, Kingsville, TX, 78363,
|
|
Keywords:
|
empirical Bayes ; internet traffic ; reliability
|
|
Abstract:
|
Due to the explosive IP traffic growth over the past five years, carrying real-time voice and video traffic over Internet (VOIP) over the non-real-time IPv4 network becomes the most pressing needs for telecommunication industry. This poses a great challenge for the telecom network carrier, which is further complicated by the stringent reliability/availability requirements (.99999) of traditional voice networks. Key to resolve the challenge is to accurately estimate traffic flow in the network so that a network with optimized capacity can be designed. An Empirical Bayes estimation procedure to estimate live traffic was developed. The "asymptotic" behavior (property) of the proposed estimator is also obtained. The proposed method can also be applied in diseased states where mortality/survival analysis is an important aspect of research and data analysis.
|
