Wide area traffic: the failure of Poisson modeling
IEEE/ACM Transactions on Networking (TON)
Self-similarity in World Wide Web traffic: evidence and possible causes
IEEE/ACM Transactions on Networking (TON)
Hyper-Erlang distribution model and its application in wireless mobille networks
Wireless Networks - Special issue: Design and modeling in mobile and wireless systsems
Performance Evaluation of Complex Systems: Techniques and Tools, Performance 2002, Tutorial Lectures
PhFit: A General Phase-Type Fitting Tool
TOOLS '02 Proceedings of the 12th International Conference on Computer Performance Evaluation, Modelling Techniques and Tools
Fitting world-wide web request traces with the EM-algorithm
Performance Evaluation - Special issue: Internet performance and control of network systems
Acyclic discrete phase type distributions: properties and a parameter estimation algorithm
Performance Evaluation
An EM-based technique for approximating long-tailed data sets with PH distributions
Performance Evaluation - Internet performance symposium (IPS 2002)
A Novel Approach for Fitting Probability Distributions to Real Trace Data with the EM Algorithm
DSN '05 Proceedings of the 2005 International Conference on Dependable Systems and Networks
QEST '05 Proceedings of the Second International Conference on the Quantitative Evaluation of Systems
KPC-Toolbox: Best recipes for automatic trace fitting using Markovian Arrival Processes
Performance Evaluation
Multi-class Markovian arrival processes and their parameter fitting
Performance Evaluation
A performance modeling scheme for multistage switch networks with phase-type and bursty traffic
IEEE/ACM Transactions on Networking (TON)
QoS and energy management with Petri nets: A self-adaptive framework
Journal of Systems and Software
An efficient MCMC algorithm for continuous ph distributions
Proceedings of the Winter Simulation Conference
Retrial queuing system with Markovian arrival flow and phase-type service time distribution
Computers and Industrial Engineering
Hi-index | 0.00 |
Approximating the empirical distribution of a measured data trace by a phase-type (PH) distribution has significant applications in the analysis of stochastic models. For phase-type fitting, a large number of different methods and tools exist. One drawback of all these methods is that the fitting effort strongly depends on the size of the data trace to be fitted. Since large data traces are necessary to capture rare events, which have a strong impact on system performance, current fitting procedures are very time consuming. In this paper, we introduce a method to generate an aggregated trace from the original trace, and we show how to effectively use the aggregated trace within a PH fitting approach, called G-FIT. In particular, we show that elements of a large traffic trace can be aggregated to a smaller number of 50-200 weighted elements, while fitting accuracy remains the same compared to the case of fitting the original trace. As a result, CPU time requirements for fitting PH distributions can be decreased by about four orders of magnitude, such that traces with ten million elements can be accurately fitted in a few seconds. The effectiveness of the proposed method is demonstrated on a set of benchmark traces and two real traffic traces as well as quantitative results from queuing analysis.