Download:
by Jason Skicewicz, Peter Dinda, Yi Qiao, Yi Qiao
http://www.cs.northwestern.edu/~pdinda/Papers/NWU-CS-02-13.pdf
Add To MetaCart
Abstract:
Distributed applications use predictions of network traffic to sustain their performance by adapting their behavior. The timescale of interest is application-dependent and thus it is natural to ask how predictability depends on the resolution, or degree of smoothing, of the network traffic signal. To help answer this question we empirically study the onestep-ahead predictability, measured by the ratio of mean squared error to signal variance, of network traffic at different resolutions. A one-step-ahead prediction at a low resolution is a prediction of the average behavior over a long interval. We apply a wide range of linear time series models to a large number of packet traces, generating different resolution views of the traces through two methods: the simple binning approach used by several extant network measurement tools, and by wavelet-based approximations. The wavelet-based approach is a natural way to provide multiscale prediction to applications. We find that predictability seems to be highly situational in practice---it varies widely from trace to trace. Unexpectedly, predictability does not always increase as the signal is smoothed. Half of the time there is a “sweet spot ” at which the ratio is minimized and predictability is clearly best. We conclude by describing plans for an online waveletbased prediction system. Effort sponsored by the National Science Foundation under Grants ANI-0093221, ACI-0112891, and EIA-0130869. The NLANR PMA traces are provided to the community by
Citations
|
1918
|
Congestion Avoidance and Control
– Jacobson
- 1988
|
|
1448
|
On the Self-Similar Nature of Ethernet Traffic (Extended Version
– Leland, Taqqu, et al.
- 1994
|
|
541
|
Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level
– Willinger, Taqqu, et al.
- 1997
|
|
482
|
The Network Weather Service: A Distributed Resource Performance Forecasting Service for Metacomputing
– Wolski, Spring, et al.
- 1999
|
|
339
|
TCP Vegas: end to end congestion avoidance on a global Internet
– Brakmo, Peterson
- 1995
|
|
284
|
A measurement-based admission control algorithm for integrated services packet networks
– Jamin, Danzig, et al.
- 1997
|
|
206
|
Forecasting Network Performance to Support Dynamic Scheduling Using the Network Weather Service
– Wolski
- 1997
|
|
201
|
Dynamics of IP traffic: A study of the role of variability and the impact of control
– Feldmann, Gilbert, et al.
- 1999
|
|
177
|
Data networks as cascades: Investigating the multifractal nature of Internet WAN traffic
– Feldmann, Gilbert, et al.
- 1998
|
|
136
|
A multifractal wavelet model with application to network traffic
– Riedi, Crouse, et al.
- 1999
|
|
118
|
An introduction to long-memory time series models and fractional differencing
– GRANGER, JOYEUX
- 1980
|
|
105
|
Fractional differencing
– HOSKING
- 1981
|
|
94
|
Scheduling from the perspective of the application
– BERMAN, WOLSKI
- 1996
|
|
78
|
Statistical methods for data with long-range dependence
– Beran
- 1992
|
|
61
|
Predictive Dynamic Bandwidth Allocation for Efficient Transport of Real-Time VBR Video over ATM
– Chong, Li, et al.
- 1995
|
|
59
|
A network measurement architecture for adaptive applications
– Stemm, Katz, et al.
- 2000
|
|
49
|
Mobile network estimation
– Kim, Noble
- 2001
|
|
45
|
A predictability analysis of network traffic
– Sang, Li
- 2000
|
|
44
|
An extensible toolkit for resource prediction in distributed systems
– DINDA, O’HALLARON
- 1999
|
|
39
|
Time series models for internet traffic
– BASU, MUKHERJEE, et al.
- 1995
|
|
36
|
Online Prediction of the Running Time of Tasks
– Dinda
- 2002
|
|
36
|
Multiresolution approximation and wavelets
– MALLAT
- 1989
|
|
33
|
The Architecture of the Remos System
– Dinda, Gross, et al.
- 2001
|
|
24
|
Long-range dependence: Revisiting aggregation with wavelets
– ABRY, VEITCH, et al.
- 1998
|
|
22
|
A new algorithm for measurement-based admission control in integrated services packet networks
– Casetti, Kurose, et al.
- 1996
|
|
21
|
Active Virtual Network Management Prediction
– Bush
- 1999
|
|
17
|
An Introduction to Random Vibrations, Spectral and Wavelet Analysis
– Newland
- 1993
|
|
12
|
On-line estimation of the parameters of long-range dependence
– ROUGHAN, VEITCH, et al.
- 1998
|
|
11
|
Time series models for internet data traffic
– You, Chandra
- 1999
|
|
6
|
A time series model of long-term NSFNET backbone traffic
– GROSCHWITZ, POLYZOS
- 1994
|
|
5
|
Internet Traffic Archive. http://ita.ee.lbl.gov
– SIGCOMM
- 1999
|
|
5
|
Multi-resolution resource behavior queries using wavelets
– SKICEWICZ, DINDA, et al.
- 2001
|
|
4
|
A nonintrusive, wavelet based approach to detecting network performance problems
– HUANG, FELDMANN, et al.
- 2001
|
|
2
|
Long-Range Dependence: Theory and Applications. Birkhauser, 2002, ch. Self-similarity and long range dependence through the wavelet lens
– ABRY, FLANDRIN, et al.
|
