Abstract | ||
---|---|---|
We assess the bias and variance of active probing measurement techniques for loss in networks. We show that loss probability is best measured using isolated probes rather than with probe `trains', which contrasts with prior work which found that probe trains better estimate statistics of lossy periods. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/LCOMM.2011.030911.101495 | IEEE Communications Letters |
Keywords | Field | DocType |
Probes,Loss measurement,Estimation,Delay,Probability,Correlation,Internet | Telecommunications,Transmission loss,Lossy compression,Data transmission,Computer science,Real-time computing,Electronic engineering,Contrast (statistics),Packet switching,Train,The Internet | Journal |
Volume | Issue | ISSN |
15 | 5 | 1089-7798 |
Citations | PageRank | References |
4 | 0.41 | 3 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
François Baccelli | 1 | 4543 | 347.87 |
Sridhar Machiraju | 2 | 435 | 37.08 |
Darryl Veitch | 3 | 903 | 84.47 |
Jean Bolot | 4 | 4 | 0.41 |