2006 4th IEEE/IFIP Workshop on End-to-End Monitoring Techniques and Services
DOI: 10.1109/e2emon.2006.1651282
|View full text |Cite
|
Sign up to set email alerts
|

An Analysis of Active End-to-end Bandwidth Measurements in Wireless Networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
17
0

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 14 publications
(17 citation statements)
references
References 10 publications
0
17
0
Order By: Relevance
“…Active probing, on the other hand, takes measurements of specific probing traffic at the ingress and the egress of the network to infer the available bandwidth of a network path. Contrary to wired networks a strong impact of packet sizes on bandwidth estimates has been observed for wireless links [15,16,21,19,6]. Here, the fluid model, which is employed by many estimation methods, is clearly violated.…”
Section: Introductionmentioning
confidence: 99%
“…Active probing, on the other hand, takes measurements of specific probing traffic at the ingress and the egress of the network to infer the available bandwidth of a network path. Contrary to wired networks a strong impact of packet sizes on bandwidth estimates has been observed for wireless links [15,16,21,19,6]. Here, the fluid model, which is employed by many estimation methods, is clearly violated.…”
Section: Introductionmentioning
confidence: 99%
“…For throughput measurement, the proposed scheme adopted two different set values for s ta and s tb , including 8 bytes of UDP header + 20 bytes of IP header + 14 bytes of MAC header, to be used as s t in the compound probes. Considering the critical packet sizes of the compound probe over the path configurations in Figure 6, with s h = 1500 bytes and an IEEE 802.11g link, we selected s ta = 1392 bytes and s tb = 1492 bytes, respectively, for the single-hop scenario, determined by (6), and s ta = 288 bytes and s tb = 388 bytes, respectively, for the multiple-hop scenario, determined by (5). Each probing train consisted of 100 compound probes, which we have found to be a suitable number through experimentation, inter-spaced with a constant interval of 100 ms. We used the same number of probing packets in the WBest measurements.…”
Section: Resultsmentioning
confidence: 99%
“…In a node i, if the transmission time of P h on the output link L i+1 of node i is smaller than the Scheme for Throughput Measurement 1 : Set s h = Path MTU 2 : Set s t = s tb , where s tb is determined from (5) or (6) 3 : Send compound probes with s h and s t 4 : Get the smallest intra-packet gap G min (s tb ) 5 : Set s t = s ta , where s ta < s tb 6 : Send compound probes with s h and s t 7 : Get the smallest intra-packet gap G min (s ta ) 8 : Get the average intra-packet gap G avg (s ta ) 9 : Calculate the capacity c n ,…”
Section: B Sizing Probing Packets To Ensure Zero-dispersion Gapmentioning
confidence: 99%
See 1 more Smart Citation
“…Recent literature related to bandwidth measurement in wireless networks [3,5,25] has reported that existing tools that aim at measuring the available bandwidth are not accurate. Many of these measuring tools have been designed following the rate response model of the FIFO queue.…”
Section: Introductionmentioning
confidence: 99%