(→TCP congestion control over a live UMTS network [http://c3lab.poliba.it/images/2/21/Umts_tcp_stacks_170407.pdf]) |
(→Goodput) |
||
| Riga 18: | Riga 18: | ||
[[Immagine:goodput_1_flow_downlink.png|350px|]][[Immagine:goodput_2_flows_downlink.png|350px]] | [[Immagine:goodput_1_flow_downlink.png|350px|]][[Immagine:goodput_2_flows_downlink.png|350px]] | ||
[[Immagine:goodput_4_flows_downlink.png|350px]][[Immagine:channel_utilization_downlink.png|350px]] | [[Immagine:goodput_4_flows_downlink.png|350px]][[Immagine:channel_utilization_downlink.png|350px]] | ||
| + | |||
| + | The channel utilization provided in the case of single flow accessing the downlink is '''less than 40%''' mainly due to the high number of timeouts (see below). | ||
We have performed an extensive campaign of measurements that involved around 3000 flows and more than 40 hours of measurements using three different TCP stacks:
The experimental evaluation has been carried out by accessing the public Internet using an UMTS card (see figure below).
The following instantaneous variable measurements have been collected by using the libnetmeas library:
We show cumulative distribution function plots to illustrate the main results of our investigation.
The channel utilization provided in the case of single flow accessing the downlink is less than 40% mainly due to the high number of timeouts (see below).
We have performed an extensive campaign of measurements that involved around 3000 flows and more than 40 hours of measurements using three different TCP stacks:
The experimental evaluation has been carried out by accessing the public Internet using an UMTS card (see figure below).
The following instantaneous variable measurements have been collected by using the libnetmeas library:
We show cumulative distribution function plots to illustrate the main results of our investigation.
The channel utilization provided in the case of single flow accessing the downlink is less than 40% mainly due to the high number of timeouts (see below).