| Project/Area Number |
15560320
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Communication/Network engineering
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
KATO Toshihiko The University of Electro-Communications, Graduate School of Information Systems, Assoc.Prof., 大学院・情報システム学研究科, 助教授 (90345421)
|
|---|
| Project Period (FY) |
2003 – 2004
|
| Project Status |
Completed (Fiscal Year 2004)
|
| Budget Amount *help |
¥3,200,000 (Direct Cost: ¥3,200,000)
Fiscal Year 2004: ¥1,800,000 (Direct Cost: ¥1,800,000)
Fiscal Year 2003: ¥1,400,000 (Direct Cost: ¥1,400,000)
|
|---|
| Keywords | TCP / Congestion Control / High Speed Communication / 超高速ネットワーク / サブコネクション / 選択的受信確認 |
|---|
| Research Abstract |
For realizing high speed TCP communication over Gbps class Internet backbone, which occupies the whole bandwidth of the network by itself, this research project studied a new congestion control scheme. It introduces multiple subconnections in a TCP connection and the congestion control using congestion window is performed by individual subconnections instead of TCP connection as a whole. As a result, it is expected that there are a number of conventional TCP connections even in the situation where there are only a small number of high speed TCP connections.
The following research activities are done in these two years.
1.Design of a new TCP congestion control algorithm
Based on the consideration mentioned above, a new algorithm was studied.
2.Evaluation of designed algorithm
The evaluation simulation software for the algorithm was developed on the network simulator ns-2,and the performance evaluation was done. But, a good result was not obtained.
3.Modification of the algorithm and its evaluation
The reason of the bad performance seemed to be the algorithm was too eager in the retransmission. So, the algorithm was modified and re-evaluated. But, although the level of congestion was improved, the throughput was similar to the first algorithm.
4.Design of the third algorithm
In order to resolve those two problems, the third algorithm was designed.
|
