| EPSRC Reference: |
EP/C522885/1 |
| Title: |
Congestion Control for the Next Generation of Networks and Applications |
| Principal Investigator: |
Rio, Professor MJ |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Electronic and Electrical Engineering |
| Organisation: |
UCL |
| Scheme: |
First Grant Scheme Pre-FEC |
| Starts: |
01 October 2005 |
Ends: |
30 September 2008 |
Value (£): |
122,666
|
| EPSRC Research Topic Classifications: |
| Networks & Distributed Systems |
|
|
| EPSRC Industrial Sector Classifications: |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
To send information from one computer to the other in the Internet, computers break the information into pieces called packets, which then travel through the Internet from the source computer to the destination. The Internet works like the roads in the UK and the packets as cars travelling on those roads from a departure city to a destination. The roads here are several types of communication links (copper cables, fibre optic cables, satellite links, etc)In the intersection of these roads , there are machines called routers that select to which link the packet goes. When there are too many packets to be sent in one link , the router has to drop the packet. This phenomenon is called congestion Oust like congestion in a normal road). Since there is no way for a computer sending information to know how congested all the links are on the path to the destination, knowing how fast to send the information is an extremely difficult problem. This problem is called congestion control.The method that computers solve this problem is as follows: Each packet sent is acknowledged by another packet sent from the destination computer. Each time an acknowledgement is received, the computer sends information a bit faster. When an acknowledgement fails to arrive, the computer assumes that there is congestion on the network and reduces drastically the sending rate to half.This project will try to design and implement better methods to achieve congestion control. Because networks are getting faster (more packets can be sent in each link) and applications want to send more data (especially applications used by scientists like physicists, astronomers or medical researchers), controlling congestion is becoming harder and harder. Because each time a packet is lost, the sending rate is halved. The waste in capacity is now bigger. This problem becomes even harder due to synchronization between flows of packets (they reduce the sending rate at the same time wasting even more transmission capacity) and because issues of fairness between flows are not yet understood.New scientific applications also require the information not only to be sent faster but with tight delay constraints (the packets have to reach the destination in a given time schedule). How to achieve this efficiently is another objective of this project.The first beneficiaries of this project will be scientists (and everybody else indirectly, since the progress of science helps everybody) but the outcomes of this project will be crucial for, in the future, all the Internet users being able to communicate using more sophisticated applications like high definition videoconferencing, video-on-demand or virtual reality environments.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
|