Intelligent no packet loss networking

• US 20030152096A1
• Filed: 02/12/2003
• Published: 08/14/2003
• Est. Priority Date: 02/13/2002
• Status: Abandoned Application

• Current Assignee: Global Network Expert Communications
• Original Assignee: Global Network Expert Communications
• Inventors: Chapman, Korey
• Application Number:
  US10/364,405
• Publication Number:
  US 20030152096A1
• Time in Patent Office: Days
• US Class Current: 370/412
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 47/803 Application aware
• CPC Class Codes: H04L 47/805 QOS or priority aware
• CPC Class Codes: H04L 47/828 Allocation of resources per group of connections, e.g. per group of users
• CPC Class Codes: H04L 49/90 Buffering arrangements

Abstract

A method and system for dynamically allocating bandwidth to at least two applications sharing a communication channel of a fixed bandwidth for simultaneous transmission in a communication network. The method includes determining a bandwidth required for optimal transmission of each application, monitoring the flow of packets of each application, determining amount of the allocated bandwidth in use by each application, and assigning an unused portion of the allocated bandwidth of one application to the other application.

Claims

1. A method of dynamically allocating bandwidth to at least two applications sharing a communication channel of a fixed bandwidth for simultaneous transmission in a communication network, the method having the steps of:

(a) monitoring traffic associated with said at least two applications;

(b) associating each of said at least two applications with a predetermined traffic class, said predetermined traffic class being associated with a set of traffic characteristics;

(c) associating each of said traffic classes with a policy map;

(d) allocating a predetermined amount of bandwidth for an optimal transmission rate to each of said traffic classes;

(e) associating each of said traffic classes with a class of service, said class of service having a value indicative of transmission priority in accordance with said policy map;

(f) routing packets of said at least two applications using IP session based packet switching;

(g) allowing any of said at least two applications to use more than said predetermined amount of bandwidth when a portion of said fixed bandwidth is unused;

(h) reducing said bandwidth of any of said at least two applications to said predetermined bandwidth if another application initiates transmission;

(i) storing packets of each traffic class in a queue;

(j) monitoring said packets stored in said queue;

(k) regulating said transmission rate using said queue; and

(l) limiting said transmission rate in accordance with said policy map;

whereby said traffic associated with said at least two applications is transmitted and received without traffic loss.

2. The method of claim 1 wherein said step of regulating said transmission rate includes a further step of notifying any of said at least two applications to reduce said transmission rate in order to maintain said queued packets below a threshold level of said queue.

3. The method of claim 2 wherein network congestion is foreseen and avoided by maintaining said queued packets below said threshold level.

4. The method of claim 1 wherein said step of routing of said packets includes a step of identifying a flow of packets that are similar in type, source and destination.

5. The method of claim 1 wherein said policy map includes executable program instructions on a computer readable medium.

6. The method of claim 1 wherein the step of monitoring said traffic includes the further steps of:

(a) monitoring flow of said packets of each of said at least two applications;

(b) analyzing traffic characteristics is said network to determine the number of packets belonging to each of said at least two applications;

(c) determining a portion of said allocated bandwidth in use by each of said at least two applications; and

(d) assigning an unused portion of said allocated bandwidth of one of each of said at least two applications to another of each of said at least two applications.

7. A method of managing a flow of traffic from a plurality of applications transmitting in a communication network, said method including the steps of:

(a) assigning said traffic to a plurality of traffic classes;

(b) determining a quality of service for each of said traffic classes, said quality of service defining a set of rules for optimal transmission for each of said traffic classes;

(c) monitoring said traffic belonging to each of said traffic classes; and

(d) adjusting in real-time said flow of traffic associated and adhering to said set of rules under any condition of said communication network;

whereby said traffic is transmitted and received without traffic loss.

8. The method of claim 7 whereby the step of monitoring said network traffic includes a further step of determining bursty traffic.

9. The method of claim 7 wherein an application associated with said bursty traffic is instructed to substantially diminish transmitting traffic for a predetermined time, such that said bursty traffic is regulated and transmitted without traffic loss.

10. A system for dynamically allocating bandwidth to at least two applications sharing a communication channel of a fixed bandwidth for simultaneous transmission in a communication network, the system having:

(a) a network entity for monitoring traffic including packets associated with said applications and associating each of said applications with a predetermined traffic class, said predetermined traffic class having a set of traffic characteristics and a predetermined quality of service;

(b) a switch for forwarding said packets between a source and a destination based on a flow rate of said packets;

(c) a queue at said source and at said destination for regulating transmission of said packets therebetween; and

(d) a set of bandwidth allocation rules defining said allocation of bandwidth when said at least two applications are transmitting simultaneously;

wherein said packets are transmitted in a lossless manner between said source and said destination.

11. The system of claim 10 said quality of service defines a predetermined amount of bandwidth for optimal transmission of packets of said traffic.

12. The system of claim 11 wherein one of said applications can use more than said predetermined amount of bandwidth when a remainder of said fixed bandwidth is available.

13. The system of claim 12 wherein if another application initiates transmission then said one application reduces said bandwidth to said predetermined amount of bandwidth, such that said each of said applications are allocated their predetermined amount of bandwidth respectively.

14. The system of claim 10 wherein said queue is of a predetermined size and includes a threshold level associated with said predetermined bandwidth;

said threshold level being less than said predetermined size.

15. The system of claim 14 wherein said queue includes a trigger when said queue size is substantially close to said a threshold level.

16. The system of claim 15 wherein said trigger includes an algorithm to distinguish between temporary traffic bursts and non-temporary traffic bursts likely to swamp network resources.

17. The system of claim 16 wherein said trigger notifies in real-time said application to reduce said packet transmission rate before queued packets exceeds said threshold level, such that network congestion is foreseen and avoided and said packets are transmitted and received in a lossless manner between said source and said destination.

18. The system of claim 10 wherein said switch identifies flows of packets that are similar in type, source and/or destination, and forwards said flows in a predetermined manner.

19. The system of claim 10 wherein said set of bandwidth allocation rules include executable program instructions on a computer readable medium.