Dynamic network-driven application packet resizing

• US 9,485,153 B2
• Filed: 01/27/2014
• Issued: 11/01/2016
• Est. Priority Date: 01/06/2014
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Vasseur, Jean-Philippe, Dasgupta, Sukrit, Mermoud, Grgory
• Primary Examiner(s): Jung, Min
• Application Number:
  US14/164,622
• Publication Number:
  US 20150195212A1
• Time in Patent Office: 1,009 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/5025 by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 45/70 Routing based on monitoring results
• CPC Class Codes: H04L 47/122 by diverting traffic away from congested entities
• CPC Class Codes: H04L 47/365 Dynamic adaptation of the packet size
• CPC Class Codes: H04W 24/02 Arrangements for optimising operational condition
• CPC Class Codes: H04W 24/04 Arrangements for maintaining operational condition
• CPC Class Codes: Y04S 40/00 Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them

Abstract

In one embodiment, information relating to network metrics in a computer network is collected. A packet delay for a packet to be transmitted along a particular communication path is predicted based on the network metrics. Then, an optimal packet size for optimizing a transmission experience of the packet to be transmitted along the particular communication path is calculated based on the predicted packet delay. Also, a size of the packet to be transmitted along the particular communication path is dynamically adjusted based on the calculated optimal packet size.

Claims

1. A method, comprising:

collecting, by a learning machine, information relating to network metrics in a computer network;

predicting, by the learning machine, a packet delay for a packet to be transmitted along a particular communication path based on the network metrics, wherein the predicting includes;

building, by the learning machine, a predictive model that takes into account packet size by inputting the collected network metrics into an engine, which then yields a prediction of the packet delay, and

calculating, by the learning machine, an optimal packet size for optimizing a transmission experience of the packet to be transmitted along the particular communication path based on the predicted packet delay; and

sending instructions to an application that will be transmitting the packet that instruct the application to dynamically adjust a size of the packet to be transmitted along the particular communication path based on the calculated optimal packet size determined from the predictive model.

2. The method as in claim 1, further comprising:

sending an instruction to a source node that transmits the packet to adjust the size of the packet based on observed network conditions.

3. The method as in claim 2, wherein the observed network conditions are proximate to one or more of a location of the source node, the particular communication path, and a location of a destination node that receives the packet.

4. The method as in claim 1, further comprising:

observing current network conditions in the network; and

calculating the optimal packet size for optimizing the transmission experience of the packet based further on the observed current network conditions.

5. The method as in claim 1, wherein the optimizing of the transmission experience comprises one or more of:

reducing packet delay, improving a transmission success rate, reducing a transmission time, reducing collisions, and reducing packet loss.

6. The method as in claim 1, further comprising:

accessing a service level agreement (SLA) in the network;

determining one or more SLA requirements according to the SLA; and

calculating the optimal packet size for optimizing the transmission experience of the packet based further on the determined SLA requirement.

7. The method as in claim 6, wherein the SLA is associated with one or more of a source node that transmits the packet and a destination node that receives the packet.

8. The method as in claim 1, further comprising:

dynamically adjusting the size of the packet at one or more times during a lifetime of the packet.

9. The method as in claim 1, further comprising:

receiving feedback regarding the dynamically adjusted size of the packet to be transmitted along the particular communication path; and

calculating the optimal packet size based further on the received feedback.

10. The method as in claim 1, further comprising:

sending artificial packets of varying sizes in the computer network in order to construct the predictive model.

11. An apparatus, comprising:

one or more network interfaces that communicate with a computer network;

a processor coupled to the one or more network interfaces and configured to execute a process; and

a memory configured to store program instructions which contain the process executable by the processor, the process comprising;

collecting information relating to network metrics in the computer network;

predicting a packet delay for a packet to be transmitted along a particular communication path based on the network metrics, wherein the predicting includes;

building a predictive model that takes into account packet size by inputting the collected network metrics into an engine, which then yields a prediction of the packet delay, and

calculating an optimal packet size for optimizing a transmission experience of the packet to be transmitted along the particular communication path based on the predicted packet delay; and

sending instructions to an application that will be transmitting the packet that instruct the application to dynamically adjust a size of the packet to be transmitted along the particular communication path based on the calculated optimal packet size,

wherein the apparatus is a learning machine.

12. The apparatus as in claim 11, wherein the process further comprises:

sending an instruction to a source node that transmits the packet to adjust the size of the packet based on observed network conditions.

13. The apparatus as in claim 12, wherein the observed network conditions are proximate to one or more of a location of the source node, the particular communication path, and a location of a destination node that receives the packet.

14. The apparatus as in claim 11, wherein the process further comprises:

observing current network conditions in the network; and

calculating the optimal packet size for optimizing the transmission experience of the packet based further on the observed current network conditions.

15. The apparatus as in claim 11, wherein the optimizing of the transmission experience comprises one or more of:

reducing packet delay, improving a transmission success rate, reducing a transmission time, reducing collisions, and reducing packet loss.

16. The apparatus as in claim 11, wherein the process further comprises:

accessing a service level agreement (SLA) in the network;

determining one or more SLA requirements according to the SLA; and

calculating the optimal packet size for optimizing the transmission experience of the packet based further on the determined SLA requirement.

17. The apparatus as in claim 16, wherein the SLA is associated with one or more of a source node that transmits the packet and a destination node that receives the packet.

18. The apparatus as in claim 11, wherein the process further comprises:

dynamically adjusting the size of the packet at one or more times during a lifetime of the packet.

19. The apparatus as in claim 11, wherein the process further comprises:

receiving feedback regarding the dynamically adjusted size of the packet to be transmitted along the particular communication path; and

calculating the optimal packet size based further on the received feedback.

20. The apparatus as in claim 11, wherein the process further comprises:

sending artificial packets of varying sizes in the network in order to construct the predictive model.

21. A tangible non-transitory computer readable medium storing program instructions that cause a learning machine to execute a process, the process comprising:

collecting information relating to network metrics in a computer network;

predicting a packet delay for a packet to be transmitted along a particular communication path based on the network metrics, wherein the predicting includes;

building, by the learning machine, a predictive model that takes into account packet size by inputting the collected network metrics into an engine, which then yields a prediction of the packet delay, and

calculating an optimal packet size for optimizing a transmission experience of the packet to be transmitted along the particular communication path based on the predicted packet delay; and

sending instructions to an application that will be transmitting the packet that instruct the application to dynamically adjust a size of the packet to be transmitted along the particular communication path based on the calculated optimal packet size.