Claims:WE CLAIM:
1. A method of performing intelligent link load balancing in a computer network comprising a plurality of network service providers (NSPs), the method comprising:
monitoring, by a network device, ongoing network traffic transaction data of the computer network;
predicting, by the network device, a current network latency level for the ongoing network traffic transaction data for each of the plurality of NSPs based on a relationship between a network latency level and network traffic transaction data for each of the plurality of NSPs, wherein the relationship is learnt based on an analysis of historical network latency level and historical network traffic transaction data for each of the plurality of NSPs;
determining, by the network device, an optimal NSP to route ongoing network traffic based on an analysis of the current network latency level of each of the plurality of NSPs; and
effecting, by the network device, routing of the ongoing network traffic through the optimal NSP.
2. The method of claim 1, wherein monitoring the ongoing network traffic transaction data further comprises:
acquiring, via the network device, the ongoing network traffic transaction data from the plurality of NSPs; and
storing, via the network device, the ongoing network traffic transaction data in a network traffic transaction database.
3. The method of claim 2, wherein the network traffic transaction database further stores the historical network traffic transaction data.
4. The method of claim 1, wherein the network traffic transaction data or the ongoing network traffic transaction data comprises at least one of a number of packets transported, an available bandwidth, a number of packets dropped, a packet drop time, or a queuing delay.
5. The method of claim 1, wherein the relationship is further learnt based on an analysis of training data, wherein the training data comprises one or more pre-defined labels, or one or more user-defined labels on the historical network latency level or the historical network traffic transaction data for each of the NSPs.
6. The method of claim 5, wherein the training data comprises one or more pre-defined labels, or one or more user-defined labels on at least one of a total number of packets transmitted, a rate of bandwidth, a total number of packets dropped, or a rate of packet dropped.
7. The method of claim 1, further comprising learning the relationship between the network latency level and the network traffic transaction data for each of the plurality of NSPs using a machine learning process.
8. The method of claim 1, wherein determining the optimal NSP further comprises determining, for each of the plurality of NSPs, at least one of a utilization level, a reliability, a load level, or a total number of packets transported in a given bandwidth.
9. The method of claim 8, wherein the optimal NSP is at least one of a least utilized NSP, or a most reliable NSP.
10. A system for performing intelligent link load balancing in a computer network comprising a plurality of network service providers (NSPs), the system comprising:
a network device comprising at least one processor and a computer-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
monitoring ongoing network traffic transaction data of the computer network;
predicting a current network latency level for the ongoing network traffic transaction data for each of the plurality of NSPs based on a relationship between a network latency level and network traffic transaction data for each of the plurality of NSPs, wherein the relationship is learnt based on an analysis of historical network latency level and historical network traffic transaction data for each of the plurality of NSPs;
determining an optimal NSP to route ongoing network traffic based on an analysis of the current network latency level of each of the plurality of NSPs; and
effecting routing of the ongoing network traffic through the optimal NSP.
11. The system of claim 10, wherein monitoring the ongoing network traffic transaction data further comprises:
acquiring the ongoing network traffic transaction data from the plurality of NSPs; and
storing the ongoing network traffic transaction data in a network traffic transaction database.
12. The system of claim 10, wherein the network traffic transaction data or the ongoing network traffic transaction data comprises at least one of a number of packets transported, an available bandwidth, a number of packets dropped, a packet drop time, or a queuing delay.
13. The system of claim 10, wherein the relationship is further learnt based on an analysis of training data, wherein the training data comprises one or more pre-defined labels, or one or more user-defined labels on the historical network latency level or the historical network traffic transaction data for each of the NSPs.
14. The system of claim 13, wherein the training data comprises one or more pre-defined labels, or one or more user-defined labels on at least one of a total number of packets transmitted, a rate of bandwidth, a total number of packets dropped, or a rate of packet dropped.
15. The system of claim 10, wherein the operations further comprise learning the relationship between the network latency level and the network traffic transaction data for each of the plurality of NSPs using a machine learning process.
16. The system of claim 10, wherein determining the optimal NSP further comprises determining, for each of the plurality of NSPs, at least one of a utilization level, a reliability, a load level, or a total number of packets transported in a given bandwidth.

Dated this 25th day of January, 2018

Swetha SN
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
This disclosure relates generally to computer networks, and more particularly to method and system for intelligent link load balancing.