Closed loop prefix management and controller for whiteboxes

Patent metadata

Field	Value
Publication number	US-11595308-B2
Application number	US-201916440185-A
Country	US
Kind code	B2
Filing date	Jun 13, 2019
Priority date	Jun 13, 2019
Publication date	Feb 28, 2023
Grant date	Feb 28, 2023

Abstract

A system for closed loop prefix management for white boxes includes a network device, a route reflector coupled to the network device, a software defined network controller coupled to the route reflector and the network device, and a prefix usage analyzer in the software defined network controller. The prefix usage analyzer determines usage attributes of prefixes and identifies the prefixes with a predetermined usage attribute. The software defined network controller instructs a network controller in the network device to store the prefixes with the predetermined usage attributes in a table in the network device.

First claim

What is claimed:

1. A method comprising:
measuring, by a processing system including a processor, a usage attribute for each prefix in a set of prefixes used in traffic through a network device to obtain network usage information, wherein the usage attribute is either a volume of traffic using each prefix or a frequency of use for each prefix;
analyzing, by the processing system, the network usage information to generate a network usage prediction;
predicting, by the processing system in accordance with the network usage prediction, a subset of the set of prefixes having a predetermined usage attribute to generate a prefix list for use during a first predetermined time period;
sending, by the processing system, instructions to the network device to store the prefix list with the predetermined usage attribute in a table in the network device, resulting in the table including less than the set of prefixes and using a reduced table memory;
updating, by the processing system, the prefix list to generate an updated prefix list for use during a second predetermined time period subsequent to the first predetermined time period; and
detecting, by the processing system, a network traffic anomaly in accordance with a difference between the prefix list and the updated prefix list being greater than an expected difference between the prefix list and the updated prefix list.

2. The method of claim 1 , wherein the measuring the usage attribute comprises measuring a frequency of use of each prefix used in the traffic through the network device.

3. The method of claim 1 , wherein the sending instructions to the network device comprises sending the instructions to a network controller in the network device to store the prefix list.

4. The method of claim 1 , wherein the predicting the subset of prefixes comprises using machine learning analytics based on a machine learning algorithm.

5. A system comprising:
a network device;
a route reflector coupled to the network device;
a software defined network controller coupled to the route reflector and the network device; and
a prefix usage analyzer in the software defined network controller, wherein the prefix usage analyzer measures a volume of traffic using each prefix of a set of prefixes or a frequency of use for each prefix of the set of prefixes to obtain network usage information, analyzes the network usage information to generate a network usage prediction, and predicts, in accordance with the network usage prediction, a subset of prefixes of the set of prefixes for use during a first predetermined time period,
wherein each prefix of the subset of prefixes has a predetermined usage attribute, and wherein the subset of prefixes comprises a prefix list for storage in a table in the network device, resulting in the table including less than the set of prefixes and using a reduced table memory, and
wherein the prefix usage analyzer updates the prefix list to generate an updated prefix list for use during a second predetermined time period subsequent to the first predetermined time period, and detects a network traffic anomaly in accordance with a difference between the prefix list and the updated prefix list being greater than an expected difference between the prefix list and the updated prefix list.

6. The system of claim 5 wherein the network device is a router.

7. The system of claim 5 wherein the prefix usage analyzer comprises a collector for collecting prefixes with the predetermined usage attribute.

8. The system of claim 5 , wherein the prefix usage analyzer measures a frequency of use of each prefix used in the traffic through the network device.

9. A non-transitory machine-readable medium comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations comprising:
measuring a usage attribute for each prefix in a set of prefixes used in traffic through a network device to obtain network usage information;
analyzing the network usage information to generate a network usage prediction;
predicting, in accordance with the network usage prediction, a subset of prefixes of the set of prefixes having a predetermined usage attribute to generate a prefix list for use during a first predetermined time period;
sending instructions to the network device to store the prefix list in a table in the network device, resulting in the table including less than the set of prefixes and using a reduced table memory, wherein the usage attribute comprises either a volume of traffic using each prefix of the set of prefixes or a frequency of use for each prefix of the set of prefixes;
updating the prefix list to generate an updated prefix list for use during a second predetermined time period subsequent to the first predetermined time period; and
detecting a network traffic anomaly in accordance with a difference between the prefix list and the updated prefix list being greater than an expected difference between the prefix list and the updated prefix list.

10. The non-transitory machine-readable medium of claim 9 wherein the measuring the usage attribute comprises measuring a frequency of use of each prefix used in the traffic through the network device.

11. The non-transitory machine-readable medium of claim 9 wherein the sending instructions to the network device comprises sending instructions to a network controller in the network device to store the prefix list.

12. The non-transitory machine-readable medium of claim 9 wherein the predicting the subset of prefixes comprises using machine learning analytics based on a machine learning algorithm.

13. The method of claim 4 , further comprising providing, by the processing system, analysis results regarding the predicting for use by a user of the processing system to verify automated decisions of the machine learning algorithm.

14. The method of claim 1 , wherein the network traffic anomaly comprises a directed denial of service attack.

15. The method of claim 1 , wherein the second predetermined time period is successive to the first predetermined time period.

16. The system of claim 5 , wherein the prefix usage analyzer predicts the subset of prefixes using machine learning analytics based on a machine learning algorithm.

17. The system of claim 16 , wherein the prefix usage analyzer provides analysis results regarding the subset of prefixes for use by a user of the system to verify automated decisions of the machine learning algorithm.

18. The system of claim 5 , wherein the second predetermined time period is successive to the first predetermined time period.

19. The non-transitory machine-readable medium of claim 9 , wherein the operations further comprise providing analysis results regarding the predicting for use by a user of the processing system to verify automated decisions of a machine learning algorithm.

20. The non-transitory machine-readable medium of claim 9 , wherein the second predetermined time period is successive to the first predetermined time period.

Assignees

• At & T Ip I Lp

Inventors

• Koral Yaron
• Monetti Steven A
• Nguyen Han
• Meier-Hellstern Kathleen
• Koch Richard
• Tse Simon

Classifications

• H04L47/11 Primary

  Identifying congestion · CPC title

• H04L43/0876

  Network utilisation, e.g. volume of load or congestion level · CPC title