IP Library › Granted Patent US 11,831,491
Granted Patent B2
US 11,831,491 · App. 17/488,268 · Granted Nov 28, 2023

System and methods to validate issue detection and classification in a network assurance system

Inventors: Waseem A Siddiqi (Campbell, CA); Rajesh S. Pazhyannur (Fremont, CA); Kedar Krishnanand Gaonkar (San Jose, CA); Aruna Nukala (Fremont, CA)
Assignee: Cisco Technology, Inc.
H04L41/0677H04L41/145H04L41/22H04W84/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,831,491
App. No.
17/488,268
Granted
Nov 28, 2023
Kind
B2
Abstract

Systems, methods and computer-readable storage media are provided for detecting and simulating issues in a network. The methodology includes identifying: event sequences within network traffic data; filtering out a subset of the event sequences based on characteristics of the subset of the event sequences; generating definition groups by performing clustering on the subset of the event sequences, the definition groups comprising event sequence characteristics associated with one or more network issues; first simulating the subset of the event sequences; generating, based on results of the first simulating, a first issue identification; second simulating a most recent one of the identified event sequences; generating, based on results of the second simulating and the generated definition groups, a second issue identification; and validating the first issue identification with the second issue identification.

Claims (46)

1. A computer-implemented method comprising:

identifying event sequences within network traffic data;

filtering out a subset of the event sequences based on characteristics of the subset of the event sequences;

generating definition groups by performing clustering on the subset of the event sequences, the definition groups comprising event sequence characteristics associated with one or more network issues;

first simulating the subset of the event sequences;

generating, based on results of the first simulating, a first issue identification;

second simulating a most recent one of the identified event sequences;

generating, based on results of the second simulating and the generated definition groups, a second issue identification; and

validating the first issue identification with the second issue identification.

2. The method of claim 1 , wherein the issue simulation engine includes a client simulation for simulating a portion of the event sequences from a client device perspective.

3. The method of claim 1 , wherein the definition groups are associated with onboarding failures.

4. The method of claim 3 , wherein the onboarding failures comprise an excess onboarding transaction.

5. The method of claim 1 , wherein the network traffic data is generated by network devices comprising one of a wireless local area network controller (WLC) or an access point (AP).

6. The method of claim 1 , wherein the network traffic data comprises a data model including one of a wireless client state, client statistics, AP radio frequency (RF) statistics, an over air packet capture, a network services key performance indicator (KPI), or a device health KPI.

7. The method of claim 1 , further comprising generating a first issue identification by applying a rules-based issue identification process to the simulated event sequences.

8. A non-transitory media storing instructions that when executed by a processor of a system cause the system to perform operations comprising:

identify event sequences within network traffic data;

filter out a subset of the event sequences based on characteristics of the subset of the event sequences;

generate definition groups by performing clustering on the subset of the event sequences, the definition groups comprising event sequence characteristics associated with one or more network issues;

first simulate the subset of the event sequences

generate, based on results of the first simulating, a first issue identification;

second simulate a most recent one of the identified event sequences;

generate, based on results of the second simulating and the generated definition groups, a second issue identification; and

validate the first issue identification with the second issue identification.

9. The non-transitory media of claim 8 , wherein the issue simulation engine includes a client simulation for simulating a portion of the event sequences from a client device perspective.

10. The non-transitory media of claim 8 , wherein the definition groups are associated with onboarding failures.

11. The non-transitory media of claim 10 , wherein the onboarding failures comprise an excess onboarding transaction.

12. The non-transitory media of claim 8 , wherein the network traffic data is generated by network devices comprising one of a wireless local area network controller (WLC) or an access point (AP).

13. The non-transitory media of claim 8 , wherein the network traffic data comprises a data model including one of a wireless client state, client statistics, AP radio frequency (RF) statistics, an over air packet capture, a network services key performance indicator (KPI), or a device health KPI.

14. The non-transitory media of claim 8 , the operations further comprising generate a first issue identification by applying a rules-based issue identification process to the simulated event sequences.

15. A system, comprising:

a processor:

a non-transitory media storing instructions that when executed by a processor of a system cause the system to perform operations comprising:

identify event sequences within network traffic data;

filter out a subset of the event sequences;

generate definition groups by performing clustering on the subset of the event sequences, the definition groups comprising event sequence characteristics associated with one or more network issues;

first simulate the subset of the event sequences

generate, based on results of the first simulating, a first issue identification;

second simulate a most recent one of the identified event sequences;

generate, based on results of the second simulating and the generated definition groups, a second issue identification; and

validate the first issue identification with the second issue identification.

16. The system of claim 15 , wherein the issue simulation engine includes a client simulation for simulating a portion of the event sequences from a client device perspective.

17. The system of claim 15 , wherein the definition groups are associated with onboarding failures.

18. System of claim 17 , wherein the onboarding failures comprise an excess onboarding transaction.

19. The system of claim 15 , wherein the network traffic data is generated by network devices comprising one of a wireless local area network controller (WLC) or an access point (AP).

20. The system of claim 15 , wherein the network traffic data comprises a data model including one of a wireless client state, client statistics, AP radio frequency (RF) statistics, an over air packet capture, a network services key performance indicator (KPI), or a device health KPI.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 28, 2021
From: SIDDIQI, WASEEM A; PAZHYANNUR, RAJESH S.; GAONKAR, KEDAR KRISHNANAND; NUKALA, ARUNA
To: CISCO TECHNOLOGY, INC.
Reel/Frame 057631/0074 →
Continuity (3)
Continuation 16393162 · Apr 24, 2019
Provisional Application 62770279 · Nov 21, 2018
Related Publication 20220021574A1 · Jan 20, 2022
Cited By (2)
US 12,401,578 US 12,549,464