Systems and methods for a virtual network assistant

Patent metadata

Field	Value
Publication number	US-10985969-B2
Application number	US-201916279243-A
Country	US
Kind code	B2
Filing date	Feb 19, 2019
Priority date	Feb 19, 2019
Publication date	Apr 20, 2021
Grant date	Apr 20, 2021

Abstract

Methods and apparatus for identifying the root cause of deterioration of system level experience (SLE). Offending network components that caused the SLE deterioration are identified and corrective actions are taken.

First claim

The invention claimed is:

1. A method, comprising:
collecting, from each of a plurality of network clients, a plurality of service level experience (SLE) parameter values;
associating each of the collected SLE parameter values with one or more network components;
classifying each of the collected SLE parameter values as either a first class or a second class;
for each of the associated network components:
determining, based on the classification, a first probability that a SLE parameter value associated with the network component is classified as the second class,
determining, based on the classification, a second probability that the plurality of SLE parameter values that are classified as the second class are associated with the network component, and
determining a product of the first probability and the second probability;
determining a probability of failure associated with each of the associated network components based on its respective product;
identifying a network component that is a root cause of a system degradation based on the probabilities of failure; and
initiating, based on the identified network component, a corrective action.

2. The method of claim 1 ,
wherein the plurality of network clients include a plurality of wireless terminals, and the associated network component include an access point associated with each of the plurality of wireless terminals, and the plurality of SLE parameter values include SLE parameter values indicating connection success between the plurality of wireless terminals and the access point and further indicating a quality and amount of data transfer between each of the plurality of wireless terminals and the access point.

3. The method of claim 2 , wherein SLE parameter values indicate one or more of: a user of one or more of the plurality of wireless terminals, a Connected Time of one or more of the plurality of wireless terminals, an IP Address of one or more of the plurality of wireless terminals, a MAC Address of one or more of the plurality of wireless terminals, a Device Type of one or more of the plurality of wireless terminals, and an operating system of one or more of the plurality of wireless terminals.

4. The method of claim 2 , further comprising collecting, from each of the associated network components, a second plurality of SLE parameter values, wherein the classifying further includes the second plurality of SLE parameter values, and wherein the second plurality of SLE parameter values indicate one or more of: a name of the access point, a service set identifier (SSID) of the access point, a channel of communication between the access point and one of the wireless terminals, band, media access control (MAC) information of the access point, and basic service set identifier (BSSID) of the access point.

5. The method of claim 2 , wherein the SLE parameter values indicate one or more of: a received signal strength indicator (RSSI), a signal to noise ratio (SNR), a receiver (Rx) Bit Rate, a transmitter (Tx) Bit Rate, a number of bytes communicated, a received (Rx) Bytes, a transmitted (Tx) Bytes, a number of packets communicated, a number of transmitted packets, or a number of packet retransmissions.

6. The method of claim 1 , wherein the initiating of a corrective action comprises one or more of: displaying a list of network components identified as a root cause, displaying the product associated with one or more of the network components, restarting the identified network component, and/or restarting the identified network component.

7. The method of claim 1 , further comprising: summing the products across the network components; and normalizing each network component's probability by the sum, wherein the probability of failure of each network component is based on the network component's normalized probability.

8. The method of claim 1 , wherein the network components include the plurality of clients.

9. The method of claim 1 , further comprising determining, for each of the associated network components, a mutual information measurement, the mutual information measurement based on a marginal distribution function of the network component, wherein the identifying of the network component that is a root cause of the system degradation is further based on the mutual information measurements.

10. The method of claim 9 , further comprising second identifying network components having a mutual information measurement meeting a criterion and a probability of failure meeting a second criterion, wherein the identifying of the network component that is the root cause of the system degradation is selected from the second identified network components.

11. A system, comprising:
a hardware processor; and memory, the memory storing instructions that when executed configure the hardware processor to perform operations comprising:
collecting, from each of a plurality of network clients, a plurality of service level experience (SLE) parameter values;
associating each of the collected SLE parameter values with one or more network components;
classifying each of the collected SLE parameter values as either a first class or a second class;
for each of the associated network components:
determining, based on the classification, a first probability that a SLE parameter value associated with the network component is classified as the second class,
determining, based on the classification, a second probability that the plurality of SLE parameter values that are classified as the second class are associated with the network component, and
determining a product of the first probability and the second probability;
determining a probability of failure associated with each of the associated network components based on its respective product;
identifying a network component that is a root cause of a system degradation based on the probabilities of failure, and
initiating, based on the identified network component, a corrective action.

12. The system of claim 11 , wherein the plurality of network clients include a plurality of wireless terminals, and the associated network component include an access point associated with each of the plurality of wireless terminals, and the plurality of SLE parameter values include SLE parameter values indicating connection success between the plurality of wireless terminals and the access point and further indicating a quality and amount of data transfer between each of the plurality of wireless terminals and the access point.

13. The system of claim 12 , wherein the SLE parameter values indicate one or more of: a user of one or more of the plurality of wireless terminals, a Connected Time of one or more of the plurality of wireless terminals, an IP Address of one or more of the plurality of wireless terminals, a MAC Address of one or more of the plurality of wireless terminals, a Device Type of one or more of the plurality of wireless terminals, and an operating system of one or more of the plurality of wireless terminals.

14. The system of claim 12 , the operations further comprising collecting, from each of the associated network components, a second plurality of SLE parameter values, wherein the classifying further includes the second plurality of SLE parameter values, and wherein second plurality of SLE parameter values indicate one or more of: a name of the access point, a service set identifier (SSID) of the access point, a channel of communication between the access point and one of the wireless terminals, band, media access control (MAC) information of the access point, and basic service set identifier (BSSID) of the access point.

Assignees

• Mist Systems Inc
• Juniper Networks Inc

Inventors

• Safavi S Ebrahim

Classifications

• H04L43/08

  Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters · CPC title

• H04L41/0895

  Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements · CPC title

• H04L41/40

  using virtualisation of network functions or resources, e.g. SDN or NFV entities · CPC title

• H04L41/0631 Primary

  using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis · CPC title

• H04L41/0886 Primary

  Fully automatic configuration · CPC title