Network system fault resolution via a machine learning model
AssigneeJuniper Networks, Inc.
InventorsJisheng Wang, Xiaoying Wu, Shmuel Shaffer, David Jea
Life of this patent
Estimating the term…
Abstract
Disclosed are embodiments for automatically resolving faults in a complex network system. Some embodiments monitor one or more of system operational parameter values and message exchanges between network components. A machine learning model detects a fault in the complex network system, and an action is selected based on a cause of the fault. After the action is applied to the complex network system, additional monitoring is performed to either determine the fault has been resolved or additional actions are to be applied to further resolve the fault.
Claims18
A network management system comprising processing circuitry configured to:
- obtain, using a machine learning model provided with operational parameter values of one or more network devices of a network system, an indication of a cause of a fault in operation of the network system and a confidence associated with the cause of the fault;
- based on the confidence associated with the cause of the fault not satisfying a fault confidence threshold, determine a diagnostic action cost threshold by:
- based on the confidence associated with the cause of the fault being within a first range, setting the diagnostic action cost threshold to a first value;
- and
- based on the confidence associated with the cause of the fault being within a second range, setting the diagnostic action cost threshold to a second value;
- select a diagnostic action from a plurality of diagnostic actions;
- and
- based on the selected diagnostic action not satisfying the selected diagnostic action cost threshold, perform a rectifying action of a plurality of rectifying actions to rectify the cause of the fault.
A method comprising:
- obtaining, by processing circuitry of a network management system and using a machine learning model provided with operational parameter values of one or more network devices of a network system, an indication of a cause of a fault in operation of the network system and a confidence associated with the cause of the fault;
- based on the confidence associated with the cause of the fault not satisfying a fault confidence threshold, determining, by the processing circuitry, a diagnostic action cost threshold by:
- based on the confidence associated with the cause of the fault being within a first range, setting the diagnostic action cost threshold to a first value;
- and
- based on the confidence associated with the cause of the fault being within a second range, setting the diagnostic action cost threshold to a second value;
- selecting, by the processing circuitry, a diagnostic action from a plurality of diagnostic actions;
- and
- based on the selected diagnostic action not satisfying the selected diagnostic action cost threshold, performing, by the processing circuitry, a rectifying action of a plurality of rectifying actions to rectify the cause of the fault.
A non-transitory, computer-readable medium comprising instructions that, when executed, are configured to cause processing circuitry of a network management system to:
- obtain, using a machine learning model provided with operational parameter values of one or more network devices of a network system, an indication of a cause of a fault in operation of the network system and a confidence associated with the cause of the fault;
- based on the confidence associated with the cause of the fault not satisfying a fault confidence threshold, determine a diagnostic action cost threshold by:
- based on the confidence associated with the cause of the fault being within a first range, setting the diagnostic action cost threshold to a first value;
- and
- based on the confidence associated with the cause of the fault being within a second range, setting the diagnostic action cost threshold to a second value;
- select a diagnostic action from a plurality of diagnostic actions;
- and
- based on the selected diagnostic action not satisfying the selected diagnostic action cost threshold, performing a rectifying action of a plurality of rectifying actions to rectify the cause of the fault.
Dependencies are inferred from the claim text.