Automatic detection and tracking of anomalous rectifiable paths using time-series dynamics
AssigneeCisco Technology, Inc.
InventorsJean-Philippe Vasseur, Sambarta Dasgupta, Vinay Kumar Kolar
Life of this patent
Estimating the term…
Abstract
In one embodiment, a device computes time series dynamics for a performance metric of a path in a network used to convey traffic for an online application. The device matches those time series dynamics to one or more dynamics categories. The device makes a determination as to whether the path in the network is anomalous, based on the one or more dynamics categories. The device provides, based on the determination, an indication that the path in the network is anomalous for display.
Claims16
A method comprising:
- computing, by a device, time series dynamics for a performance metric of a path in a network used to convey traffic for an online application;
- matching, by the device, those time series dynamics to one or more dynamics categories that represent one or more categories of temporal evolution of the performance metric over time, wherein the one or more dynamics categories comprise at least one of:
- a simple periodic category, a non-linear periodic category, or a linear autoregressive flat category;
- making, by the device, a determination as to whether the path in the network is anomalous, based on the one or more dynamics categories for the performance metric having changed to a different one or more dynamics categories;
- providing, by the device and based on the determination, an indication that the path in the network is anomalous for display;
- and
- confirming, by the device, whether a rectification action for the path has caused the path to become non-anomalous.
An apparatus, comprising:
- one or more network interfaces;
- a processor coupled to the one or more network interfaces and configured to execute one or more processes;
- and
- a memory configured to store a process that is executable by the processor, the process when executed configured to:
- compute time series dynamics for a performance metric of a path in a network used to convey traffic for an online application;
- match those time series dynamics to one or more dynamics categories that represent one or more categories of temporal evolution of the performance metric over time, wherein the one or more dynamics categories comprise at least one of:
- a simple periodic category, a non-linear periodic category, or a linear autoregressive flat category;
- make a determination as to whether the path in the network is anomalous, based on the one or more dynamics categories for the performance metric having changed to a different one or more dynamics categories;
- provide, based on the determination, an indication that the path in the network is anomalous for display;
- and
- confirm whether a rectification action for the path has caused the path to become non-anomalous.
A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
- computing, by the device, time series dynamics for a performance metric of a path in a network used to convey traffic for an online application;
- matching, by the device, those time series dynamics to one or more dynamics categories that represent one or more categories of temporal evolution of the performance metric over time, wherein the one or more dynamics categories comprise at least one of:
- a simple periodic category, a non-linear periodic category, or a linear autoregressive flat category;
- making, by the device, a determination as to whether the path in the network is anomalous, based on the one or more dynamics categories for the performance metric having changed to a different one or more dynamics categories;
- providing, by the device and based on the determination, an indication that the path in the network is anomalous for display;
- and
- confirming, by the device, whether a rectification action for the path has caused the path to become non-anomalous.
Dependencies are inferred from the claim text.