20240039856. AUTO-DETECTION OF APPLICATION FAILURES FOR FORECASTING NETWORK PATH PERFORMANCE simplified abstract (Cisco Technology, Inc.)
AUTO-DETECTION OF APPLICATION FAILURES FOR FORECASTING NETWORK PATH PERFORMANCE
Organization Name
Inventor(s)
Romain Kakko-chiloff of Paris (FR)
Mukund Yelahanka Raghuprasad of San Jose CA (US)
Vinay Kumar Kolar of San Jose CA (US)
Jean-Philippe Vasseur of Saint Martin d’Uriage (FR)
AUTO-DETECTION OF APPLICATION FAILURES FOR FORECASTING NETWORK PATH PERFORMANCE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240039856 titled 'AUTO-DETECTION OF APPLICATION FAILURES FOR FORECASTING NETWORK PATH PERFORMANCE
Simplified Explanation
The patent application describes a device that provides a user interface with a timeseries display showing the probability of a network path violating a service level agreement (SLA) associated with an online application. The device receives thresholds from the user interface, which define periods of time when the application experience is believed to be degraded. Based on these thresholds, the device trains a machine learning model to predict when the application experience will be degraded. It then uses a predictive routing engine to reroute traffic of the online application based on the model's prediction.
- The device provides a timeseries display of the probability of a network path violating an SLA for an online application.
- Thresholds are received from the user interface to define periods of degraded application experience.
- A machine learning model is trained based on the thresholds to predict when the application experience will be degraded.
- The predictive routing engine is used to reroute traffic based on the model's prediction.
Potential applications of this technology:
- Network management systems can use this technology to proactively reroute traffic and maintain a high-quality application experience.
- Cloud service providers can utilize this technology to ensure SLAs are met and minimize disruptions for their customers.
- Online gaming platforms can benefit from this technology to optimize network paths and reduce lag for players.
Problems solved by this technology:
- It addresses the challenge of predicting and preventing degraded application experience caused by network path violations.
- It helps in proactively managing network traffic to maintain SLAs and avoid service disruptions.
- It enables efficient resource allocation and optimization in network management systems.
Benefits of this technology:
- Improved user experience by minimizing application performance degradation.
- Enhanced reliability and availability of online applications by proactively rerouting traffic.
- Efficient utilization of network resources by dynamically adapting to changing network conditions.
Original Abstract Submitted
in one embodiment, a device provides, to a user interface, a timeseries for display of a probability over time of a network path violating a service level agreement (sla) associated with an online application. the device receives, from the user interface, a plurality of thresholds for the timeseries that define periods of time during which application experience of the online application is believed to be degraded. the device trains, based on the plurality of thresholds, a machine learning model to predict when the application experience of the online application will be degraded. the device causes a predictive routing engine to reroute traffic of the online application based on a prediction by the machine learning model that the application experience of the online application will be degraded.
