Dynamic QoS controller
AssigneeCharter Communications Operating, LLC
InventorSandeep Reddy Mereddy
Life of this patent
Estimating the term…
Abstract
Various embodiments comprise systems, methods, architectures, mechanisms and apparatus for controlling Quality of Service (QoS) within a service provider network by retrieving from the network QoS related data, processing the retrieved QoS related data via one or more time series prediction algorithm to determine QoS prediction data, and responsively generating network management or configuration commands adapted to ensure continued services delivery in accordance with QoS requirements.
Claims30
A method of controlling Quality of Service (QoS) in a service provider network, comprising
- receiving, from each of a plurality of routers within the service provider network, current utilization level data for each router interface queue supporting a client service;
- receiving topology data indicative of the provider equipment (PE) currently provisioned to support client services within the service provider network;
- determining, for each router interface queue, a respective required QoS;
- using a machine learning model to predict whether any of the router interface queue utilization levels will exceed a threshold utilization level;
- determining, for at least a portion of said router interface queues predicted to exceed the threshold utilization level, one or more network configuration updates operative to constrain router interface queue utilization levels to less than the threshold utilization level;
- and
- transmitting a message configured to invoke the one or more network configuration updates or service configuration updates;
- wherein the machine learning model uses current and historic utilization level data for each router interface queue supporting a client service and the required QoS of the respective supported client service;
- wherein the machine learning model uses network topology data indicative of the provider equipment (PE) supporting the client services supported by the router interface queues.
A computing device configured to communicate with a service provider network to manage Quality of Service (QoS) of router queues therein, the computing device performing a method, comprising
- receiving, from each of a plurality of routers within the service provider network, current utilization level data for each router interface queue supporting a client service;
- receiving topology data indicative of the provider equipment (PE) currently provisioned to support client services within the service provider network;
- determining, for each router interface queue, a respective required QoS;
- using a machine learning model to predict whether any of the router interface queue utilization levels will exceed a threshold utilization level;
- determining, for at least a portion of said router interface queues predicted to exceed the threshold utilization level, one or more network configuration updates operative to constrain router interface queue utilization levels to less than the threshold utilization level;
- and
- transmitting a message configured to invoke the one or more network configuration updates or service configuration updates;
- wherein the machine learning model uses current and historic utilization level data for each router interface queue supporting a client service and the required QoS of the respective supported client service;
- wherein the machine learning model uses network topology data indicative of the provider equipment (PE) supporting the client services supported by the router interface queues.
A Quality of Service (QoS) controller, implemented at a computing device configured to communicate with a service provider network, to manage QoS of router queues therein, the QoS controller performing a method, comprising
- receiving, from each of a plurality of routers within the service provider network, current utilization level data for each router interface queue supporting a client service;
- receiving topology data indicative of the provider equipment (PE) currently provisioned to support client services within the service provider network;
- determining, for each router interface queue, a respective required QoS;
- using a machine learning model to predict whether any of the router interface queue utilization levels will exceed a threshold utilization level;
- determining, for at least a portion of said router interface queues predicted to exceed the threshold utilization level, one or more network configuration updates operative to constrain router interface queue utilization levels to less than the threshold utilization level;
- and
- transmitting a message configured to invoke the one or more network configuration updates or service configuration updates;
- wherein the machine learning model uses current and historic utilization level data for each router interface queue supporting a client service and the required QoS of the respective supported client service;
- wherein the machine learning model uses network topology data indicative of the provider equipment (PE) supporting the client services supported by the router interface queues.
Dependencies are inferred from the claim text.