Automatic detection and prevention of network overload conditions using sdn
AssigneeAT&T Intellectual Property I, L.P.
InventorsSun-Uk Park, Minh Huynh, Ashima Mangla
Life of this patent
Estimating the term…
Abstract
A controller node in a network implementing software defined networking (SDN) proactively detects network overload conditions in a target node and subsequently prevents the conditions from developing by launching a new virtual network node. The detection and prevention are based on the determination of a probability of failure of the target node as a weighted function of information from the target node and probabilities of failure of related nodes.
Claims20
A method for mitigating network overload conditions at a target network node in a communications network, comprising:
- by a controller node of the communications network, monitoring key performance indicators of a plurality of network nodes related to the target network node;
- by the controller node, based on the key performance indicators of the plurality of network nodes related to the target network node, computing probabilities of failure of each of the network nodes related to the target node;
- by the controller node, monitoring key performance indicators of the target network node;
- by the controller node, computing a probability of failure of the target network node based on the key performance indicators of the target network node and further based on the probabilities of failure of the nodes related to the target network node, weighted by a closeness of relationships to the target network node;
- making a determination that the probability of failure of the target network node exceeds a threshold;
- and
- based on the determination, spawning a new instance of the target network node.
A network controller software node of a communications network, comprising:
- at least one processor;
- at least one network interface;
- and
- at least one computer readable storage device having stored thereon computer readable instructions that, when executed by the at least one processor, cause the at least one processor to perform operations for mitigating network overload conditions at a target network node in a communications network comprising:
- monitoring key performance indicators of a plurality of network nodes related to the target network node;
- based on the key performance indicators of the plurality of network nodes related to the target network node, computing probabilities of failure of each of the network nodes related to the target node;
- monitoring key performance indicators of the target network node;
- computing a probability of failure of the target network node based on the key performance indicators of the target network node and further based on the probabilities of failure of the nodes related to the target network node, weighted by a closeness of relationships to the target network node;
- making a determination that the probability of failure of the target network node exceeds a threshold;
- and
- based on the determination, spawning a new instance of the target network node.
A tangible computer-readable medium having stored thereon computer readable instructions for mitigating network overload conditions at a target network node in a communications network, wherein execution of the computer readable instructions by a processor causes the processor to perform operations comprising:
- monitoring key performance indicators of a plurality of network nodes related to the target network node;
- based on the key performance indicators of the plurality of network nodes related to the target network node, computing probabilities of failure of each of the network nodes related to the target node;
- monitoring key performance indicators of the target network node;
- computing a probability of failure of the target network node based on the key performance indicators of the target network node and further based on the probabilities of failure of the nodes related to the target network node, weighted by a closeness of relationships to the target network node;
- making a determination that the probability of failure of the target network node exceeds a threshold;
- and
- based on the determination, spawning a new instance of the target network node.
Dependencies are inferred from the claim text.