Network traffic flow management using machine learning
AssigneeNEC Laboratories America, Inc.
InventorsKonstantinos Kanonakis, Yawei Yin, Mahmoud Sayed
Life of this patent
Estimating the term…
Abstract
A system and method for management of network traffic flow for one or more networks of interconnected computing devices, including predicting one or more types of network traffic data flows using a Machine Learning (ML) classifier, and updating the ML classifier according to identified changes in the network traffic data flows. Using software-defined-networking (SDN) tools and an updated ML classifier, training data is generated to formulate accurate new predictions of the one or more types of network traffic data flows. Network traffic flow is regulated based on the generated new predictions.
Claims20
A computer implemented method for management of network traffic flow for one or more networks of interconnected computing devices, comprising:
- predicting one or more types of network traffic data flows using a Machine Learning (ML) classifier;
- updating the ML classifier according to identified changes in the network traffic data flows;
- using software-defined-networking (SDN) tools and an updated ML classifier, generating training data to formulate accurate new predictions of the one or more types of network traffic data flows;
- and
- regulating network traffic flow based on the generated new predictions.
A system for management of network traffic flow for one or more networks of interconnected computing devices, comprising:
- a Machine Learning (ML) classifier to predict one or more types of network traffic data flows, the ML classifier being updated according to identified changes in the network traffic data flows;
- software-defined-networking (SDN) tools to train and update the ML classifier, wherein training data generated by the SDN tools is employed to formulate accurate new predictions of the one or more types of network traffic data flows;
- and
- a regulator to control network traffic flow based on the generated new predictions.
A computer-readable storage medium comprising a computer readable program, wherein the computer readable program when executed on a computer causes the computer to perform the steps of:
- predicting one or more types of network traffic data flows in a network of interconnected computers using a Machine Learning (ML) classifier;
- updating the ML classifier according to identified changes in the network traffic data flows;
- using software-defined-networking (SDN) tools and an updated ML classifier, generating training data to formulate accurate new predictions of the one or more types of network traffic data flows;
- and
- regulating network traffic flow based on the generated new predictions.
Dependencies are inferred from the claim text.