Abstract: A device may determine sample points associated with network routes within a network during a time interval, wherein each sample point that is associated with a respective network route comprises an amount of uptime for the respective network route during the time interval and a total frequency of state changes for the respective network route during the time interval. The device may generate, using an unsupervised machine learning mechanism, clusters of the sample points and may label the network routes with route stability labels based at least in part on the clusters. The device may generate, using a supervised machine learning mechanism, a route stability classifier based at least in part on the route stability labels for the network routes, and may determine, using the route stability classifier, a route stability of a new network route within the network.

Abstract: An example method can include tracking, by a network device, a plurality of database operations performed and a plurality of expected database operations for an event that executes for a time period, generating, by the network device, a plurality of clusters based on a ratio of the database operations performed compared to the plurality of expected database operations and the time period for the event, classifying, by the network device, the clusters based on performance, and evaluating, by the network device, a system performance metric based on a classification of real time data into the clusters.

Abstract: An example method can include tracking, by a network device, a plurality of attributes associated with a plurality of unique client device identifiers stored in a tracking table; deriving, by the network device, a training data set based on the plurality of attributes; and generating, by the network device, a plurality of clusters by inputting the derived training data set to an unsupervised machine learning mechanism. The example method can include receiving, by the network device, a labeling of the plurality of unique client device identifiers in the tracking table based at least on the plurality of clusters; generating, by the network device, a plurality of classifiers by inputting the labelled tracking table to a supervised machine learning mechanism; and classifying, by the network device, a new unique client device identifier in the tracking table based at least on the plurality of classifiers.

Abstract: Examples provided herein describe a method for providing security for Internet of Things (IoT) devices. For example, a data packet from an IoT device may be received at an edge device. A signature associated with the IoT device may be accessed at the edge device, where the signature includes network layer information about the IoT device. A set of rules may be applied by the edge device to validate the IoT device based on the accessed signature. Responsive to the IoT device being validated based on the accessed signature, received data packet, and the applied set of rules, the edge device may process the data packet from the IoT device.

Abstract: One embodiment of the present invention provides a switch. The switch includes a storage device, a processing module, and a database module. The storage device can maintain a database storing configuration information for the switch. During operation, the processing module produces a piece of data associated with operations of the switch based on the configuration information. The database module then stores the piece of data in a database table of the database without caching the piece of data in a memory of the switch after the piece of data is stored in the database. In this way, the database module can reduce the memory occupancy of the processing module in comparison with the storage occupancy of a schema corresponding to the database table. Subsequently, the processing module can program a hardware module of the switch with the piece of data prior to receiving an acknowledgment from the database module.

Abstract: An example method can include tracking, by a network device, a plurality of database operations performed and a plurality of expected database operations for an event that executes for a time period, generating, by the network device, a plurality of clusters based on a ratio of the database operations performed compared to the plurality of expected database operations and the time period for the event, classifying, by the network device, the clusters based on performance, and evaluating, by the network device, a system performance metric based on a classification of real time data into the clusters.

Abstract: A device may determine sample points associated with network routes within a network during a time interval, wherein each sample point that is associated with a respective network route comprises an amount of uptime for the respective network route during the time interval and a total frequency of state changes for the respective network route during the time interval. The device may generate, using an unsupervised machine learning mechanism, clusters of the sample points and may label the network routes with route stability labels based at least in part on the clusters. The device may generate, using a supervised machine learning mechanism, a route stability classifier based at least in part on the route stability labels for the network routes, and may determine, using the route stability classifier, a route stability of a new network route within the network.

Abstract: An example method can include tracking, by a network device, a plurality of database operations performed and a plurality of expected database operations for an event that executes for a time period, generating, by the network device, a plurality of clusters based on a ratio of the database operations performed compared to the plurality of expected database operations and the time period for the event, classifying, by the network device, the clusters based on performance, and evaluating, by the network device, a system performance metric based on a classification of real time data into the clusters.

Abstract: A device may determine sample points associated with network routes within a network during a time interval, wherein each sample point that is associated with a respective network route comprises an amount of uptime for the respective network route during the time interval and a total frequency of state changes for the respective network route during the time interval. The device may generate, using an unsupervised machine learning mechanism, clusters of the sample points and may label the network routes with route stability labels based at least in part on the clusters. The device may generate, using a supervised machine learning mechanism, a route stability classifier based at least in part on the route stability labels for the network routes, and may determine, using the route stability classifier, a route stability of a new network route within the network.

Abstract: One embodiment of the present invention provides a switch. The switch includes a storage device, a processing module, and a database module. The storage device can maintain a database storing configuration information for the switch. During operation, the processing module produces a piece of data associated with operations of the switch based on the configuration information. The database module then stores the piece of data in a database table of the database without caching the piece of data in a memory of the switch after the piece of data is stored in the database. In this way, the database module can reduce the memory occupancy of the processing module in comparison with the storage occupancy of a schema corresponding to the database table. Subsequently, the processing module can program a hardware module of the switch with the piece of data prior to receiving an acknowledgment from the database module.

Abstract: A device may track network traffic and may determine sample points associated with a plurality of time intervals, where each sample point from the plurality of sample points that is associated with a respective time interval from the plurality of time intervals comprises a count of packet lengths associated with a plurality of packets that comprise at least a specified portion of total network volume for the respective time interval and a total number of packet lengths observed during the respective time interval. The device may generate a plurality of clusters of the plurality of sample points and may, in response to determining a plurality of new sample points associated with a plurality of new time intervals based on the network traffic, determine a network traffic trend for the network based at least in part on a distribution of the plurality of new sample points within the plurality of clusters.

Abstract: A device may determine sample points associated with network routes within a network during a time interval, wherein each sample point that is associated with a respective network route comprises an amount of uptime for the respective network route during the time interval and a total frequency of state changes for the respective network route during the time interval. The device may generate, using an unsupervised machine learning mechanism, clusters of the sample points and may label the network routes with route stability labels based at least in part on the clusters. The device may generate, using a supervised machine learning mechanism, a route stability classifier based at least in part on the route stability labels for the network routes, and may determine, using the route stability classifier, a route stability of a new network route within the network.

Abstract: An example method can include tracking, by a network device, a plurality of database operations performed and a plurality of expected database operations for an event that executes for a time period, generating, by the network device, a plurality of clusters based on a ratio of the database operations performed compared to the plurality of expected database operations and the time period for the event, classifying, by the network device, the clusters based on performance, and evaluating, by the network device, a system performance metric based on a classification of real time data into the clusters.

Abstract: An example method can include classifying a data set based on a plurality of classifiers generated by inputting the data set into a supervised machine learning mechanism and determining a portion of the classified data set comprises unseen data based on the classification. The unseen data can include data having an attribute not seen by the data set prior to inputting the data set into the supervised machine learning mechanism. The example method can include generating an additional rule based on the unseen data portion, adding the additional rule to the plurality of classifiers, and classifying a new received piece of data based on the plurality of classifiers and the additional rule.

Abstract: An example method can include tracking, by a network device, a plurality of attributes associated with a plurality of unique client device identifiers stored in a tracking table; deriving, by the network device, a training data set based on the plurality of attributes; and generating, by the network device, a plurality of clusters by inputting the derived training data set to an unsupervised machine learning mechanism. The example method can include receiving, by the network device, a labeling of the plurality of unique client device identifiers in the tracking table based at least on the plurality of clusters; generating, by the network device, a plurality of classifiers by inputting the labelled tracking table to a supervised machine learning mechanism; and classifying, by the network device, a new unique client device identifier in the tracking table based at least on the plurality of classifiers.

Abstract: A method, system, and computer-readable storage device for detecting conflicts in a hybrid network device is described herein. A hybrid network device may receive a local controller command from a network management device (e.g., a laptop, operated by a network administrator, executing a command line interface). The hybrid network device may convert the local controller command to a software defined command format. The hybrid network device may detect a lack of conflict between the converted local controller command and active flows represented in an active flow repository. Based on the detected lack of conflict, the hybrid network device may update a traffic forwarding table of the hybrid network device in accordance to the local controller command.

Abstract: A hybrid software defined networking (SDN) switch has a forwarding table including local flow entries and SDN flow entries. In one example, the hybrid SDN switch may send both local flow entries and SDN flow entries to a SDN controller.

Abstract: In one example, a software-defined networking (SDN) controller can access flow capability information for flow paths along network data path elements in the control plane of the SDN controller. The SDN controller can determine network compatibility for an SDN controller application based on whether the accessed flow capability information fails to meet a flow requirement for the application. The SDN controller can further notify the application when it is determined that the flow requirements for the application are not met by a flow path. Related methods and machine-readable storage mediums are also described.

Abstract: A match field and an action for a flow rule may be received from a software defined networking application. A mapping of table identifications to attributes may be analyzed to obtain a table identification. The table identification may be for a pipeline table of a network device. The pipeline table may be able to implement the match field and the action.

Abstract: A hybrid software defined networking (SDN) switch has a forwarding table including local flow entries and SDN flow entries. In one example, the hybrid SDN switch may send both local flow entries and SDN flow entries to a SDN controller.