Abstract: This disclosure describes techniques are described for proactively computing configuration information for policy-driven on-demand tunnel creation and deletion between sites in a software-defined networking in wide area network (SD-WAN) environment. In some examples, a controller device is configured to precompute configuration data for an overlay tunnel through the wide area network to connect a first site and a second site of a plurality of sites in the SD-WAN environment. The controller device is further configured to obtain, after precomputing the configuration data, an indication to configure the overlay tunnel. The controller device is also configured to send, in response to receiving the indication to configure the overlay tunnel, at least some of the configuration data to the first site to configure the first site with the overlay tunnel.

Abstract: A system and method for dynamically altering static parameters on a live network device is disclosed. The system includes a live network device having a plurality of parameters configured thereon that control the application of services to subscriber packet flows and a machine learning device operable to monitor the subscriber packet flows and apply a machine learned model to identify patterns in the monitored subscriber pack flows. The machine learning device is further operable to dynamically alter at least one of the plurality of parameters on the network device based upon the patterns in the monitored subscriber packet flows.

Abstract: A system and method for dynamically altering static parameters on a live network device is disclosed. The system includes a live network device having a plurality of parameters configured thereon that control the application of services to subscriber packet flows and a machine learning device operable to monitor the subscriber packet flows and apply a machine learned model to identify patterns in the monitored subscriber pack flows. The machine learning device is further operable to dynamically alter at least one of the plurality of parameters on the network device based upon the patterns in the monitored subscriber packet flows.

Abstract: A network device may receive an IPv6 packet that includes an IPv6 source address and an IPv6 destination address. The network device may determine, based on the IPv6 packet including an extension header that includes an address prefix option, whether to translate the IPv6 packet into an IPv4 packet. Additionally, based on a determination to translate the IPv6 packet into the IPv4 packet, the network device generates an IPv4 packet that includes an IPv4 source address and an IPv4 destination address. Because the PLAT unit may make the determination whether to translate the IPv6 packet into an IPv4 packet based on the IPv6 packet including the address prefix option instead of based on the IPv6 source address including a customer-translation (CLAT) source prefix, it may be unnecessary to distribute the CLAT source prefix to the network device.

Abstract: In general, the disclosure describes techniques for evaluating application quality of experience metrics over a software-defined wide area network. For instance, a network device may receive an application data packet of a data flow. In response to receiving the application data packet, the network device determines whether a packet size of the application data packet is represented in a reference data store. In response to determining that the packet size is not represented in the reference data store, the network device predicts, based on the reference data store, flow metrics for the packet size for each of a plurality of Wide Area Network (WAN) links. The network device selects a WAN link on which to send the application data packet based on the predicted flow metrics.

Abstract: In general, the disclosure describes techniques for evaluating application quality of experience metrics over a software-defined wide area network. For instance, a network device may receive an application data packet of a data flow. In response to receiving the application data packet, the network device determines whether a packet size of the application data packet is represented in a reference data store. In response to determining that the packet size is not represented in the reference data store, the network device predicts, based on the reference data store, flow metrics for the packet size for each of a plurality of Wide Area Network (WAN) links. The network device selects a WAN link on which to send the application data packet based on the predicted flow metrics.

Abstract: A first device may receive a network information request that identifies a data object relating to a network device. The data object may correspond to or identify an attribute associated with the network device. The first device may determine that the attribute is a static attribute relating to a configuration of the network device. The first device may determine whether a second device stores the data object. The second device may store data objects corresponding to static attributes. The first device may selectively obtain the data object from the network device or from the second device based on determining whether the second device stores the data object. The first device may provide the data object based on the network information request.

Abstract: A method may include receiving a first network traffic flow that is associated with a first private network address. The first network traffic flow may be destined to a first external network address. The method may include determining that the first external network address is not identified by a data structure. The data structure may identify external network addresses and private network addresses of network traffic flows to which a single public network address has been assigned. The method may include assigning the single public network address to the first network traffic flow based on determining that the first external network address is not identified by the data structure. The method may include storing the first external network address and the first private network address. The method may include outputting the first network traffic flow with the first external network address and the single public network address.

Abstract: A device may receive a packet associated with a flow and may assign a flow identifier to the flow. The device may generate a first flow record based on a first template. The first flow record may include the flow identifier and a first quantity of fields determined based on the first template. The device may export the first flow record. The device may generate a second flow record, including the flow identifier, based on a second template and after exporting the first flow record. The second flow record may include a second quantity of fields, determined based on the second template, that is less than the first quantity of fields. The device may export the second flow record.

Abstract: A method may include receiving a first network traffic flow that is associated with a first private network address. The first network traffic flow may be destined to a first external network address. The method may include determining that the first external network address is not identified by a data structure. The data structure may identify external network addresses and private network addresses of network traffic flows to which a single public network address has been assigned. The method may include assigning the single public network address to the first network traffic flow based on determining that the first external network address is not identified by the data structure. The method may include storing the first external network address and the first private network address. The method may include outputting the first network traffic flow with the first external network address and the single public network address.