Abstract: Systems and methods described herein allow a configurable policy for managing Power over Ethernet (PoE) to be implemented by Power Sourcing Equipments (PSEs) across a network. The policy specifies a set of rules for prioritizing power distribution over Ethernet for the computer network. When Powered Devices (PDs) are connected via Ethernet cables to the PSEs, the PDs send identification information about themselves (e.g., device type and location) to the PSEs. The PSEs assign priority levels to the PDs by electronically comparing the identification information to the set of rules. When a present level of available power is insufficient to power all the PDs via PoE, the PSEs use the priority levels to determine which PDs to power down.

Abstract: Systems and methods are provided for dynamic virtual private network concentrators (VPNC) gateway selection and on-demand VRF-ID configuration. A dynamic VPNC gateway selection component can dynamically route to a particular VPNC gateway based on multiple user-specific factors, including: a) behavior of users on the network; and b) performance of a destination service/device. A dynamic VPNC gateway selection component can rank a user based on one or more factors relating to the behavior of the user. Also, the dynamic VPNC gateway selection component can determine whether a VPNC gateway at a data center is healthy, and whether a destination service at the data center is healthy. The dynamic VPNC gateway selection component can dynamically select a VPNC gateway from a plurality of VPNC gateways at the data center for communicating forwarded traffic from the user based on the user's ranking if either the VPNC gateway or the service are unhealthy.

Abstract: Systems and methods are provided for optimizing resource consumption by bringing intelligence to the key allocation process for fast roaming. Specifically, embodiments of the disclosed technology use machine learning to predict which AP a wireless client device will migrate to next. In some embodiments, machine learning may also be used to select a subset of top neighbors from a neighborhood list. Thus, instead of allocating keys for each of the APs on the neighborhood list, key allocation may be limited to the predicted next AP, and the subset of top neighbors. In some embodiments, a reinforcement learning model may be used to dynamically adjust the size of the subset in order to optimize resources while satisfying variable client demand.

Abstract: An example branch gateway includes processing circuitry, memory including instructions, and a plurality of ports. The branch gateway transmits, from a plurality of ports, a first broadcast message. The branch gateway receives, in response to the first broadcast message, response messages on respective ports. The branch gateway determines, based on a receipt order of the response messages, an identifying address from a first response message. The branch gateway assigns the respective port for each response message to a unique VLAN. The branch gateway determines, for each port assigned to a unique VLAN, a link health parameter. The branch gateway selects a primary port to connect to an activation server of a WAN. The branch gateway selects a secondary port to connect to the activation server.

Abstract: A method including receiving, in a controller, from a client device in a network, a resolution query specifying a host name, is provided. The method includes parsing the resolution query to determine whether the host name is associated with an core host or with a public host, and directing the resolution query to a remote domain name system server dedicated to service the core host when the host name is associated with an enterprise name. The method also includes directing the resolution query to a local domain name system server when the host name is associated with a public service provided by the public host. A system to perform the above method is also provided.

Abstract: Some examples relate to identifying a dynamic network parameter probe interval in an SD-WAN. In an example, a controller may define a probe profile of an uplink in the SD-WAN. The probe profile of the uplink may include a static probe interval and a probe retry value. The controller may determine the value of the network parameter for the uplink, prior to expiration of a static probe timer interval. If the value of the network parameter is in negative deviation with a baseline value of the network parameter, the controller may identify a dynamic probe interval for each successive determination of the value of the network parameter. The identification of the dynamic probe interval for a given successive determination may depend on at least one previously determined value of the network parameter. The controller may initiate duplicate network traffic on a secondary uplink in the SD-WAN.

Abstract: Systems and methods are provided for clustering network devices into cohorts. Next, the systems may determine a subset of the network devices between which tunnels are created, based on any of amounts of available memory, jitter, latency, packet loss, and average round trip time. The selective determination may include, determining to create a first tunnel between a first network device of the first cohort and a second network device within the first cohort, and a second tunnel between the first network device and a third network device within the second cohort, and determining not to create tunnels between first remaining network devices of the first cohort and the second set of network devices of the second cohort. The systems provision the tunnel and the second tunnel to transmit data.

Abstract: Some examples relate to managing multicast group traffic. In an example, a switch anchor controller receives a request for a multicast group from an associated network switch in a multicast-capable network. The associated network switch registers to the switch anchor controller in the multicast-capable network. In response to the request, the switch anchor controller selects a non-anchor controller in the multicast-capable network to serve the multicast group to the associated network switch. The switch anchor controller provides the information related to the non-anchor controller to the associated network switch, which in response creates a specific multicast tunnel between the associated network switch and the non-anchor controller to transfer multicast traffic related to the multicast group.

Abstract: Systems and methods are provided for optimizing resource consumption by bringing intelligence to the key allocation process for fast roaming. Specifically, embodiments of the disclosed technology use machine learning to predict which AP a wireless client device will migrate to next. In some embodiments, machine learning may also be used to select a subset of top neighbors from a neighborhood list. Thus, instead of allocating keys for each of the APs on the neighborhood list, key allocation may be limited to the predicted next AP, and the subset of top neighbors. In some embodiments, a reinforcement learning model may be used to dynamically adjust the size of the subset in order to optimize resources while satisfying variable client demand.

Abstract: In an example, a Dynamic Host Configuration Protocol (DHCP) lease request from a client device connected to a network is received. Based on the DHCP lease request, an Internet Protocol (IP) address is assigned to the client device for a lease time. A first lease renewal request is received. A probability of utilization for a lease time block is predicted based on a historical lease pattern, device characteristics, traffic information, and DHCP information. Based on a combination of the probability of utilization and a reward value, the lease time block is allotted for lease renewal. For each allotment, the reward value is adjusted based on deployment characteristics and traffic load in the network, and a network connection duration of the client device. A normalized reward value for the lease time block is determined based on reward values for the lease time block over multiple allotments.

Abstract: Systems and methods are provided for dynamic virtual private network concentrators (VPNC) gateway selection and on-demand VRF-ID configuration. A dynamic VPNC gateway selection component can dynamically route to a particular VPNC gateway based on multiple user-specific factors, including: a) behavior of users on the network; and b) performance of a destination service/device. A dynamic VPNC gateway selection component can rank a user based on one or more factors relating to the behavior of the user. Also, the dynamic VPNC gateway selection component can determine whether a VPNC gateway at a data center is healthy, and whether a destination service at the data center is healthy. The dynamic VPNC gateway selection component can dynamically select a VPNC gateway from a plurality of VPNC gateways at the data center for communicating forwarded traffic from the user based on the user's ranking if either the VPNC gateway or the service are unhealthy.

Abstract: A method is disclosed comprising, checking, at a first node, for receipt of an advertisement message from a second node within an advertisement time interval (102), wherein the first node acts as a backup for the second node in a network. The method further comprises, in response to not receiving the advertisement message within the advertisement time interval (104), sending a probe message to the second node (106) and checking for a response to the probe message from the second node (108).

Abstract: An example branch gateway includes processing circuitry, memory including instructions, and a plurality of ports. The branch gateway transmits, from a plurality of ports, a first broadcast message. The branch gateway receives, in response to the first broadcast message, response messages on respective ports. The branch gateway determines, based on a receipt order of the response messages, an identifying address from a first response message. The branch gateway assigns the respective port for each response message to a unique VLAN. The branch gateway determines, for each port assigned to a unique VLAN, a link health parameter. The branch gateway selects a primary port to connect to an activation server of a WAN. The branch gateway selects a secondary port to connect to the activation server.

Abstract: An end controller, comprising: a processing resource; and a memory resource storing machine-readable instructions to cause the processing resource to: receive, using internet protocol security (IPSec) messages, a plurality of subnetworks that form a route to a branch device via a branch gateway; transfer the plurality of subnetworks to a layer-2-layer-3 module; transfer the plurality of subnetworks to an open shortest path first (OSPF) module; and publish the plurality of subnetworks that form the route to the branch device to a core router using OSPF link state advertisements (LSAs).

Abstract: An example branch gateway includes processing circuitry, memory including instructions, and a plurality of ports. The branch gateway transmits, from a plurality of ports, a first broadcast message. The branch gateway receives, in response to the first broadcast message, response messages on respective ports. The branch gateway determines, based on a receipt order of the response messages, an identifying address from a first response message. The branch gateway assigns the respective port for each response message to a unique VLAN. The branch gateway determines, for each port assigned to a unique VLAN, a link health parameter. The branch gateway selects a primary port to connect to an activation server of a WAN. The branch gateway selects a secondary port to connect to the activation server.

Abstract: Some examples relate to managing multicast group traffic. In an example, a switch anchor controller receives a request for a multicast group from an associated network switch in a multicast-capable network. The associated network switch registers to the switch anchor controller in the multicast-capable network. In response to the request, the switch anchor controller selects a non-anchor controller in the multicast-capable network to serve the multicast group to the associated network switch. The switch anchor controller provides the information related to the non-anchor controller to the associated network switch, which in response creates a specific multicast tunnel between the associated network switch and the non-anchor controller to transfer multicast traffic related to the multicast group.

Abstract: Systems and methods are provided for monitoring a connection state between a primary DHCP server and a secondary DHCP server, determining that a connection between the primary DHCP server and the secondary DHCP server has not been established within a first timeframe, establishing a partner-down operation state at one or more of the primary DHCP server and secondary DHCP server, and, during an established partner-down operation state, issuing/allocating short-term network address leases from one of the primary DHCP servers or secondary DHCP servers. Short-term network leases of the present disclosure may have a duration of between 1 second and 5 minutes.

Abstract: Systems and methods described herein allow a configurable policy for managing Power over Ethernet (PoE) to be implemented by Power Sourcing Equipments (PSEs) across a network. The policy specifies a set of rules for prioritizing power distribution over Ethernet for the computer network. When Powered Devices (PDs) are connected via Ethernet cables to the PSEs, the PDs send identification information about themselves (e.g., device type and location) to the PSEs. The PSEs assign priority levels to the PDs by electronically comparing the identification information to the set of rules. When a present level of available power is insufficient to power all the PDs via PoE, the PSEs use the priority levels to determine which PDs to power down.

Abstract: Some examples relate to identifying a dynamic network parameter probe interval in an SD-WAN. In an example, a controller may define a probe profile of an uplink in the SD-WAN. The probe profile of the uplink may include a static probe interval and a probe retry value. The controller may determine the value of the network parameter for the uplink, prior to expiration of a static probe timer interval. If the value of the network parameter is in negative deviation with a baseline value of the network parameter, the controller may identify a dynamic probe interval for each successive determination of the value of the network parameter. The identification of the dynamic probe interval for a given successive determination may depend on at least one previously determined value of the network parameter. The controller may initiate duplicate network traffic on a secondary uplink in the SD-WAN.

Abstract: A method including receiving, in a controller, from a client device in a network, a resolution query specifying a host name, is provided. The method includes parsing the resolution query to determine whether the host name is associated with an core host or with a public host, and directing the resolution query to a remote domain name system server dedicated to service the core host when the host name is associated with an enterprise name. The method also includes directing the resolution query to a local domain name system server when the host name is associated with a public service provided by the public host. A system to perform the above method is also provided.