Techniques for improved routing based on network traffic are provided. Telemetry data relating to a first network node of a plurality of network nodes in a locator ID separation protocol (LISP) fabric is received. A first portion of the telemetry data that relates to a first destination of a plurality of destinations is identified. Further, a first routing weight associated with a first interface of the first network node is revised based on the first portion of the telemetry data, where the first interface is associated with the first destination. The revised first routing weight is published to a second plurality of network nodes in the LISP fabric, wherein the second plurality of network nodes route packets to the first network node based in part on the revised first routing weight.

A system and methods for mobile device active callback prioritization, utilizing an enhanced callback prioritization engine operating on a user's mobile device for integration through the operating system and software applications operating on the device, wherein the enhanced callback prioritization engine receives intercepted data or voice messages sent to the mobile device, retrieves and aggregates data related to the assigned messages, inputs the assigned data message and aggregate data into one or more machine learning algorithms wherein the algorithms may analyze the input data, the results of the analysis may be used to compute a priority score for the assigned data message, and generates a callback list from the computed prioritization score. The priority score is in part based on 3rd party application data related to the data or voice messages providing context to the machine learning algorithms.

Various example embodiments for supporting multi-tier deterministic networking are presented. Various example embodiments for supporting multi-tier deterministic networking may be configured to support provisioning of deterministic flows in multi-tier deterministic networking. Various example embodiments for supporting multi-tier deterministic networking may be configured to support adaptive deterministic routing in multi-tier deterministic networks. Various example embodiments for supporting multi-tier deterministic networking may be configured to support score-based deterministic routing in multi-tier deterministic networks. Various example embodiments for supporting multi-tier deterministic networking may be configured to support adaptive deterministic routing and/or score-based deterministic routing in multi-tier deterministic networks based on analysis of a state representation for path and/or sub-path selection in multi-tier deterministic networks. Various example embodiments for supporting multi-tier deterministic networking may be configured to support hierarchical resource allocation and deallocation in multi-tier deterministic networking, optimal route finding in multi-tier deterministic networking, and so forth.

A system that includes a data source, a plurality of network devices, a routing device, and a network analysis device. The network analysis device is configured to obtain metric information that is associated with a plurality of messages and to input the metric information into a first machine learning model that outputs a traffic volume classification based on the metric information. The network analysis device is further configured to obtain bandwidth information that is associated with the plurality of network devices and to input the bandwidth information and the traffic volume classification into a second machine learning model that outputs routing recommendations based on the bandwidth information and the traffic volume classification. The network analysis device is further configured to generate routing instructions based on the routing recommendations and to reconfigure the routing device based on the routing instructions.

In one embodiment, a device uses a multi-armed bandit model to select different network paths over time via which traffic associated with an online application is routed. The device obtains, from a provider of the online application, application experience metrics associated with the different network paths and indicative of user satisfaction with the online application. The device learns, by the multi-armed bandit model, which of the different network paths will provide satisfactory application experience metrics, based on the application experience metrics associated with the different network paths. The device causes the traffic associated with the online application to be routed via a set of one or more paths expected by the multi-armed bandit model to provide satisfactory application experience metrics for the online application.

A multicast group creation method, a multicast group joining method, and an apparatus, where the multicast group creation method includes: a user multicast source terminal sending a first request message to a first control plane network element to request creation of a multicast group; the first control plane network element sending a second request message to a second control plane network element to request creation of the multicast group; the second control plane network element determining that a next-hop user plane network element of the second user plane network element is a first user plane network element, and then sending information about the first user plane network element to the first control plane network element, which indicates the second user plane network element to send a multicast packet received from the terminal to the first user plane network element.

In order to provide an information processing apparatus that easily finds a network configuration corresponding to characteristics of a terminal to be connected, the information processing apparatus includes a model generation section and a specifying section, the model generation section being configured to generate a traffic pattern generation model, based on learning of a traffic pattern of a terminal, and the specifying section being configured to specify traffic for an output of the traffic pattern generation model, based on virtual traffic in the traffic pattern generation model. The information processing apparatus may further include a packet generation section configured to generate a packet, based on the specified traffic.

In one embodiment, a device uses a classification model to determine whether implementation of a routing change suggested by a predictive routing engine for a network will result in a violation of one or more network policies. The device computes a trust score, based on performance metrics for the classification model. The device causes, based in part on the trust score, implementation of the routing change in the network, when the classification model determines that application of the routing change will not result in a violation of the one or more network policies.

In one embodiment, a device computes an efficiency metric regarding ingestion of telemetry data from a particular portion of a network by a predictive routing engine used to make predictive routing decisions for that portion of the network. The device makes a comparison between the efficiency metric and one or more control rules. The device determines, based on the comparison, whether ingestion of the telemetry data from the particular portion of the network by the predictive routing engine should be disabled. The device causes the predictive routing engine to stop ingesting telemetry data from the particular portion of the network.

A network device includes a forwarding plane and an artificial intelligence (AI) circuit. The forwarding plane is coupled to the AI circuit. The AI circuit is configured to process data about network packets from the forwarding plane using a first AI algorithm. The forwarding plane may be directly coupled to the AI circuit, and the forwarding plane may further pre-process the network packets to obtain the data about the network packets.