Abstract: Presented herein are techniques to analyze network traffic and equipment based on telemetry generated by a plurality of network devices. A method includes generating first telemetry at a first network device, receiving, at the first network device, via an Internet Protocol anycast addressing scheme, at least one of second telemetry generated at a second network device, and third telemetry generated at a third network device, performing, on the first network device using a local processing unit, first analytics on the first telemetry, performing, on the first network device using the local processing unit, second analytics on the at least one of the second telemetry and the third telemetry, and transmitting data resulting from the first analytics and the second analytics to a fourth network device.

Abstract: This disclosure describes techniques for configuring an edge router of a communication provider network, the edge router coupled to communicate with a plurality of media streaming playback devices. Based at least in part on an indication of characteristics associated with the plurality of media streaming playback devices, a first multicast join for the edge router is configured to the communication provider network such that one or more media servers delivers a first plurality of media streams to the edge router via the communication provider network. Based at least in part on an indication of a request for an additional media stream not included in the first plurality of media streams, a second multicast join for the edge router is configured to the communication provider network such that the one or more media servers delivers the additional media stream to the edge router via the communication provider network.

Abstract: This disclosure describes techniques for configuring an edge router of a communication provider network, the edge router coupled to communicate with a plurality of media streaming playback devices. Based at least in part on an indication of characteristics associated with the plurality of media streaming playback devices, a first multicast join for the edge router is configured to the communication provider network such that one or more media servers delivers a first plurality of media streams to the edge router via the communication provider network. Based at least in part on an indication of a request for an additional media stream not included in the first plurality of media streams, a second multicast join for the edge router is configured to the communication provider network such that the one or more media servers delivers the additional media stream to the edge router via the communication provider network.

Abstract: Presented herein are techniques to analyze network anomaly signals based on both a spatial component and a temporal component. A method includes identifying a plurality of factors that trigger a first anomaly signal by a first network node and a second anomaly signal by a second network node in a network comprising a plurality of network nodes, determining that the first network node is adjacent to the second network node in the plurality of network nodes, calculating an anomaly severity score for the first network node based on a number of co-occurring factors from among the plurality of factors that trigger both the first anomaly signal and the second anomaly signal, and adjusting the anomaly severity score for the first network node based on a value of a prior anomaly severity score for the first network node.

Abstract: Presented herein are techniques to analyze network anomaly signals based on both a spatial component and a temporal component. A method includes identifying a plurality of factors that trigger a first anomaly signal by a first network node and a second anomaly signal by a second network node in a network comprising a plurality of network nodes, determining that the first network node is adjacent to the second network node in the plurality of network nodes, calculating an anomaly severity score for the first network node based on a number of co-occurring factors from among the plurality of factors that trigger both the first anomaly signal and the second anomaly signal, and adjusting the anomaly severity score for the first network node based on a value of a prior anomaly severity score for the first network node.

Abstract: In one embodiment, a device deploys a first machine learning model to an inference location in a network. The first machine learning model is used at the inference location to make inferences about the network. The device receives, from the inference location, an indication that the first machine learning model is exhibiting poor performance. The device identifies a corrective measure for the poor performance that minimizes resource consumption by a model training pipeline of the device. The device deploys, based on the corrective measure, a second machine learning model to the inference location. The second machine learning model is used in lieu of the first machine learning model to make the inferences about the network.

Abstract: Seamless multipoint label distribution protocol (mLDP) transport over a bit index explicit replication (BIER) core may be provided. First, it may be determined that a first plurality of network devices comprise BIER edge routers. Then, in response to determining that the first plurality of network devices comprise BIER edge routers, a Targeted Label Distribution Protocol (T-LDP) session may be created between a first one of the first plurality of network devices and a second one of the first plurality of network devices. Next, an address of a peer device connected to the second one of the first plurality of network devices may be advertised by the second one of the first plurality of network devices over the T-LDP session.

Abstract: Seamless multipoint label distribution protocol (mLDP) transport over a bit index explicit replication (BIER) core may be provided. First, it may be determined that a first plurality of network devices comprise BIER edge routers. Then, in response to determining that the first plurality of network devices comprise BIER edge routers, a Targeted Label Distribution Protocol (T-LDP) session may be created between a first one of the first plurality of network devices and a second one of the first plurality of network devices. Next, an address of a peer device connected to the second one of the first plurality of network devices may be advertised by the second one of the first plurality of network devices over the T-LDP session.