Juniper Networks

Techniques are described for multipath traffic engineering (MPTE). In an example, computer-readable storage media comprises instructions for causing one or more processors of a network node to: obtain data associating a first incoming link, a second incoming link, a share of outgoing bandwidth for a first outgoing link, and a share of outgoing bandwidth for a second outgoing link; and forward, based on the data, incoming network traffic received at the network node on the first incoming link and incoming network traffic received at the network node on the second incoming link via the first outgoing link according to the share of outgoing bandwidth for the first outgoing link and via the second outgoing link according to the share of outgoing bandwidth for the second outgoing link.

Techniques are disclosed for a network management system (NMS) that determines a non-WIFI channel assignment for an access point (AP). In an example, the NMS is configured to determine neighbor APs at a site based on scan radio data for a frequency band at the site. The NMS determines a non-WIFI channel to assign to a non-WIFI transceiver of the AP that does not interfere with operating channels for non-WIFI transceivers of one or more APs of the neighbor APs and that does not interfere with operating channels for WIFI radios of the AP and the neighbor APs that operate on the same frequency band as the non-WIFI transceiver of the AP. The NMS is further configured to send a message to the AP to cause the AP to operate the non-WIFI transceiver on the assigned non-WIFI channel.

In general, techniques are described for determining a location of a wireless device in a site based on a plurality of directional beams transmitted with a plurality of offset angles. For example, a network device comprises a plurality of directional antennas configured to transmit a plurality of directional beams, wherein each directional beam of the plurality of directional beams offset by one of a plurality of offset angles, wherein at least one directional beam of the plurality of directional beams is formed by one or more signals with a phase shift. The processing circuitry of the network device is configured to send, to a network management system, information associated with one or more directional beams of the plurality of directional beams that are received by a wireless device to determine a location of the wireless device in a site.

A computing system comprising storage media and processing circuitry may perform the techniques. The processing circuitry may aggregate a plurality of performance metrics for a plurality of network entities of a network system into a metric indicative of a health of the plurality of network entities. The processing circuitry may, based at least in part on a determination that the aggregated metric indicative of the health of the plurality of network entities does not satisfy a threshold, identify one or more network entities of the plurality of network entities for which the corresponding performance metrics of the plurality of performance metrics contributed to the aggregated metric not satisfying the threshold. The processing circuitry may output a cause of fault associated with the identified one or more network entities.

Techniques are disclosed for a network management system (NMS) that computes a channel score based on a normalized metric for a channel and assigns a channel to an access point (AP) based on the channel score). In one example, the NMS obtains data associated with at least one channel of a plurality of channels in a frequency band at a site, where the data includes a set of metrics. The NMS computes a normalized metric for each metrics of the set of metrics with respect to a threshold value representative of degraded performance of the at least one channel. The NMS computes a channel score based on a product of the normalized metrics. The NMS assigns a channel to at least one AP based on the channel score for the channel.

This disclosure describes techniques for managing multiple wireless networks providing overlapping coverage to user devices. In one example, this disclosure describes a computing system configured to collect network data associated with a first wireless network; collect network data associated with a second wireless network, wherein the first wireless network and the second wireless network have an overlapping coverage area, and wherein the first wireless network and the second wireless network are different wireless network types; identify, based on the network data associated with the first wireless network, a user device that is attached to the first wireless network and is in the overlapping coverage area, wherein the user device is also capable of attaching to the second wireless network; and predict, based on both the network data associated with the first wireless network and the network data associated with the second wireless network, a network condition impacting the user device.

Packets that experience longer delays (residence time) on a router are identified and used in determining whether or not to sample the packet. Information about sampled packets, along with information such as on router (or on router forwarding engine) residence time, normalized delay, and a reason(s) for the higher delay are then exported to an external collector device. This mechanism of reporting delayed packets helps with finding the root cause of latency service level agreement (SLA) breaches.

Techniques are disclosed for a computing system that compares media access control (MAC) address profiles associated with the MAC address of a device to detect anomalies between the MAC address profiles. In one example, the computing system obtains a current profile of a MAC address associated with a device requesting access to a network at a location. The computing system compares the current profile of the MAC address to one or more historical profiles of the MAC address over time or concurrent profiles of the MAC address at other locations. The computing system detects an anomaly between the current profile of the MAC address and at least one of the historical profiles or the concurrent profiles of the MAC address. The computing system generates a notification identifying the anomaly.

Techniques are disclosed for end-to-end assurance of application workloads. For example, a computing system receive time series data comprising performance indicators for elements of layers of a system having host computing devices executing application workloads. The computing system creates, based on mapping, using the time series data, Graphics Processing Units (GPUs) of a compute layer to network devices of a network layer, a dependency graph representing cross-layer relationships between elements of different layers of the layers. The computing system determines an anomaly in the performance of one of the application workloads. The computing system determines, based on a dependency within the dependency graph of the application workload on an element of the network layer, an issue with the element as a root cause of the anomaly in the performance of the workload, and performs a remedial action for the issue with the element of the network layer.

Techniques are disclosed for using prompt engineering and statistical root cause analysis (RCA) to increase the accuracy of machine learning RCA. In an example, a computing system generates a prompt for root cause analysis of an application-layer anomaly within system of elements across a plurality of layers. The prompt comprises a cross-layer topology graph of the elements across the plurality of layers, diagnostics information for the elements, and a list of the elements and corresponding diagnostics information ordered according to a likelihood of being a source of a root cause of the application-layer anomaly. The computing system provides the generated prompt to a machine learning model to obtain, based at least in part on the generated prompt, a response comprising the root cause of the application-layer anomaly. The computing system outputs the response.