Juniper Networks

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 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.

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 a conversational assistant system that employs a machine learning system to act as an intermediary between natural language questions of a user and one or more Application Programming Interfaces (APIs) implemented by a network analysis system. In one example, the conversational assistant system receives API definition files including sets of function definitions and corresponding function descriptions and a natural language question from a user device. The conversational assistant system processes the API definition files and the natural language question to obtain function definitions invoking API endpoints of the APIs. The conversational assistant system sequentially invokes, based on the function definitions, the API endpoints to obtain responses from the APIs implemented by the network analysis system. The conversational assistant system generates, based at least in part on the responses from the APIs, a natural language answer for output at an output device.

In general, techniques are described for a computing system that generates a first graph representative of a of a first application topology of a distributed application at a first time that includes a first plurality of nodes of a computing infrastructure across a plurality of layers. The computing system generates a second graph representative of a second application topology of the distributed application at a second time. The computing system determines, based on a comparison of the first graph and the second graph, that a path has changed. Based on the determination that the path has changed, the computing system outputs an indication that an alarm indicative of an issue in the computing infrastructure is caused by the change to the path.

This disclosure describes techniques that include assessing trust in a system based on subjective factors. In one example, this disclosure describes a method that includes determining, by the computing system, a prerequisite score for a network entity in a computer network; determining, by the computing system, a subjective score for the network entity based on one or more subjective factors for the network entity, wherein each of the one or more subjective factors for the network entity corresponds to a subjective characteristic of the network entity; determining, by a computing system, a trust score for the network entity based on the prerequisite score and the subjective score; and modifying, by the computing system, operation of the computer network based on the trust score for the network entity

Example devices and techniques are described. An example device includes one or more processors and one or more memories storing instructions. When executed, the instructions cause the one or more processors to determine a respective configured ambient temperature for each of a plurality of network devices. The instructions cause the one or more processors to determine a respective current traffic load on each of the plurality of network devices. The instructions cause the one or more processors to determine, for each of the plurality of network devices and based on the respective configured ambient temperatures and the respective current traffic loads, a respective estimated power usage value. The instructions cause the one or more processors to sum the respective estimated power usage values to generate an overall estimated power usage value and output a representation of the overall estimated power usage value.

Techniques are described for configuration and application of intent-based network access control (NAC) policies for authentication and authorization of multi-tenant, network access server (NAS) devices to access enterprise networks of organizations. A network management system configures intent-based NAC policies for an organization. A cloud-based NAC system may apply an appropriate intent-based NAC policy in response to an authentication request from a NAS device. The NAC system identifies a vendor of the NAS device, matches incoming attributes in the authentication request to a set of normalized match rules of the intent-based NAC policy, and translates a set of abstracted policy results corresponding to the set of normalized match rules into a vendor-specific set of return attributes based on the vendor of the NAS device. The NAC system sends the vendor-specific set of return attributes to the NAS device to enable the NAS device to access the enterprise network of the organization.

Techniques are disclosed for improved energy efficiency of network devices of a network system. For example, a computing system obtains time series data comprising information about computing devices of a computer network. The computing devices access other devices of the computer network via network devices that exchange network traffic of the computing devices. The computing system applies a machine learning system, trained with historical time series data, to the obtained time series data to predict a requirement of one or more of the network devices for exchanging network traffic of the computing devices for a next time interval. The computing system adjusts, based at least in part on the predicted requirement for the next time interval, operation of the one or more of the network devices.

A method includes deploying a network device within a fabric having a management network by attaching the network device through the management network to a port of a role allocator, wherein the role allocator includes one or more ports designated as first level port connections and one or more other ports designated as second level port connections. If the deployed network device is attached to one of the ports designated as first level port connections, the deployed network device is configured as a first level device. If the deployed network device is attached to one of the ports designated as second level port connections, the deployed network device is configured as a second level device.