Cisco Technology, Inc.

Andrea Di Pietro

Jean-Philippe Vasseur

Javier Cruz Mota

Grégory Mermoud

Sukrit Dasgupta

Jonathan W Hui

Erwan Barry Tarik Zerhouni

Pierre-André Savalle

Vinay Kumar Kolar

Fabien Flacher

Jean-Phillippe Vasseur

Jean-Philippe J Vasseur

Javier Mota

In one embodiment, a service receives telemetry data collected from a plurality of different networks. The service combines the telemetry data into a synthetic input trace. The service inputs the synthetic input trace into a plurality of machine learning models to generate a plurality of predicted key performance indicators (KPIs), each of the models having been trained to assess telemetry data from an associated network in the plurality of different networks and predict a KPI for that network. The service compares the plurality of predicted KPIs to identify one of the plurality of different networks as exhibiting an abnormal behavior.

Using raw network telemetry traces to generate predictive insights using machine learning

In one embodiment, a service computes a data fidelity metric for network telemetry data used by a machine learning model to monitor a computer network. The service detects unacceptable performance of the machine learning model. The service determines a correlation between the data fidelity metric and the unacceptable performance of the machine learning model. The service adjusts generation of the network telemetry data for input to the machine learning model, based on the determined correlation between the data fidelity metric and the unacceptable performance of the machine learning model.

Assessing data fidelity in a machine learning-based network assurance system

In one embodiment, a network assurance service executing in a local network clusters measurements obtained from the local network regarding a plurality of devices in the local network into measurement clusters. The network assurance service computes aggregated metrics for each of the measurement clusters. The network assurance service sends a machine learning model computation request to a remote service outside of the local network that includes the aggregated metrics for each of the measurement clusters. The remote service uses the aggregated metrics to train a machine learning-based model to analyze the local network. The network assurance service receives the trained machine learning-based model to analyze performance of the local network. The network assurance service uses the receive machine learning-based model to analyze performance of the local network.

Privacy-aware model generation for hybrid machine learning systems

In one embodiment, a network assurance service maintains a data lake of network telemetry data obtained by the service from any number of computer networks. The service generates a machine learning model for on-premise execution in a particular computer network to detect network issues in the particular network. To do so, the service repeatedly selects a candidate set of model settings based in part on the data lake of network telemetry data, trains a machine learning model using network telemetry data from the data lake that matches the candidate set of model settings, and tests performance of the trained model using an emulator that emulates network issues in the particular network. The service further deploys the generated machine learning model to the particular computer network for on-premise execution.

Model training for on-premise execution in a network assurance system

In one embodiment, possible voting nodes in a network are identified. The possible voting nodes each execute a classifier that is configured to select a label from among a plurality of labels based on a set of input features. A set of one or more eligible voting nodes is selected from among the possible voting nodes based on a network policy. Voting requests are then provided to the one or more eligible voting nodes that cause the one or more eligible voting nodes to select labels from among the plurality of labels. Votes are received from the eligible voting nodes that include the selected labels and are used to determine a voting result.

Designating a voting classifier using distributed learning machines

In one embodiment, a device in a network receives information regarding a network anomaly detected by an anomaly detector deployed in the network. The device identifies the detected network anomaly as a false positive based on the information regarding the network anomaly. The device generates an output filter for the anomaly detector, in response to identifying the detected network anomaly as a false positive. The output filter is configured to filter an output of the anomaly detector associated with the false positive. The device causes the generated output filter to be installed at the anomaly detector.

Filtering mechanism to reduce false positives of ML-based anomaly detectors and classifiers

In one embodiment, a network assurance service that monitors a plurality of networks subdivides telemetry data regarding devices located in the networks into subsets, wherein each subset is associated with a device type, time period, metric type, and network. The service summarizes each subset by computing distribution percentiles of metric values in the subset. The service identifies an outlier subset by comparing distribution percentiles that summarize the subsets. The service reports insight data regarding the outlier subset to a user interface. The service adjusts the subsets based in part on feedback regarding the insight data from the user interface.

Pattern discovery from high dimensional telemetry data using machine learning in a network assurance service

In one embodiment, a device in a network performs anomaly detection functions using a machine learning-based anomaly detector to detect anomalous traffic in the network. The device identifies an ability of one or more nodes in the network to perform at least one of the anomaly detection functions. The device selects a particular one of the anomaly detection functions to offload to a particular one of the nodes, based on the ability of the particular node to perform the particular anomaly detection function. The device instructs the particular node to perform the selected anomaly detection function.

Distributed anomaly detection management

In one embodiment, a network assurance service receives data regarding a monitored network. The service analyzes the received data using a machine learning-based model, to perform a network assurance function for the monitored network. The service detects a lowered performance of the machine learning-based model when a performance metric of the machine learning-based model is below a threshold for the performance metric. When it is determined that the lowered performance of the machine-learning based model is correlated with the sample rate of the received data, the service adjusts the sample rate of the data.

Dynamically adjusting sample rates based on performance of a machine-learning based model for performing a network assurance function in a network assurance system

In one embodiment, a local service of a network reports configuration information regarding the network to a cloud-based network assurance service. The local service receives a classifier selected by the cloud-based network assurance service based on the configuration information regarding the network. The local service classifies, using the received classifier, telemetry data collected from the network, to select a modeling strategy for the network. The local service installs, based on the modeling strategy for the network, a machine learning-based model to the local service for monitoring the network.

Dynamic selection of models for hybrid network assurance architectures

In one embodiment, a network assurance service receives, from a reporting entity, data regarding a monitored network for input to a machine learning-based analyzer of the network assurance service. The service forms a reporting entity model of the reporting entity, based on at least a portion of the data received from the reporting entity. The service identifies a behavioral change of the reporting entity by comparing a sample of the data received from the reporting entity to the reporting entity model. The service correlates the behavioral change of the reporting entity to a change made to the reporting entity. The service causes performance of a mitigation action, to prevent the behavioral change from affecting operation of the machine learning-based analyzer.

Data source modeling to detect disruptive changes in data dynamics

In one embodiment, a primary networking device in a branch network receives a notification of an anomaly detected by a secondary networking device in the branch network. The primary networking device is located at an edge of the network. The primary networking device aggregates the anomaly detected by the secondary networking device and a second anomaly detected in the network into an aggregated anomaly. The primary networking device associates the aggregated anomaly with a location of the secondary networking device in the branch network. The primary networking device reports the aggregated anomaly and the associated location of the secondary networking device to a supervisory device.

Increased granularity and anomaly correlation using multi-layer distributed analytics in the network

In one embodiment, a node in a network detects an anomaly in the network based on a result of a machine learning-based anomaly detector analyzing network traffic. The node determines a packet capture policy for the anomaly by applying a machine learning-based classifier to the result of the anomaly detector. The node selects a set of packets from the analyzed traffic based on the packet capture policy. The node stores the selected set of packets for the detected anomaly.

Adaptive capture of packet traces based on user feedback learning

In one embodiment, a device receives health status data indicative of a health status of a data source in a network that provides collected telemetry data from the network for analysis by a machine learning-based network analyzer. The device maintains a performance model for the data source that models the health of the data source. The device computes a trustworthiness index for the telemetry data provided by the data source based on the received health status data and the performance model for the data source. The device adjusts, based on the computed trustworthiness index for the telemetry data provided by the data source, one or more parameters used by the machine learning-based network analyzer to analyze the telemetry data provided by the data source.

Growing community of inventors

Lausanne, Switzerland

Andrea Di Pietro