Abstract: In one embodiment, a device initiates, using a chaos engineering tool, performance of randomized actions in a network via which an online application is accessible. The device obtains telemetry data from the network. The device computes correlations between the telemetry data and the randomized actions. The device uses the correlations to determine a root cause of an event in the network with respect to the online application.

Abstract: Techniques and apparatus for performing sticky client detection and/or remediation with machine learning are described. An example technique includes determining one or more parameters associated with roaming activity of a client station (STA) within a wireless network. The one or more parameters are evaluated with a machine learning model to predict a sliding boundary associated with the client STA, a first access point (AP) within the wireless network, and a second AP within the wireless network. Information associated with the sliding boundary is transmitted to the first AP. A frame including a request for the client STA to roam to the second AP and the information associated with the sliding boundary is transmitted to the client STA.

Abstract: The present disclosure describes an apparatus that generates headers for backscattering devices. The apparatus includes one or more memories and one or more processors communicatively coupled to the one or more memories. A combination of the one or more processors determined an Internet protocol (IP) address for a backscattering device, generates a header that includes the IP address, and communicates a first energizing frame to the backscattering device. The first energizing frame includes the header. The combination of the one or more processors also receives a message from the backscattering device. The message includes the header.

Abstract: In one embodiment, a device obtains client attribute data for clients of an online application that access the online application via a plurality of points of presence in a network. The device forms a performance model that models an application experience metric for the online application as a function of the client attribute data for each of the plurality of points of presence. The device selects, using the performance model, a particular point of presence from among the plurality of points of presence to be used by a particular client to access the online application, based on its client attribute data. The device causes the particular client to access the online application via the particular point of presence selected by the device using the performance model.

Abstract: In one embodiment, a device obtains quality of experience metrics for an online application whose traffic traverses a particular interface of a router located at a first site in a network. The device identifies a correlation between throughput of the particular interface and the quality of experience metrics for the online application. The device makes a determination that the correlation is a root cause of degradation of the quality of experience metrics for the online application at least in part by determining whether throughput of an interface of a remote router located at a second site in the network is correlated with the quality of experience metrics. The device configures, based on the determination, a priority queue associated with the particular interface for use by traffic of the online application.

Abstract: In one embodiment, a device obtains interaction data indicative of a flow of interactions performed by a user with an online application accessible via a network. The device detects an anomaly by applying an anomaly detection model to the interaction data. The device determines that the anomaly is attributable to a condition present in the network. The device causes performance of an adjustment to the network, to mitigate the condition.

Abstract: In one embodiment, a device obtains a set of probing motifs. Each probing motif groups similar patterns of path probing results for one or more path metrics in a network. The device generates signatures for the set of probing motifs. Each signature relates a probing strategy with a measure of performance of a classifier to detect that motif were path probing to be conducted in accordance with that probing strategy. The device selects, based on the signatures for the set of probing motifs, a particular probing strategy to use in the network. The device causes one or more probing agents in the network to conduct path probing in accordance with the particular probing strategy.

Abstract: In one embodiment, a device receives application performance metrics generated by an online application accessible via a network and indicative of a particular state of the online application. The device performs testing of the online application by replicating a plurality of network impairments. The device associates, based on results of the testing, a particular network impairment from plurality of network impairments with the particular state of the online application. The device provides an indication of the particular network impairment as a cause of the particular state of the online application.

Abstract: In one embodiment, a device predicts, for each of a plurality of applications accessible via a network, quality metrics for different network paths where traffic for that application be routed via one or more paths among the different network paths. The device generates a congestion risk prediction model that predicts a risk of traffic congestion for a particular combination of: applications from among the plurality of applications, traffic flows associated with those applications, and paths among the network paths via which those traffic flows may be routed. The device performs a constrained optimization based on the predicted quality metrics and on the risk of traffic congestion predicted by the model, to assign traffic flows for the applications to a selected subset of the different paths. The device causes the traffic flows to be routed in the network via the selected subset of the different paths to which they are assigned.

Abstract: In one embodiment, a device generates a plurality of recommendations for a network, each recommendation indicating a suggested action to optimize quality of experience of a corresponding application accessible via the network. The device assigns scores to different possible groupings of the plurality of recommendations. The device selects a particular grouping from among the plurality of recommendations, based on their scores. The device provides the particular grouping for implementation in the network.

Abstract: In one embodiment, a device obtains path metrics for a network path used to convey application traffic for an online application. The device discretizes the path metrics into labeled states. The device generates state transition visualization data that represents the labeled states as nodes and transitions between the labeled states as edges connecting the nodes. The device provides the state transition visualization data for display.

Abstract: In one embodiment, a device determines a mapping between a network destination and Border Gateway Protocol (BGP) peers located across a plurality of autonomous systems for which the network destination is reachable. The device causes, based on the mapping, performance of probing tests along a plurality of paths to the network destination and via the BGP peers, to obtain path performance measurements for the plurality of paths. The device uses a prediction model to generate predicted performance metrics for the plurality of paths based on the path performance measurements. The device configures, based on the predicted performance metrics for the plurality of paths, the BGP peers with BGP peering policies to convey application traffic associated with the network destination via particular path from among the plurality of paths.

Abstract: In one embodiment, a device causes, in accordance with a probing strategy, performance of a probing test by one or more agents in a network and with respect to an online application. The device obtains quality of experience measurements for the online application. The device adjusts, using reinforcement learning, the probing strategy based on how well a predictive model was able to predict the quality of experience measurements given results of the probing test. The device repeats the causing, obtaining, and adjusting steps using the probing strategy adjusted by the device, to find a minimally disruptive probing strategy that provides acceptable performance by the predictive model.

Abstract: In one embodiment, a device obtains cross-layer telemetry associated with an online application accessible via a network and from three or more layers of the network. The device estimates a quality of experience metric for the online application using the cross-layer telemetry as input to a cognitive model. The device selects a network action to increase the quality of experience metric estimated by the device. The device causes performance of the network action in the network.

Abstract: In one embodiment, a recommendation service of a device provides a recommended action to a client of an online application predicted to improve a quality of experience metric for the online application. The device receives feedback from the client indicative of the recommended action not being implemented by a user of the client. The device determines, based on the feedback, a reason for the recommended action not being implemented. The device updates the recommendation service based on the reason for the recommended action not being implemented.

Abstract: In one embodiment, a device obtains quality of experience labels for an online application accessible via a network. The device also obtains telemetry data from the network that is associated with quality of experience labels. The device makes, based on the quality of experience labels and telemetry data, a determination as to whether the online application is similar to a second online application for which a prediction model is already available. The device trains, based on the determination, a prediction model for the online application to predict a quality of experience metric for the online application.

Abstract: In one embodiment, a first networking device in a network coordinates, with a second networking device in the network, capture of packet maps for a traffic flow in the network associated with a particular application. The packet maps comprise multi-dimensional histograms indexed by identified properties of packets of the traffic flow and time. The first networking device inspects packets of the traffic flow, to identify properties of packets of the traffic flow. The first networking device generates a first packet map for the traffic flow based on the properties of the packets of the traffic flow identified by the first networking device. The first networking device causes a comparison between the first packet map and a second packet map generated by the second networking device to be used as a measure of application experience for the particular application.

Abstract: In one embodiment, a device forms a latent space by applying dimensionality reduction to timeseries snippets of path metrics for a network path via which traffic for an online application is conveyed. The device extracts a plurality of path states from the latent space. The device presents the plurality of path states for display by a user interface. The device associates a set of transitions between the plurality of path states with the online application providing degraded application experience.

Abstract: In one embodiment, a device obtains application data captured by an intermediate node in a network by inserting monitoring code into traffic associated with one or more online applications accessible via the network. The device identifies, based on the application data, a workflow of actions performed by a user of the one or more online applications. The device determines that a particular stage of the workflow is associated with a quality of experience metric for the one or more online applications being degraded. The device provides a recommended change in the network for presentation by a user interface that is expected to optimize the quality of experience metric for the one or more online applications.

Abstract: In one embodiment, a service in a network computes an expected information gain associated with rerouting traffic from a first tunnel onto a backup tunnel in the network. The service initiates, based on the expected information gain, rerouting of the traffic from the first tunnel onto the backup tunnel. The service obtains performance measurements for the traffic rerouted onto the backup tunnel. The service uses the performance measurements to train a machine learning model to predict whether rerouting traffic from the first tunnel onto the backup tunnel will satisfy a service level agreement (SLA) of the traffic.