Methods and systems provide for early detection of failures in cables and/or physical layer devices (PHY) linked thereto, of a communications network in a vehicle. The methods and systems employ a computer trained model that analyzes changes in detected values obtained from a given vehicle within an operational time period, against a range of operational values, collected from different vehicles and/or the given vehicle, for the respective PHY parameter, to determine that the cable and/or the PHY linked thereto in the given vehicle may fail within a predetermined time period.

The present disclosure facilitates improving the operation of a cloud service by updating its configuration information and its resource requirements. The resource utilization of the cloud service can be monitored, and a decision logic module can determine whether action is required. When action is required, an update can be prepared and applied, and notifications can be generated about the condition and its resolution. Resolutions can require correlation of multiple cloud services to provide real-time access to information that is not otherwise available to a single entity. Resolutions can be learned and predicted in a number of ways using a predictive engine.

Methods, apparatus, and processor-readable storage media for artificial intelligence-based redundancy management are provided herein. An example computer-implemented method includes obtaining telemetry data from one or more client devices within at least one system; predicting one or more hardware component failures in at least a portion of the one or more client devices within the at least one system by processing at least a portion of the telemetry data using a first set of one or more artificial intelligence techniques; determining, using a second set of one or more artificial intelligence techniques, one or more redundant hardware components for implementation in connection with the one or more predicted hardware component failures; and performing at least one automated action based at least in part on the one or more redundant hardware components.

In one embodiment, a supervisory service for a network obtains quality of experience metrics for application sessions of an online application. The supervisory service maps the application sessions to paths that traverse a plurality of autonomous systems. The supervisory service identifies, based in part on the quality of experience metrics, a particular autonomous system from the plurality of autonomous systems associated with a decreased quality of experience for the online application. The supervisory service causes application traffic for the online application to avoid the particular autonomous system.

Systems, methods, and non-transitory computer-readable storage media are provided for predicting the likelihood or probability of a subscriber of a service to cancel or not renew a subscription. A method, according to one implementation, includes a step of receiving data pertaining to aspects of a service that is provided by a service provider to a subscriber in accordance with a subscription. The data may include one or more impact factors each having a positive, neutral, or negative influence on the likelihood of subscriber churn. The method also includes a step of using the one or more impact factors to predict the likelihood that the subscriber will cancel the subscription.

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

A method for detecting network anomalies includes receiving a control message from a cellular network and extracting one or more features from the control message. The method also includes predicting a potential label for the control message using a predictive model configured to receive the one or more extracted features from the control message as feature inputs. Here, the predictive model is trained on a set of training control messages where each training control message includes one or more corresponding features and an actual label. The method further includes determining that a probability of the potential label satisfies a confidence threshold. The method also includes analyzing the control message to determine whether the control message corresponds to a respective network performance issue. When the control message impacts network performance, the method includes communicating the network performance issue to a network entity responsible for the network performance issue.

A computer system automatically tests a network communication model by predicting whether particular traffic (whether actual or simulated) should be allowed on the network, and then estimating the accuracy of the network communication model based on the prediction. Such an estimate may be generated even before the model has been applied to traffic on the network. For example, the model may be generated based on a first set of network traffic. The accuracy of the model may then be estimated based on a second set of network traffic. This allows the accuracy of the model to be estimated without first waiting to apply the model to actual network traffic, thereby reducing the risk associated with applying the model before its accuracy is known.

A method for detecting network anomalies includes receiving a control message from a cellular network and extracting one or more features from the control message. The method also includes predicting a potential label for the control message using a predictive model configured to receive the one or more extracted features from the control message as feature inputs. Here, the predictive model is trained on a set of training control messages where each training control message includes one or more corresponding features and an actual label. The method further includes determining that a probability of the potential label satisfies a confidence threshold. The method also includes analyzing the control message to determine whether the control message corresponds to a respective network performance issue. When the control message impacts network performance, the method includes communicating the network performance issue to a network entity responsible for the network performance issue.

The properties of a plurality of operational units are estimated by generating a central system state graph model representing the properties of the plurality of operational units as probabilities of transitions between states for the plurality of operational units, where the states represent operational data. Then a respective updated system state graph model is generated for each of the plurality of operational units, based on the central system state graph model and based on new operational data for the respective operational unit. A distance measure is determined between the respective updated system state graph models. If the distance measure fulfils a divergence criterion, a plurality of new central system state graph models are generated, each representing the properties of a respective subset of the plurality of operational units as the probabilities of transitions between states for the respective subset of the plurality of operational units.