This disclosure describes systems, methods, and devices related to anomaly detection of CPE firmware revisions. A method may include collecting metrics data for a plurality of customer-provided equipment (CPE) models over a window of time; training a first autoencoder for a first CPE model of the plurality of CPE models using at least a portion of the metrics data to detect anomalies within a plurality of firmware versions of the first CPE model; identifying, using the first autoencoder, that a first firmware version of the plurality of firmware versions is anomalous across a first time series; and storing data indicating that the first firmware version of the plurality of firmware versions is anomalous across the first time series. Metrics data may include one or more of interactive voice response (IVR) session data; calls handled data; and truck schedule data.

The autonomous cloud design system may determine a design that may appropriately mix emerging technologies and operations to provide a versatile and cost-effective or efficient solution for a given cloud site.

In one embodiment, an apparatus obtains unstructured text generated by a device regarding operation of the device. The apparatus identifies the unstructured text as associated with a particular command or process that generated the unstructured text. The apparatus classifies a portion of the unstructured text as anomalous by inputting the portion of the unstructured text to a machine learning-based model trained to predict text generated by the particular command or process. The apparatus provides provide the unstructured text for display that includes an indication that the portion of the unstructured text is anomalous.

Systems and methods include provisioning a default slice having a default subdomain corresponding to a set of resources that are any of physical and virtual components in a network; decomposing the default subdomain into a first set of one or more subdomains, wherein collectively the first set of one or more subdomains include all of the set of resources; provisioning one or more application slices as children from the default slice that inherit capabilities of the default slice; and assigning one or more subdomains from the first set of the one or more subdomains to the respective one or more application slices.

A building network system of a building including one or more processing circuits configured to generate virtual networks, each virtual network of the virtual networks generated for one building equipment group of building equipment groups and deploy the virtual networks on network infrastructure of the building. The one or more processing circuits are configured to generate updates to the virtual networks to address resource changes in at least one of the building equipment groups and deploy the updates to the virtual networks.

The disclosure relates to system and method for facilitating designing of an Internet of Things (IoT) infrastructure for deploying an IoT application. The method includes determining a Manhattan distance between each of a plurality of existing requirements and a new requirement, identifying one or more of the plurality of existing requirements corresponding to a minimum Manhattan distance, determining a relevancy score for each of the one or more identified existing requirements based on a similarity between the each of the one or more identified existing requirements and the new requirement, and providing one or more IoT components and one or more IoT designs corresponding to a similar existing requirement for facilitating designing of the IoT infrastructure. The similar existing requirement comprises one of the one or more identified existing requirement with a maximum relevancy score.

A real-time stream-based clustering algorithm is disclosed for correlating network impact according to time and space. The clustering algorithm operates at discrete time steps and produces a partitioning of a network graph such that each partition is a cluster. Clusters are tracked at each time step and the partitions can change by disappearing, splitting or merging with others. To track an incident over many clustering time steps, an ID is assigned to and related to previous clusters such that the same ID can propagate between multiple cluster time steps. Thus, a same incident can be tracked over time as its effect traverses the network. Anchor nodes can be assigned to the clusters to establish a relationship between clusters at different time steps.

A data stream classification model updating method is disclosed. Determining, based on packet information of a current data stream and a behavior classification model, a first data stream class corresponding to the current data stream; determining, based on a target correspondence and a common feature of the current data stream, a second data stream class corresponding to the current data stream, where the target correspondence is a correspondence between a plurality of common features and a plurality of data stream classes; and if the first data stream class is different from the second data stream class, obtaining correction data corresponding to the current data stream, where the correction data includes the packet information of the current data stream and the second data stream class, and the correction data is used as a training sample to update the behavior classification model.

The disclosure relates to a method, executed by an NFV-MANO, for providing a requested Service Availability Level (SAL) for a Network Service (NS). The method comprises at each of a plurality of layers of the NFV-MANO, mapping the requested SAL to a SAL that needs to be provided by a lower layer of the NFV-MANO. The method comprises propagating the mapped requested SAL through interfaces between layers of the NFV-MANO, from an NFVO towards a VIM. The method comprises receiving an estimated SAL′ for the NS based on virtual resources (VR) allocated by the VIM for satisfying the requested SAL. The method comprises, upon determining that the estimated SAL′ does not satisfy the requested SAL, taking actions to meet the requested SAL, or upon determining that the estimated SAL′ satisfies the requested SAL taking no further actions.

A method of generating a synthetic network includes receiving, by a group structure identification module, anonymized input data related to an original network. The anonymized input data includes an anonymized list of nodes, a list of edges and a list of groups. The method further includes determining, by the group structure identification module, for each pair of nodes, a probability of an edge between the pair of nodes. A resulting list of probabilities corresponds to a summary group structure. The method further includes generating, by a synthetic random network generation module, at least one synthetic random network based, at least in part, on the determined probabilities.