Abstract: Dynamic Traffic Control (DTC) aims at balancing network capacity demand and supply at a finer grain to minimize capacity buffer always comfortably meeting the demand trends. Resiliency of DTC enables handling traffic management of network regions that have gone thru equipment replacement, or upgrades, or service expansions. DTC should be a fully automated close-loop control process in managing regional traffic without human intervention but reporting benefits measuring improvements from a baseline. In one embodiment, a method of providing dynamic traffic control includes forecasting, using a model, network traffic build up over a region ahead of time; and adjusting network capacity to match a forecasted demand from the model, allowing a precise control of capacity and demand closely matched all times.

Abstract: A method of providing warnings in a telecom network based on forecasting Key Performance Indicators (KPIs), the method comprising: receiving, at a data processing and preparation service, data; transforming, by the data processing and preparation service, the data and feeding transformed data to a forecasting model; predicting, by the forecasting model, a future KPI value for each cell, wherein each KPI has a pre-trained model for prediction that covers all cells; sending, by the forecasting model, predictions to a notification component; receiving, by the notification component, predicted KPI values; and matching, by the notification component, the predicted KPI value against a threshold to generate warnings for any predicted value that exceeds the threshold.

Abstract: In one embodiment, a method of providing automatic configuration of cells includes training a Cell Configuration Bot (CCBot); wherein the training includes providing, by the CCBot, coverage optimization and capacity optimization; wherein the coverage optimization includes measuring Reference Signal Received Power (RSRP) and Signal to Inference and Noise Ratio (SINR) are measured as LTE coverage indicators; wherein the capacity optimization includes measuring a number of Radio Resource Control (RRC) connections and evolved Radio Access Bearer (eRAB) establishments per cell as a measure of the cell accessibility; and adjusting antenna tilt and reference power to impact the cell coverage and capacity.

Abstract: A method may be disclosed for energy savings in cellular networks, comprising: collecting performance data from the cellular network; sharing the performance data with a batch process to train a prediction model; loading the prediction model into a closed-loop process; using the performance data in combination with the trained prediction model to predict cellular access network load for a particular cell; using the predicted cellular access network load to determine a recommended action; and executing the recommended action. The method may be implemented using a public cloud. The trained prediction model may be used to classify different cells and determine different recommended actions for the different cells.

Abstract: An apparatus comprises a processing platform implementing a data set discovery engine and a data set valuation engine. The data set discovery engine is configured to generate data set similarity measures each relating a corresponding one of a plurality of data sets to one or more other ones of the plurality of data sets. The data set valuation engine is coupled to the data set discovery engine and configured to generate valuation measures for respective ones of at least a subset of the plurality of data sets based at least in part on respective ones of the data set similarity measures generated by the data set discovery engine. For example, the data set valuation engine may generate the valuation measure for a given data set as a function of valuation measures previously generated for respective other data sets determined to exhibit at least a threshold similarity to the given data set.

Abstract: Systems and methods are disclosed for performing computations on data at an intelligent data pipe en route to a data store. In one embodiment, a method is disclosed, comprising: receiving metadata regarding a data stream from a data source; performing an analysis of the metadata at a service orchestrator; creating at least one container instance based on the analysis; streaming the data stream from the data source to a data sink via the at least one container; and processing the data stream as it passes through the at least one container instance, thereby enabling application-aware processing of data streams in real time prior to arrival at the data store.

Abstract: Systems and methods are disclosed for performing computations on data at an intelligent data pipe en route to a data store. In one embodiment, a method is disclosed, comprising: receiving metadata regarding a data stream from a data source; performing an analysis of the metadata at a service orchestrator; creating at least one container instance based on the analysis; streaming the data stream from the data source to a data sink via the at least one container; and processing the data stream as it passes through the at least one container instance, thereby enabling application-aware processing of data streams in real time prior to arrival at the data store.

Abstract: An apparatus in one embodiment comprises a processing platform having one or more processing devices. The processing platform is configured to obtain metadata characterizing a plurality of data sets, to generate data set operational signatures for respective ones of at least a subset of the data sets based at least in part on the obtained metadata, and to automatically perform one or more management operations for each of one or more of the data sets based at least in part on respective corresponding ones of the data set operational signatures. The processing platform may be further configured to implement a target signature for a particular data set management policy, and to automatically perform a particular management operation for a given one of the data sets based at least in part on a result of a comparison of the data set operational signature for the given data set to the target signature.

Abstract: An apparatus in one embodiment comprises an ingestion manager, a plurality of ingestion engines associated with the ingestion manager, and an analytics platform configured to receive data from the ingestion engines under the control of the ingestion manager. The ingestion manager is configured to interact with one or more of the ingestion engines in conjunction with providing data to a given one of a plurality of analytics workspaces of the analytics platform. For example, the analytics workspaces of the analytics platform are illustratively configured to receive data from respective potentially disjoint subsets of the ingestion engines under the control of the ingestion manager. Additionally or alternatively, the ingestion manager may be configured to implement data-as-a-service functionality for one or more of the analytics workspaces of the analytics platform.

Abstract: An apparatus comprises a processing platform configured for characterization, provisioning and access of data set virtual neighborhoods. The processing platform comprises a virtual neighborhood describer, a virtual neighborhood provisioner and a virtual neighborhood visitor. The virtual neighborhood describer is configured to generate characterizations of data set virtual neighborhoods responsive to one or more requirements, such as specified or derived requirements, or combinations thereof. The virtual neighborhood provisioner is configured to utilize the characterizations to generate provisioned data set virtual neighborhoods responsive to one or more corresponding provisioning requests.

Abstract: Systems and methods for governing access to or use of assets in an analytics platform. Access to assets is controlled with policies that reference attributes. A context of an access request is defined by collecting attributes associated with an access request. The context is then evaluated in light of attributes referenced by the policy applicable to the asset or with a class of the asset. The access request is granted, denied, or partially granted based on whether the attributes defined by the context of the access request comport with the policy.

Abstract: Systems and methods are disclosed for performing training using superimposed pilot subcarriers to determine training data. The training includes starting with a training duration (T) equal to a number of antennas (M) and running a Convolutional Neural Network (CNN) model using training samples to determine if a testing variance meets a predefined threshold. When the testing variance meets a predefined threshold, then reducing T by one half and repeating the running Convolutional Neural Network (CNN) model until the testing variance fails to meet the predefined threshold. When the testing variance fails to meet the predefined threshold, then multiplying T by two and using the new value of T as the new training duration to be used. Generating a run-time model based on the training data, updating the run-time model with new feedback data received from a User Equipment (UE), producing a DL channel estimation from the run-time model; and producing an optimal precoding matrix from the DL channel estimation.

Abstract: A registration framework is disclosed that allows assets to be registered with an analytics platform. When an asset is ingested into the analytics platform, the registration framework operates to register the asset in an asset roster. The asset roster identifies the asset and stores information about the asset. The registration framework can then be used by users to discover assets. Assets may also be deployed by the registration framework to workspaces.

Abstract: Systems and methods are disclosed for performing training using superimposed pilot subcarriers to determine training data. The training includes starting with a training duration (T) equal to a number of antennas (M) and running a Convolutional Neural Network (CNN) model using training samples to determine if a testing variance meets a predefined threshold. When the testing variance meets a predefined threshold, then reducing T by one half and repeating the running Convolutional Neural Network (CNN) model until the testing variance fails to meet the predefined threshold. When the testing variance fails to meet the predefined threshold, then multiplying T by two and using the new value of T as the new training duration to be used. Generating a run-time model based on the training data, updating the run-time model with new feedback data received from a User Equipment (UE), producing a DL channel estimation from the run-time model; and producing an optimal precoding matrix from the DL channel estimation.

Abstract: Systems and methods are disclosed for performing computations on data at an intelligent data pipe en route to a data store. In one embodiment, a method is disclosed, comprising: receiving metadata regarding a data stream from a data source; performing an analysis of the metadata at a service orchestrator; creating at least one container instance based on the analysis; streaming the data stream from the data source to a data sink via the at least one container; and processing the data stream as it passes through the at least one container instance, thereby enabling application-aware processing of data streams in real time prior to arrival at the data store.

Abstract: An apparatus comprises a processing platform configured for integration of compliance and analytic environments. The compliance and analytic environments are implemented at least in part by the processing platform. The processing platform comprises at least a portion of a data lake at least partially shared between the compliance and analytic environments. The processing platform further comprises one or more integration mechanisms supporting interaction between the compliance and analytic environments via the data lake.

Abstract: An apparatus in one embodiment comprises a processing platform implementing an Internet of Things (IoT) distributed management system accessible to a plurality of user devices over at least one network. The processing platform is configured to determine IoT infrastructure for a given IoT deployment in at least one particular usage context, to control placement of multiple workflow processes for the IoT deployment over a plurality of distributed locations within the IoT infrastructure, and to manage execution of the workflow processes at the distributed locations in accordance with one or more constraints of the particular usage context. The IoT deployment comprises one or more IoT platforms each configured to interact with a different set of IoT devices. The placement of multiple workflow processes over the plurality of distributed locations illustratively provides a designated distribution of data, services, applications and analytics for the IoT deployment in the particular usage context.

Abstract: An apparatus in one embodiment comprises a processing platform implementing a data set discovery engine. The data set discovery engine comprises a data set indexer configured to generate similarity indexes for a plurality of data sets, and a relativistic retriever coupled to the data set indexer and configured to obtain a suitability template for a query and to execute the query against one or more of the similarity indexes based at least in part on the suitability template. A given one of the similarity indexes comprises at least first and second auxiliary information generated from respective ones of at least first and second different similarity measures of a plurality of different similarity measures. The first and second similarity measures comprise selected ones of the plurality of different similarity measures that are supported by the data set discovery engine with the supported similarity measures comprising both frequency-based and non-frequency-based similarity measures.

Abstract: An apparatus in one embodiment comprises an analytics platform and a controller. The controller is associated with the analytics platform and configured to control automated deployment of analytics workspaces of the analytics platform. The analytics platform includes or otherwise has access to sets of at least data ingestion engines, data containers, analytics tools and virtual resources. The controller is configured to deploy a given one of the analytics workspaces of the analytics platform as an at least partially user-specified combination of particular selected ones of the data ingestion engines, data containers, analytics tools and virtual resources. The controller may additionally be configured to monitor usage of the combination of particular selected ones of the data ingestion engines, data containers, analytics tools and virtual resources of the given analytics workspace, and to alter the combination responsive to the monitoring.

Abstract: An apparatus in one embodiment comprises an ingestion manager, a plurality of ingestion engines associated with the ingestion manager, and an analytics platform configured to receive data from the ingestion engines under the control of the ingestion manager. The ingestion manager is configured to interact with one or more of the ingestion engines in conjunction with providing data to a given one of a plurality of analytics workspaces of the analytics platform. For example, the analytics workspaces of the analytics platform are illustratively configured to receive data from respective potentially disjoint subsets of the ingestion engines under the control of the ingestion manager. Additionally or alternatively, the ingestion manager may be configured to implement data-as-a-service functionality for one or more of the analytics workspaces of the analytics platform.