Abstract: The described technology is generally directed towards beam recovery for an antenna array. One or more recovery beams or recovery beam patterns can be defined for an antenna array, and in response to a failure, the antenna array can be restored to a defined recovery beam or recovery beam pattern. Techniques for defining recovery beams and recovery beam patterns for the antenna array, selecting a recovery beam or recovery beam pattern for the antenna array, and entering a selected recovery beam or recovery beam pattern by the antenna array are also disclosed.

Abstract: A model-driven system automatically deploys a virtualized service, including multiple service components, on a distributed cloud infrastructure. A master service orchestrator causes a cloud platform orchestrator to retrieve a cloud services archive file, extract a cloud resource configuration template and create cloud resources at appropriate data centers as specified. The master service orchestrator also causes a software defined network controller to retrieve the cloud services archive file, to extract a cloud network configuration template and to configure layer 1 through layer 3 virtual network functions and to set up routes between them. Additionally, the master service orchestrator causes an application controller to retrieve the cloud services archive file, to extract a deployment orchestration plan and to configure and start layer 4 through layer 7 application components and bring them to a state of operational readiness.

Abstract: Aspects of the subject disclosure may include, for example, a device including a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of receiving signal to noise and interference ratio (SINR) measurements from a cell for two or more uplink carriers associated with a mobile device; determining an optimal uplink carrier from the two or more uplink carriers based on plural parameters, wherein the plural parameters include the SINR measurements; selecting the optimal uplink carrier from the two or more uplink carriers; and sending the optimal uplink carrier selected to the cell, wherein the mobile device uses the optimal uplink carrier for uplink transmissions. Other embodiments are disclosed.

Abstract: A system can obtain a labelled data set, including historic video data and labelled events. The system can divide the labelled data set into historic training/testing data sets. The system can determine, using the historic training data set, a plurality of different parameter configurations to be used by a video encoder to encode a video that includes a plurality of video frames. Each parameter configuration can include a group of pictures (“GOP”) size and a scenecut threshold. The system can calculate an accuracy of event detection (“ACC”) and a filtering rate (“FR”) for each parameter configuration. The system can calculate, for each parameter configuration of the plurality of different parameter configurations, a harmonic mean between the ACC and the FR. The system can then select a best parameter configuration of the plurality of different parameter configurations based upon the parameter configuration that has the highest harmonic mean.

Abstract: The technologies described herein are generally directed to modeling radio wave propagation in a fifth generation (5G) network or other next generation networks. For example, a method described herein can include, for a network application, identifying, by a system comprising a processor, a user equipment communicatively coupled to base station equipment via a first network connection implementing a first radio access technology and a second network connection implementing a second radio access technology. The method can further include identifying, by the system, performance characteristics of the first network connection and the second network connection. Further, the method can include, based on the first performance characteristic and the second performance characteristic, facilitating, by the system, allocating, to the user equipment, power for uplink transmission by the first network connection and the second network connection, resulting in an uplink power allocation.

Abstract: The described technology is generally directed towards a cellular network area optimizer. The area optimizer observes cellular network conditions at multiple radio access network (RAN) nodes within a target area. Based on observed conditions, the area optimizer applies a set of parameter values at the multiple RAN nodes. The set of parameter values enhances the overall throughput, while maintaining or improving connection retainability and accessibility, of the multiple RAN nodes under the observed conditions. The area optimizer learns different sets of parameter values to apply in response to different observed conditions by making parameter value adjustments and observing the effect of the adjustments on overall throughput of the RAN nodes in the target area.

Abstract: Aspects of the subject disclosure may include, for example, obtaining predicted available bandwidths for an end user device, monitoring buffer occupancy of a buffer of the end user device, determining bit rates for portions of media content according to the predicted available bandwidths and according to the buffer occupancy, and adjusting bit rates for portions of media content according to the predicted available bandwidths and according to the buffer occupancy during streaming of the media content to the end user device over a wireless network. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, receiving, over a communication network, a plurality of requests for frames of video content to provide to a mobile device. Further embodiments can include determining a first portion of the plurality of requests are for pre-fetch frames of the video content, and providing, over the communication network, the pre-fetch frames to the mobile device over a default bearer path. Additional embodiments can include determining a second portion of the plurality of requests are for emergent frames of the video content, and providing, over the communication network, the emergent frames to the mobile device over a dedicated bearer path. Other embodiments are disclosed.

Abstract: The described technology is generally directed towards reducing latency in a wireless communications network. Radio access network latency data corresponding to a measured latency impact criterion is obtained by a network device of a wireless network. Based on the radio access network latency data, latency guidance data usable by the radio network device to achieve a reduction in communication latency that is experienced by a user equipment is predicted, e.g., by a learned model. The latency guidance data can be used to facilitate a reduction in the communication latency that is experienced by a user equipment.

Abstract: The described technology is generally directed towards beam recovery for an antenna array. One or more recovery beams or recovery beam patterns can be defined for an antenna array, and in response to a failure, the antenna array can be restored to a defined recovery beam or recovery beam pattern. Techniques for defining recovery beams and recovery beam patterns for the antenna array, selecting a recovery beam or recovery beam pattern for the antenna array, and entering a selected recovery beam or recovery beam pattern by the antenna array are also disclosed.

Abstract: Aspects of the subject disclosure may include, for example, obtaining predicted available bandwidths for an end user device, monitoring buffer occupancy of a buffer of the end user device, determining bit rates for portions of media content according to the predicted available bandwidths and according to the buffer occupancy, and adjusting bit rates for portions of media content according to the predicted available bandwidths and according to the buffer occupancy during streaming of the media content to the end user device over a wireless network. Other embodiments are disclosed.

Abstract: The disclosed technology is directed towards dynamic spread spectrum (DSS) deployments, in which two cells such as an LTE cell and a new radio (NR) cell share available physical resource blocks during a given transmission time interval. The LTE cell and NR cell determine priority values for their user equipments to be scheduled, and both cells provide requested scheduling information including the priority values and requested resource blocks for user equipments in the upcoming transmission time interval. Based on the priority values, a real-time joint scheduler processes the combined scheduling information from both cells to determine how many physical resource blocks of the total available to allocate to the LTE cell and how many to allocate to the NR cell for the next transmission time interval. To avoid collisions, the LTE cell and NR cell modify their respective UE schedules based on their respective number of allocated physical resource blocks.

Abstract: Aspects of the subject disclosure may include, for example, system for tile-based video streaming using a proxy executing at a mobile edge cloud, which adaptively offloads decoding and merging of video tiles from mobile devices to the mobile edge cloud. A processing system including the proxy communicates with a video server and a client device. The proxy receives a request for video content from a client device; the request includes historical field of view (FoV) information. The proxy predicts a client FoV, requests video tiles from the server, downloads the tiles from the server, generates a video chunk by decoding and merging the downloaded tiles, and delivers the video chunk to the client device. The client device performs local decoding and rendering of the generated video chunk. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, receiving, over a communication network, a plurality of requests for frames of video content to provide to a mobile device. Further embodiments can include determining a first portion of the plurality of requests are for pre-fetch frames of the video content, and providing, over the communication network, the pre-fetch frames to the mobile device over a default bearer path. Additional embodiments can include determining a second portion of the plurality of requests are for emergent frames of the video content, and providing, over the communication network, the emergent frames to the mobile device over a dedicated bearer path. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

Abstract: The described technology is generally directed towards wireless communications for vehicle collision response. Devices onboard vehicles can wirelessly exchange information in response to detecting a collision. Public encryption keys can be exchanged, and exchanged information can optionally be encrypted using a received public encryption key. Exchanged information can include vehicle identification information and collision information. The collision information can furthermore be certified using a vehicle's private encryption key.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system obtains a sample of a content stream directed to a user device, identifies a type of the content stream, and selects a model for recognizing objects appearing in the content stream. The system analyzes the content stream in accordance with the model to recognize the object, generates a label for the object, and associates the label with the object in the content stream. The system also delivers the content stream for presentation at the user device; the label is delivered in-line with respect to the content stream and is generated in real time with respect to the presentation. The method further includes training the model in accordance with a machine learning procedure; the model is refined based on the analyzing of the content stream. Other embodiments are disclosed.

Abstract: The disclosed technology is directed towards dynamic spread spectrum (DSS) deployments, in which two cells such as an LTE cell and a new radio (NR) cell share available physical resource blocks during a given transmission time interval. The LTE cell and NR cell determine priority values for their user equipments to be scheduled, and both cells provide requested scheduling information including the priority values and requested resource blocks for user equipments in the upcoming transmission time interval. Based on the priority values, a real-time joint scheduler processes the combined scheduling information from both cells to determine how many physical resource blocks of the total available to allocate to the LTE cell and how many to allocate to the NR cell for the next transmission time interval. To avoid collisions, the LTE cell and NR cell modify their respective UE schedules based on their respective number of allocated physical resource blocks.

Abstract: Deployment of Internet-of-things devices can comprise sensors deployed in remote and hard to reach areas and locations. Due to lack of access to reliable power, these sensors cannot always be connected to a network and also have limited computation power. Consequently, a mechanism can be established to periodically access these sensors and collect data from them. The mechanism can utilize a mobile radio unit device to serve as data collectors. The mobile radio unit device can make use of an adaptive beam scanning to perform sensory data collection via the beam scanning operation. Additionally, the platform can also comprise a radio access network intelligent controller to manage the data collecting radio units by providing specific instructions and data collection methodologies.