At&t Intellectual Property I, LP

At&t Mobility Ii LLC

Jie Chen

Wenjie Zhao

Huahui Wang

Abraham George

Ye Ge

Sheldon Kent Meredith

Jeremy Fix

Sarat Puthenpura

Sam Houston Parker

Yuning Yang

Huijing Yang

Ke Zhang

Laurie Bigler

Sichong Guan

Ganesh Krishnamurthi

Zhen Wan

Yu Chen

Xidao Wen

The described technology is generally directed towards spammer location detection, and in particular, to locating a spammer that makes multiple calls from a given location via a cellular communications network. In some examples, network equipment can obtain call trace records associated with the multiple calls, identify a group of call trace records based on a shared call trace feature, aggregate data from call trace records within the group, and determine an estimated location based on the aggregated data.

Spammer location detection

Locations and azimuths of cells of a communication network can be estimated, determined, and validated. Cell attribute management component (CAMC) can estimate, determine, and/or validate cell locations based on analysis of timing advance (TA) measurement data and/or location data associated with devices associated with base stations associated with cells. CAMC can estimate azimuth of a cell associated with a base station based on analysis of a validated cell location of the cell and location data associated with devices associated with the cell. CAMC can determine whether a recorded azimuth of the cell is validated based on analysis of the estimated azimuth of the cell and the recorded azimuth of the cell. CAMC can tag the recorded azimuth of the cell as validated if applicable azimuth accuracy criteria is met, inaccurate if applicable azimuth criteria is not met, or omni if the cell is an omni cell.

Automated cell azimuth estimation and validation

The described technology is generally directed towards user equipment (UE) geolocation using a long history of network information. In some examples, a long history of network information associated with a UE can be processed to identify frequently repeated serving cell and correlated timing advance values. The frequently repeated serving cell and correlated timing advance values are indicative of frequently visited places. Next, the long history can be leveraged to determine locations of the frequently visited places with enhanced accuracy, and the resulting enhanced accuracy locations can be identified in a location lookup table for the UE. When the UE subsequently connects to the frequently repeated serving cell and the correlated timing advance value is observed, the location lookup table can be used to quickly assign an enhanced accuracy location to the UE.

User equipment geolocation using a history of network information

The described technology is generally directed towards user equipment geolocation. Network measurement data associated with user equipment can be separated into static periods in which the user equipment was not moving, and moving periods in which the user equipment was moving. Static location processing can be applied to determine static locations from the static period network measurements, and moving location processing can be applied to determine moving locations from the moving period network measurements. Resulting static location information and moving location information can then be merged in order to improve the accuracy of both the static and the moving location information. The enhanced accuracy location information can be stored and used for any desired application.

Moving user equipment geolocation

Static user equipment geolocation

A processing system including at least one processor may obtain operational data from a radio access network (RAN), format the operational data into state information and reward information for a reinforcement learning agent (RLA), processing the state information and the reward information via the RLA, where the RLA comprises a plurality of sub-agents, each comprising a respective neural network, each of the neural networks encoding a respective policy for selecting at least one setting of at least one parameter of the RAN to increase a respective predicted reward in accordance with the state information, and where each neural network is updated in accordance with the reward information. The processing system may further determine settings for parameters of the RAN via the RLA, where the RLA determines the settings in accordance with selections for the settings via the plurality of sub-agents, and apply the plurality of settings to the RAN.

Radio access network control with deep reinforcement learning

Facilitating analysis and resource planning for advanced heterogeneous networks (e.g., 5G, 6G, and beyond) is provided herein. A system is provided that includes a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations. The operations can include determining that a resource is to be added to existing resources at a grid level of a heterogeneous network. Further, the operations can include selecting candidate locations for placement of the resource based on a coverage-driven objective and a capacity-driven objective defined for the heterogeneous network. The coverage-driven objective can be associated with a demand for services within the grid level of the heterogeneous network. The capacity-driven objective can be associated with demand growth within the grid level of the heterogeneous network. The resource can be a fifth generation millimeter wave node or a cloud radio access network node.

Facilitating heterogeneous network analysis and resource planning for advanced networks

Locations of cells of a communication network can be estimated, determined, and validated. Cell location component (CLC) can analyze timing advance (TA) measurement data and/or location data associated with devices associated with a base station associated with one or more cells. CLC can estimate a first location of the base station, based on the TA measurement data and/or location data, to facilitate estimating the location of an associated cell. CLC can validate the estimated cell location or recorded cell location of the cell (recorded in a cell location pool) based on analysis of estimated cell location, recorded cell location, TA measurement data, and/or location data, and, based on the validation, can tag the cell location determination as accurate, acceptable, bad, or uncertain. CLC can request additional monitoring of a cell location determination tagged as uncertain, or investigation of a cell location determination tagged as bad.

Automated cell location estimation and validation

The technologies described herein are generally directed to facilitating operation of a system for implementing fifth generation (5G) or other next generation networks. In accordance with one or more embodiments, a method described herein can include identifying, by a device comprising a processor, predicted resource usage of a first antenna covering a geographic zone. Further, the method can include selecting, by the device, a group of geographic siting locations within the geographic zone for potentially siting ones of a group of second antennas. In addition, selecting, by the device, a spatial arrangement in relation to the first antenna, of a subset of the group of geographic siting locations can occur, with a selected spatial arrangement including an arrangement to maintain the predicted resource usage in the condition.

Densifying a mobility network by siting antennas with demand zone planning, in a communications network

A device can receive, from a network node device, call trace event data relating to characteristics of a wireless communication session between the network node device and a user equipment. The device can sequence and combine the call trace event data for a period of the wireless communication session. The device can analyze the call trace event data to determine a category of network communication traffic transmitted via a communication channel between the network node device and the user equipment. In response to a determination that the network communication traffic comprises streaming video packets, the device can facilitate directing of network resources to be allocated to support the wireless communication session.

Real-time user traffic classification in wireless networks

Concepts and technologies disclosed herein are directed to the optimization of over-the-air ('OTA') file distribution for connected cars based upon a heuristic scheduling algorithm. A schedule provided by the heuristic scheduling algorithm is designed to distribute OTA data flow to connected cars over the network (geographically) and over a scheduling time horizon (timely), and is capable of reducing the negative impact of OTA file updates on overall wireless network performance. This schedule is created based upon historical statistics associated with connected car driving patterns and simulations of connected car-specific OTA traffic over the network. By leveraging connected cars that connect to different cells at different times based upon driving patterns, the heuristic scheduling algorithm is effective in reducing OTA impact on the network.

Optimization of over-the-air file distribution for connected cars based upon a heuristic scheduling algorithm

The described technology is generally directed towards user equipment (UE) geolocation. A machine learning model can be trained to estimate UE locations based on historical network communication data associated with the UEs. In order to train the machine learning model, known previous UE locations and corresponding historical network communication data can be provided to the machine learning model. A variety of other information, such as topographical information, can also be provided to the machine learning model. The machine learning model can be trained to predict the known previous UE locations based on the corresponding historical network communication data and any other provided information. Once it is trained, the machine learning model can be deployed to estimate real-time UE locations based on historical network communication data associated with the UEs.

User equipment geolocation

Techniques for locating a mobile device using a time distance of arrival (TDOA) method with disturbance scrutiny are provided. In an aspect, for respective combinations of three base station devices of a number of base station devices greater than or equal to three, intersections in hyperbolic curves, generated using a closed form function with input values based on differences of distances from the device to pairs of base station devices of the respective combinations of three base station devices, are determined. The intersection points are then tested for robustness against measurement errors associated with the input values and a subset of the intersection points that are associated with a degree of resistance to the measurement errors are selected to estimate a location of the device.

Growing community of inventors

Watchung, NJ, United States of America

Jie Chen