Method and system for managing handover decisions while maintaining quality-of-service (QoS) of active user application sessions in a wireless network is disclosed. The method includes determining QoS requirement for each of the active user application sessions (UASs) based on user entitlements for relevant services associated with the active UASs, assessing the active UASs to determine instantaneous QoS level for each of the active UASs, and identifying impacted user equipment (UE) based on an overall QoS level for a set of active UAS, from among the active UASs, running on the impacted UE. The overall QoS level may be based on the instantaneous QoS level and the QoS requirement for each UAS in the set of active UAS. The method further includes managing a handover decision for the impacted UE based on a need for a handover of the impacted UE and a feasibility of the handover of the impacted UE.

The described technology is generally directed towards having a wireless network device assist a user equipment to facilitate narrow beam handover. A network device determines narrow beam handover candidates of neighbor cell sites based on geometric relationships between the user equipment, a serving cell site and the neighbor cell site candidates. Historical information such as previous narrow beam handovers from a serving beam to neighbor narrow beams can be used to select a lesser number of the possible candidate beams. The network device sends the candidate beams to the user equipment, which then measures and reports the measurements to the network device. If handover criteria based on the measurement is met, the network device orders a handover to a selected narrow beam, e.g., the narrow beam with the best measurement data of the candidates.

A system accesses a plurality of ratio values for similar AOIs, each ratio value indicating a ratio between a count of device users at a similar AOI and a count of vehicles of the similar AOI. The similar AOIs are AOIs that have measurable characteristics within a range of similarity with those of the target AOI. The count of vehicles of the similar AOI is generated using aerial imagery received for the similar AOI. The count of device users at the similar AOI is extracted from third party data for the similar AOI. The system accesses a count of a number of reported device users at the target AOI, and generates an estimate of the vehicle count for the target AOI using the count of the number of reported device users at the target AOI and a combination of the plurality of ratio values for similar AOIs.

A method for selecting a gateway node to support handover when a user equipment (UE) attaches to a 4G long-term evolution (LTE) network may include receiving a prediction from a machine learning engine predicting whether the UE is more likely to handover between the 4G LTE network and a 3G network or between the 4G LTE network and a 5G network based on handover data in the UE's location area. The method may further include selecting a first gateway node if the prediction indicates that the UE is more likely to handover between the 4G LTE network and the 3G network, and selecting a second gateway node if the prediction indicates that the UE is more likely to handover between the 4G LTE network and a 5G network. The first gateway node may support 4G and 3G sessions, and the second gateway node may support 4G and 5G sessions.

Methods and systems are described for generating and utilizing a pattern of association. The pattern of association can comprise information that indicates to which of a plurality of network devices one or more mobile devices are likely to connect. The pattern of association can comprise information that indicates an order of association. The pattern of association can be associated with one or more factors which can be any information that provides insight into the pattern of association. The pattern of association can be used to identify a next network device that a mobile device will transition to, based on which network device the mobile device is currently connected to. Data, such as authentication information, can be pushed to the identified next network device to reduce network connectivity issues that may occur by transitioning between network devices.

The present disclosure provides relates to methods and apparatus for handover optimization in a 5G context using reinforcement learning (RL). In contrast to the conventional handover methods, handovers between base-stations (BSs) are controlled using a centralized RL-based machine learning (ML) agent. This ML agent handles the radio measurement reports from the UEs and chooses appropriate handover actions in accordance with the RL machine learning framework to maximize a long-term utility.

A communication device includes a wireless communication device, a location information acquisition device, a storage and a controller. The wireless communication device wirelessly communicates with a base station used as a connection destination. The location information acquisition device acquires location information on a location of the communication device. The storage stores historical communication information on past communication status. The controller determines a degree of risk of occurrence of reduction in an amount of available communication bandwidth beyond a tolerance limit based on the historical communication information and the location information. The controller further controls a transmission rate for communicating the data based on a result of determination of the degree of risk.

In a network handover method disclosed in this application, when an electronic device accesses a first mobile network by using the first SIM card, the electronic device obtains network information of the first mobile network in a process in which the electronic device moves along a first route. When the electronic device predicts, according to the obtained network information of the first mobile network, that an exception is going to occur in the first mobile network, the electronic device accesses the second mobile network by using the second SIM card. In this technical solution, an electronic device having a dual SIM card can be handed over from a first mobile network to a second mobile network in advance when it is predicted that an exception is going to occur in the first mobile network, thereby reducing the possibility of frame freezing or network disconnecting when a user accesses the Internet.

The present invention discloses a terminal configuration method, including: obtaining, by a network device, cell access information and/or beam access information; determining configuration information based on the cell access information and/or the beam access information; and sending the configuration information to a terminal. The present invention further discloses a network device and a terminal that can implement the foregoing terminal configuration method. In the present invention, mobility of the terminal can be accurately determined, so that cell reselection performance, cell handover performance, or beam change performance of the terminal can be improved.

A system for location detection is provided that includes a device that is disposed within a detection environment and is adapted to communicate over a radio frequency communication link. The device may be a wireless access point disposed within the environment, including a wireless transceiver in communication with the device over a radio frequency communication link using a plurality of channels, and recording a channel state information data set for the radio frequency communication link. The wireless access point Wi-Fi signal is used to detect motion within the detection environment. The system further integrates with 5G networks to allow motion and location tracking outside of the detection environment and range of the Wi-Fi motion detection system by using the 5G CSI data on a mobile station, such as a mobile device.