Methods and apparatuses for load balance are disclosed. According to an embodiment, a first base station determines a first spatial distribution of terminal devices in a first cell of the first base station, based on measurement reports which are received from the terminal devices and comprise beam candidates suitable for serving the terminal devices. The first base station determines whether the first cell has a first area whose load needs to be offloaded, based on the first spatial distribution. When determining that the first cell has the first area, the first base station sends, to one or more neighboring base stations, an offload request comprising part of the first spatial distribution corresponding to the first area.

A method, system and device load balancing in a telecommunications network is provided where the selection of the one or more User Equipment (UE) 150, to be relocated from a source cell 112 to a target cell 122, is based on a prediction value of the performance in the target cell. The prediction of the performance in the target cell is performed by mapping the current load of the target cell and a current detected signal of the target cell, into a perceived performance, perceived by UEs that have been relocated previously. After relocation of the UE the perceived performance in the target cell is measured actually and fed back 312 by the target cell RBS 120 to the source cell RBS 110, and used for updating the predicted performance value.

A processing system may obtain values of carrier attributes for a new carrier to be deployed in a cellular network, obtain values of the carrier attributes and values of a configuration parameter for a plurality of existing carriers in the cellular network, and construct an attribute value matrix comprising the values of the carrier attributes for the plurality of existing carriers, where the attribute value matrix associates the carrier attributes to the plurality of existing carriers, apply a regression to a function associating the attribute value matrix to a vector of the values of the configuration parameter for the plurality of existing carriers to learn coefficients of the function, apply the coefficients to a vector comprising the values of the plurality of carrier attributes for the new carrier to generate a value of the configuration parameter for the new carrier, and apply the generated value to the new carrier.

A paging method, includes: in response to determining that user equipment (UE) to which a Subscriber Identification Module (SIM) card to be paged belongs is multi-SIM user equipment and multiple SIM cards of the multi-SIM UE belong to a same network operator's network, determining a first base station accessed by the connected SIM card of the multi-SIM user equipment; and sending paging signaling for paging the SIM card to be paged to the first base station.

The present invention discloses a method and apparatus for identifying handover requirement by a Radio access network (RAN) controller in open RAN (O-RAN) environment. The O-RAN environment has a virtualized network architecture having at least one RAN controller that is able to control, via an E2 node, a plurality of user equipments (UEs) positioned in a serving cell, a cell covering a location for serving a UE, the serving cell is adjacent to a plurality of neighbour cells. The method includes parallel execution of the operations performed by the RAN controller for each serving cell and each of the neighbor cell and updating CIOs in stepwise i.e., gradually with repeated comparing of the serving cell load parameter with each of the plurality of neighbour cell load parameters and updating the serving cell handover parameter and the plurality of neighbour cell handover parameters based on the comparison.

In a wireless network with a plurality of access points, device calculates, for each wireless station in the network, a score based on at least an availability of the wireless network for the wireless station, combines the scores for the wireless stations into a current network score for a present configuration of the wireless network, calculates a plurality of predicted network scores corresponding to predicted network configurations with one wireless station moved to a different access point than in the present configuration, each predicted network score being a combination of the scores for wireless stations not moved in the predicted network configuration and a predicted score for the wireless station moved in the predicted network configuration, selects one of the current network score and the plurality of predicted network scores that satisfies a criterion; and, in case a predicted network score is selected.

The present invention is directed to communications methods and apparatus for efficiently distributing traffic to processing entities. An exemplary method includes the steps of: receiving, at a first Session Initiation Protocol (SIP) load balancer (SLB), a first SIP INVITE message; selecting, at the first SLB, which Session Border Controller (SBC) in a first cluster of SBCs to send the first SIP invite message based on a message allocation weight determined based on message loss information corresponding to different SBCs in the first cluster of SBCs, the selecting including allocating a portion of incoming received SIP INVITE messages to an individual SBC based on a message loss rate corresponding to the individual SBC and the message allocation rate, said selecting including selecting a first SBC from the first cluster of SBCs to send said first SIP INVITE message, and sending the first SIP INVITE message to the first SBC.

A method and system for controlling uplink communication from a user equipment device (UE) that has at least two co-existing air-interface connections including a first air-interface connection with a first access node and a second air-interface connection with a second access node. An example method includes comparing a level of antenna pattern efficiency associated with the first air-interface connection with a level of antenna pattern efficiency associated with the second air-interface connection and, based at least on the comparing, configuring an uplink split ratio defining a distribution of uplink user-plane data flow of the UE between at least the first air-interface connection and the second air-interface connection. In an example implementation, this could involve configuring one of the air-interface connections as a primary uplink path to which the UE restricts its uplink communication unless and until a trigger occurs for transitioning the UE to operate in an split-uplink mode.

A processing system may obtain values of carrier attributes for a new carrier to be deployed in a cellular network, obtain values of the carrier attributes and values of a configuration parameter for a plurality of existing carriers in the cellular network, and construct an attribute value matrix comprising the values of the carrier attributes for the plurality of existing carriers, where the attribute value matrix associates the carrier attributes to the plurality of existing carriers, apply a regression to a function associating the attribute value matrix to a vector of the values of the configuration parameter for the plurality of existing carriers to learn coefficients of the function, apply the coefficients to a vector comprising the values of the plurality of carrier attributes for the new carrier to generate a value of the configuration parameter for the new carrier, and apply the generated value to the new carrier.

Among other things there is disclosed a method for determining corrected load values. The method includes obtaining a set of input features, each input feature being one of: i) a reported load value that was reported by a target base station to a source base station and ii) a derived load value derived using the reported load value; obtaining a set of output features, each output feature being a determined load value determined by the source base station, wherein each output feature is associated with a single one of the input features; and determining, using the set of input features and the set of output features, a set of one or more parameters for a mathematical model for determining a corrected load value based on one or more load values provided by the target base station.