Abstract: A radio base station in a mobile communication network sends a handover request message to multiple target base stations to initiate handover of a wireless device. The radio base station maintains one or more handovers counters used for monitoring and evaluating performance. The base station receives one or more handover response messages from respective target base stations. In response to receiving the one or more handover response messages, the base station increments a handover counter associated with the wireless device once regardless of a number of the handover response messages received.

Abstract: A method performed by a wireless device includes obtaining User Plane (UP) information comprising at least one Handover (HO) interruption time. The at least one HO interruption time is associated with a first packet of a plurality of duplicate packets received by the wireless device. The wireless device transmits, to a network node, a report associated with a handover of the wireless device, the report comprising the UP information comprising the at least one HO interruption time associated with the first packet of the plurality of duplicate packets received by the wireless device.

Abstract: Techniques for inter base station handovers are provided for the case where a wireless device is operating in a PDCP packet duplication mode. The handover techniques enable the wireless device to transition from PDCP packet duplication with the source cell to DAPS and to transition back to PDCP packet duplication with the target cell when the handover is complete. In some embodiments, the RLC entities established with the source cell are preserved during the inter base station handover. The handover techniques ensure that QoS requirements for URLLC can be met during the inter base station handover.

Abstract: A method performed by a wireless device includes declaring a radio link failure (RLF) in a source cell of a source network node during a dual active protocol stack handover (DAPS HO) from the source cell of the source network node to a target cell of a target network node. The wireless device stores information associated with the DAPS HO and information associated with the RLF. The wireless device transmits the information to an access node.

Abstract: The present disclosure relates to a computer implemented method, performed by a wireless device, for reducing data transmission in a communications network by compression of measurements of network characteristics of the communications network, comprising the method steps of: obtaining a trained encoder, of a trained autoencoder, performing a measurements of network characteristics of the communications network, applying the trained encoder to compress the result of the measurements of network characteristics, and transmitting the compressed representation of measurements of network characteristics towards a network entity, whereby the network entity may perform a method comprising the method steps of: obtaining a trained decoder, of the trained autoencoder, receiving a compressed representation of a measurements of network characteristics, and applying the trained decoder to reconstruct the compressed representation of the measurements of network characteristics.

Abstract: A first network node in a communication network can communicate with a second network node to configure a conditional handover (“CHO”) for a communication device. The first network node can, responsive to communicating with the second network node to configure the CHO, determine a conditional reconfiguration delay.

Abstract: Systems and methods are disclosed herein for enhanced feedback for cascaded federated machine learning (ML). In one embodiment, a method of operation of a server comprises, for a training epoch, receiving, from each of client device, information including a local ML model as trained at the client device and an estimated value of each parameter output by the local ML model. The method further comprises aggregating the local ML models to provide a global ML model and training a network ML model based on the estimated values of each of the parameters output by the local ML models and global data available at the server. The method further comprises providing, to each client device, information including the global ML model and feedback information related to a hidden neural network layer of the network ML model. The method further comprises repeating the process for one or more additional training epochs.

Abstract: In a method in a user equipment, UE, in a communications network, of determining whether to perform a handover procedure from a first network node to a second network node, a location of the UE is provided as input to a model stored on the UE, the model having been trained using a machine learning process to predict conditions on the second network node in the communications network based on the location of the UE. A prediction of conditions on the second network node at the provided location of the UE is provided by the model. The received predicted conditions are then used to determine whether to perform a handover procedure.

Abstract: Methods and apparatus in a communications network as described herein are suitable for determining a first model for use in predicting conditions on carrier frequencies in the communications network. In a method, network measurements are obtained (302) of conditions on a plurality of carrier frequencies. A first model is then determined (304) based on the obtained measurements that takes as input the conditions on a first subset of the plurality of carrier frequencies and outputs a prediction of the conditions on a second subset of the plurality of carrier frequencies, based on the conditions of the first subset of carrier frequencies.

Abstract: A method for estimating up-link latency, and/or down-link latency, and/or round-trip latency in a packet based wireless network for communication between two network nodes, wherein the method includes. a. measuring one or more metrics and/or using information from network procedures to estimate metrics, wherein the metrics have at least one or more of radio metrics available to a UE (User Equipment) or to a BS (Base Station) or similar access-point, b. measuring the metrics defined in a) either in a dedicated mode using packet sequence, and/or in a dedicated mode using available traffic, and/or in an idle mode, c. measuring the metrics defined in a) both on a serving and a non-serving cells, and/or beams, d. estimating up-link latency, and/or down-link latency, and/or round-trip latency by using multivariable, non-linear or linear function prediction, machine learning based prediction or mathematical or logical predictions based on the metrics defined in a).