Abstract: A communication device in a communications network that includes a first network node can receive an indication of a network configuration identifier, ID, from the first network node. The network configuration ID can be associated with a future network configuration. The communication device can r determine whether a current model supports the future network configuration. The communication device can determine a future model based on determining whether the current model supports the future network configuration. The communication device can receive an indication of when the future network configuration will be active. Subsequent to receiving the indication that the future network configuration is active, the communication device can communicate with a second network node using the future model.

Abstract: Methods and apparatus are provided. In an example aspect, a method in a wireless communication device of precoding symbols for transmission is provided. The method includes determining an indication of distortion of symbols transmitted by transmission apparatus of the wireless communication device or an indication of a correction for the distortion, determining precoding parameters based on the indication of distortion or the indication of the correction, and precoding symbols to be transmitted based on the precoding parameters.

Abstract: Embodiments herein relate to, for example, a method performed by a transmitter node (12) for adapting a signal processing capability of a receiver of a receiver node (10) in a communication network (1). The transmitter node (12) obtains an estimated signal quality of a signal, an indication of a hardware quality, a status of an energy source associated with the receiver, and/or a target KPI. The transmitter node (12) further initiates an adaption of the signal processing capability of the receiver based on the estimated signal quality, the indicated hardware quality, the status of the energy source, and/or the target KPI.

Abstract: Systems and methods related to traffic flow prediction in a wireless network are disclosed. In one embodiment, a computer-implemented method comprises collecting training data comprising Internet Protocol (IP) addresses extracted from packets for traffic flows in a wireless network and one or more actual traffic type related parameters for each of the traffic flows. The method further comprises training heavy-hitter IP address encodings based on the extracted IP addresses and encoding the extracted IP addresses using the trained heavy-hitter IP address encodings. The method further comprises training a traffic type predictor of a traffic flow predictor based on the encoded IP addresses and the one or more actual traffic type related parameters for each of the traffic flows, where the traffic type predictor is a learning model that maps encoded IP addresses to one or more predicted traffic type related parameters.

Abstract: A method for managing a first node in a communication network is disclosed, wherein the first node is operable to exchange traffic flows with other nodes in the communication network. The method includes using a Variational Autoencoder (VAE) to generate a predicted traffic distribution for the first node, wherein the VAE has been trained using information about historical data flows exchanged by the first node with at least one other node in the communication network, and configuring at least one radio resource parameter of the first node based on the obtained predicted traffic distribution for the first node. Also disclosed are a method including training a VAE and nodes and a computer program product suitable for carrying out such methods.

Abstract: Methods and apparatus are provided. In an example aspect, a method in a wireless communication device of precoding symbols for transmission is provided. The method includes determining an indication of distortion of symbols transmitted by transmission apparatus of the wireless communication device or an indication of a correction for the distortion, determining precoding parameters based on the indication of distortion or the indication of the correction, and precoding symbols to be transmitted based on the precoding parameters.

Abstract: A method performed by a first network node is provided. The method includes determining a power backoff indicator (PBI) for a first user equipment (UE) based on at least one of channel conditions of the first UE and channel conditions of a second UE, data reliability requirements of the second UE, and data performance of the first UE. The method includes transmitting the PBI toward the first UE. The method includes receiving second data from the first UE, wherein transmission of the second data has been adjusted based on the PBI. The UE receives the PBI. Responsive to determining to apply the PBI, the UE backs off the power by adjusting the power according to at least one of a configuration and the PBI. The UE transmits second data to the first network node with the backed off or adjusted power.

Abstract: Methods and apparatuses for adaptation of communication parameter are disclosed. According to an embodiment, a transmitter performs a first transmission to a receiver. The transmitter receives, from the receiver, first information related to one or more candidate constellation maps adapted to one or more current operating conditions, or second information usable for deriving the one or more candidate constellation maps. The transmitter determines a target constellation map based at least on the first information or the second information. The transmitter performs a second transmission to the receiver based on the determined target constellation map.

Abstract: Computer implemented methods for training a Student Neural Network, SNN, and for managing an environment of a communication network using a trained SNN are disclosed. The SNN is for generating an action prediction matrix for an environment in a communication network, the action prediction matrix comprising action predictions for a plurality of nodes or resources in the environment. The training method comprises using a Reinforcement Learning process to train a Teacher Neural Network, TNN, to generate an action prediction for a resource or node in the environment, and using the trained TNN to generate a first training data set including action predictions for individual nodes or resources. The training method further comprises generating a second training data set from the first training data set such that the second training data set includes action prediction matrices, and using the second training data set to update values of the parameters of the SNN.

Abstract: Systems and methods related to traffic flow prediction in a wireless network are disclosed. In one embodiment, a computer-implemented method comprises collecting training data comprising Internet Protocol (IP) addresses extracted from packets for traffic flows in a wireless network and one or more actual traffic type related parameters for each of the traffic flows. The method further comprises training heavy-hitter IP address encodings based on the extracted IP addresses and encoding the extracted IP addresses using the trained heavy-hitter IP address encodings. The method further comprises training a traffic type predictor of a traffic flow predictor based on the encoded IP addresses and the one or more actual traffic type related parameters for each of the traffic flows, where the traffic type predictor is a learning model that maps encoded IP addresses to one or more predicted traffic type related parameters.

Abstract: A method for dynamically assigning communication resources between two or more radio access technologies (RAT) in a wireless access network. The method includes obtaining a network observation ot indicating a current state of the wireless access network, predicting a sequence of future states of the wireless access network by iteratively simulating hypothetical communication resource assignments a1, a2, a3 over a time window w starting from the current state, evaluating a reward function for each hypothetical communication resource assignment a1, a2, a3 over the time window w, and dynamically assigning the communication resources based on the simulated hypothetical communication resource assignment a1 associated with maximized reward function over the time window w when the wireless access network is in the current state.

Abstract: A method for managing allocation of radio resources to users in a cell of a communication network during an allocation episode is disclosed. The method comprises generating a representation of a scheduling state of the cell for the allocation episode and generating a radio resource allocation decision for the allocation episode by performing a series of steps sequentially for each radio resource or for each user in the representation. The steps comprise selecting a radio resource or a user and using a trained neural network to update a partial radio resource allocation decision for the allocation episode on the basis of a current version of the scheduling state representation and updating the scheduling state representation to include the updated partial radio resource allocation decision. The method further comprises initiating allocation of cell radio resources to users during the allocation episode in accordance with the generated radio resource allocation decision.

Abstract: A method performed by a first network node is provided. The method includes determining a power backoff indicator (PBI) for a first user equipment (UE) based on at least one of channel conditions of the first UE and channel conditions of a second UE, data reliability requirements of the second UE, and data performance of the first UE. The method includes transmitting the PBI toward the first UE. The method includes receiving second data from the first UE, wherein transmission of the second data has been adjusted based on the PBI. The UE receives the PBI. Responsive to determining to apply the PBI, the UE backs off the power by adjusting the power according to at least one of a configuration and the PBI. The UE transmits second data to the first network node with the backed off or adjusted power.

Abstract: A technique for controlling and selecting a coverage level (502, 504, 506) for a radio device connected or connectable to an access node over a radio medium is described. As to one method aspect of the technique, a state or usage of at least one of the radio medium and the access node is determined. Control information is transmitted to the radio device. The control information is indicative of at least one threshold value (512, 514) that depends on the determined state or usage for controlling the coverage level (502, 504, 506) selected by the radio device based on a comparison of power (510) of a downlink signal received over the radio medium from the access node with the at least one threshold value (512, 514).

Abstract: A method and a network node (700) serving a first cell in a wireless network, for reducing interference in a second cell caused by transmission of reference signals in the first cell. The network node (700) transmits (7:2) in the first cell a scheduling block where a number of said reference signals are located in predefined resource element positions in the scheduling block, using a time offset relative transmission of a scheduling block in the second cell. Thereby, the impact of interference from a reference signal from one network node will be distributed over several resource elements in the other network node so that the impact in each resource element is reduced, as compared to when all interference from the reference signal hits one single resource element when no time offset is used.

Abstract: A method and a first network node (800) serving a first cell (800A) in a wireless network, for enabling reduction of interference in a second cell (800B) caused by transmission of reference signals in the first cell (800A). The first network node (800) transmits (8:1) scheduling blocks with said reference signals, using a time offset relative transmission of scheduling blocks in the second cell. A timing advance value is determined (8:3) for a wireless device (802) and the wireless device (802) instructed (8:4) to apply said timing advance value for uplink transmissions. The timing advance value was determined such that uplink symbols transmitted from the wireless device (802) are aligned with uplink symbols received at a second network node (804) of the second cell (804A).

Abstract: Apparatus and methods for link adaptation for downlink transmissions in which the quality of the downlink radio channel is predicted with improved accuracy. For example, predicted channel gains are determined based on uplink transmissions on a per frequency sub-band basis and these predicated channel gains are then used in a link adaptation process for a downlink transmission.

Abstract: A method performed by a node in a wireless communication network of estimating parameters used for determining a signal-to-interference measure at a communication device served by a base station, and a node performing the method. The method comprises acquiring an estimate of channel condition between the communication device and the serving base station, and between the communication device and at least one base station of a neighbouring cell, estimating the signal-to-interference measure using the estimate of the respective channel condition, and acquired output power and Physical Resource Block (PRB) utilization of each of the base stations, and receiving an indication of quality of a channel via which the communication device is served by the base station. The method further comprises determining whether a change in the estimate of the signal-to-interference measure is required based on the indication of channel quality, and updating the estimate of the channel condition.

Abstract: A network node and a method performed thereby for supporting VoIP service of a wireless device are provided. The network node is operable in a wireless communication network, and the method comprises, when a channel quality of a channel between the wireless device and the network node falls below a predetermined threshold: determining (110) QoS requirements with regard to GBR for services which the wireless device is currently using; determining (120) an achievable bitrate using TTI bundling; and determining (150) to enable TTI bundling of the wireless device based on the determined aggregated GBR requirement and the determined achievable bitrate.

Abstract: In a method for downlink link adaptation in a network node in a communication system, the network node serving a cell and active user equipment within the cell, performing the steps of obtaining uplink path gain and downlink SINR for at least a subset of active user equipment in the cell, estimating an initial downlink SINR for new user equipment in the cell, based on an estimated uplink path gain together with a determined statistical measure for the obtained uplink path gain and downlink SINR for the at least a subset of active user equipment in the cell, and utilizing the estimated initial downlink SINR for downlink link adaptation for a subsequent transmission to the new user equipment.