Abstract: A method of estimating, for an antenna of a base station, variations in received signal strength at User Equipments, UEs, the method comprising: transmitting, to a plurality of UEs, a reference signal; receiving, as input data: signal strength measurements indicating received reference signal strength of the reference signal from the UEs, and positional information from the UEs; generating model coefficients by processing the input data in a training model; and estimating variations in received signal strength of the received reference signal received at the UEs, the estimated variations corresponding to an electrical tilt change of the antenna, wherein the variations in received signal strength are estimated by: processing, in a prediction model, the generated model coefficients, a Remote Electrical Tilt, RET, increment which defines the electrical tilt change, and the positional information received from the UEs.

Abstract: A computer-implemented method for optimization of downlink (DL) transmit powers in a wireless communication network includes acquiring deployment data describing a deployment of a cluster of cells of the wireless communication network. Further, the method includes acquiring measurement data representing measurements performed with respect to a plurality of connections established between wireless devices and the wireless communication network. Further, the method includes, based on the deployment data and the measurement data, emulating effects of applying different DL transmit powers in at least some cells on the plurality of connections. Further, the method includes estimating state information for each of the cells based on the emulated effects. Further, the method includes, based on the estimated state information, training a machine learning (ML) model for optimization of the DL transmit powers of the cells.

Abstract: A method (50) and apparatus (60) for quantifying similarities between first and second cells (12a, 12b) in a mobile communications network (10) is provided. In particular, for each of the first cell and the second cell, a network node (60) receives input parameters, and based on those parameters, determines (54) respective sets of features for the cell. Each respective set of features defines a cell configuration and a coverage area morphology for the cell. So determined, a level of similarity between the first and second cells can be determined (56) based on their respective sets of features.

Abstract: A method and apparatus extend existing cell parameter optimization techniques so that they can be used in cases where different cells are controlled by the same control element. Particularly, a coordination agent (46) receives an intermediate control decision for controlling a control element (48) shared by the plurality of cells (14). The coordination agent consolidates each of the received intermediate decisions into a single consolidated control decision, and sends the consolidated control decision to the shared control element. The control element then controls a network element (26) in each of the cells using the same consolidated control decision.

Abstract: Methods and devices for signal strength prediction. In one aspect, a machine learning model is trained using physical cell information and geographic information to derive features corresponding to a region of a cell with a known signal strength value. The machine learning model can be used to predict signal strength values for other regions of the cell.

Abstract: Deviations of signal strengths in a first frequency band from signal strengths in at least one second frequency band are predicted based on a trained machine-learning model (350?). At least one source signal strength map is obtained. The at least one source signal strength map describes signal strengths in the at least one second frequency band for a coverage area of the wireless communication network. Based on the at least one source signal strength map and the predicted deviations of signal strengths, at least one target signal strength map describing signal propagation in the first frequency band for the coverage area is determined.

Abstract: According to an aspect, there is provided a computer-implemented method of training a policy for use by a reinforcement learning, RL, agent (406) in a communication network, wherein the RL agent (406) is for optimising one or more cell parameters in a respective cell (404) of the communication network according to the policy, the method comprising: (i) deploying (1001) a respective RL agent (408) for each of a plurality of cells (404) in the communication network, the plurality of cells (404) including cells that are neighbouring each other, each respective RL agent (408) having a first iteration of the policy; (ii) operating (1003) each deployed RL agent (408) according to the first iteration of the policy to adjust or maintain one or more cell parameters in the respective cell (404); (iii) receiving (1005) measurements relating to the operation of each of the plurality of cells (404); and (iv) determining (1007) a second iteration of the policy based on the received measurements relating to the operation of

Abstract: A method and a network node (110) for providing an RF model of a telecommunications system (100) are disclosed, The network node (110) configures (A030) reporting of call traces indicative of: a first type of measurement event relating to serving cell with a first time-to-trigger value and a first threshold value, and a second type of measurement event relating to neighbouring cells with respect to the serving cell with a second time-to-trigger value and a second threshold value, wherein the first time-to-trigger value is greater than the second time-to-trigger value. The network node (110) receives (A090) a respective call trace representing a firstly reported measurement event of the first or second type for a connection in said each cell. Moreover, the network node (110) processes (A100) the respective call trace to extract an Reference Signal Received Power “RSRP” or to extract a Carrier-To-Interferer ratio “C/I”.

Abstract: A method for detecting swapped antenna sectors in a cellular communications network. For each of one or more cells in the cellular communications network, an azimuth is estimated for each of two or more antenna sectors in the cell using a plurality of geo-located signal measurements for each antenna sector and a machine-learning algorithm. The estimated azimuths are compared to azimuths associated with the corresponding antenna sectors in a stored representation of the cellular communications network, to detect swapped antenna sectors in the cell.

Abstract: A method of monitoring a UMTS network is provided. The method comprises getting a recorded Radio Resource Control, RRC, message associated with a user and getting recorded data indicative of cell radio resource usage in the UMTS network. Further, the method comprises correlating the RRC message with the data indicative of cell radio resource usage. Further, the method comprises determining a measurement quantity indicated in the RRC message and, based on the measurement quantity indicated in the RRC message and the correlated data indicative of cell radio resource usage, calculating quality of a HSDPA radio channel for the user.

Abstract: A network node and a method performed by the network node for congestion control in a Radio Base Station, RBS, are provided. The method comprises determining that the RBS is congested. The method further comprises determining an interference level in a neighboring RBS caused by wireless devices currently being served by the RBS, or determining a level of inter-cell coupling between the RBS and the neighboring RBS. Still further, method comprises increasing a value of an average received signal level target, P0, for wireless devices currently being served by the RBS if the RBS is congested, if the determined interference level in the neighboring RBS is below an interference threshold or if the level of inter-cell coupling is below a coupling threshold.

Abstract: Known HO performance indicators comprise Retainability Rate and HO Successful Rate. The Retainability Rate is defined as the ratio between abnormal connection releases and the total number of releases, and HO Successful Rate is defined as the ratio of successful HOs and the total number of HO attempts. The application proposes two new HO performance indicators LowCqiRateWhenHo (522) and LowUISinrRateWhenHo (524). These two HO performance indicators are based on radio link conditions before a HO for the DL and UL channels respectively. The indicator LowCqiRateWhenHo is defined as the ratio of low, i.e. below a threshold (514). CQI measurement samples of users (502) just before a HO and is as a measure of DL connection quality during HO. The indicator LowUISinrRateWhen Ho is defined as the ratio of low, i.e. below a threshold (516). SINR measurement samples (506) in UL just before a HO and is as a measure of UL connection quality during HO.

Abstract: An offset is monitored which is applied by at least one access node (100) of a cellular network to adapt a signal quality value determined for a radio connection to a communication device (10). The adapted signal quality value is applied in a first control loop to select, a modulation and coding scheme for the radio connection. The offset is adapted in a second control loop, starting from an initial value and depending on feedback information concerning transmissions on the radio connection. Depending on the monitored offset, the initial value of the offset to be applied by the at least one access node (100) with respect to further radio connections to communication devices is determined.

Abstract: Known HO performance indicators comprise Retainability Rate and HO Successful Rate. The Retainability Rate is defined as the ratio between abnormal connection releases and the total number of releases, and HO Successful Rate is defined as the ratio of successful HOs and the total number of HO attempts. The application proposes two new HO performance indicators LowCqiRateWhenHo (522) and LowUISinrRateWhenHo (524). These two HO performance indicators are based on radio link conditions before a HO for the DL and UL channels respectively. The indicator LowCqiRateWhenHo is defined as the ratio of low, i.e. below a threshold (514). CQI measurement samples of users (502) just before a HO and is as a measure of DL connection quality during HO. The indicator LowUISinrRateWhen Ho is defined as the ratio of low, i.e. below a threshold (516). SINR measurement samples (506) in UL just before a HO and is as a measure of UL connection quality during HO.

Abstract: A network node and a method performed by the network node for congestion control in a Radio Base Station, RBS, are provided. The method comprises determining that the RBS is congested. The method further comprises determining an interference level in a neighbouring RBS caused by wireless devices currently being served by the RBS, or determining a level of inter-cell coupling between the RBS and the neighbouring RBS. Still further, method comprises increasing a value of an average received signal level target, P0, for wireless devices currently being served by the RBS if the RBS is congested, if the determined interference level in the neighbouring RBS is below an interference threshold or if the level of inter-cell coupling is below a coupling threshold.