Abstract: Selecting a transport configuration for a data network adapted to transport data traffic belonging to different traffic types. A selecting device determines an actual traffic mix of traffic types and corresponding traffic loads transported on the data network. The device determines, based on the actual traffic mix, multiple future traffic mixes of traffic types and corresponding traffic loads, wherein the future traffic mixes are associated with probability values and classifiable into different future traffic mix classes, each future traffic mix class being associated with a predefined transport configuration capable of handling any future traffic mix falling in that future traffic mix class. The device is configured to aggregate the probability values associated with those future traffic mixes that belong to the same future traffic mix class and to select the transport configuration associated with the highest probability value across the aggregated and non-aggregated probability values.

Abstract: Wireless network cells are classified into groups based on radio and network conditions in the cells. Quality of Service, QoS, policy optimization is then performed per each classified cell group, by selecting more or less stringent predetermined rules until a target Quality of Experience, QoE, is met, at least for the highest priority traffic. To classify the cells into groups, the radio and network parameters collected (110) are ranked (112) by their influence on QoE. Based on this ranking, only a few of the most impactful parameter are selected (114). The range of values of each parameter is then divided (116) into a plurality of ranges, for example by the ability of the parameter, when within each range, to impact service quality. Cells are then classified (118) into groups based on the same parameters within the cells falling into the same value ranges. QoE targets for at least high priority traffic classes are obtained (120).

Abstract: User-specific network analytics for application data services provided to user equipment (UEs) in a wireless network is disclosed herein. User interaction for an application data service and captured by an overlay on the UE triggers network analytics. The wireless network filters or otherwise controls the network analytics performed by the network node responsive to the trigger. In so doing, the user-specific network analytics disclosed herein decreases the network functions and analytics load at the network, and enables the network to focus on specific events, which enables the network to establish and support specific application goals.

Abstract: A technique for performing Quality of Service, QoS, control regarding control messages communicated from a robot controller to a robot via a mobile communication network in a cloud robotics system is disclosed. A method implementation of the technique comprises triggering applying a mapping of control messages communicated from the robot controller to the robot to QoS classes among a plurality of data session related QoS classes supported by the mobile communication network for transmission of traffic via the mobile communication network, wherein each of the control messages is mapped to a respective QoS class depending on a Quality of Control, QoC, tolerance associated with the respective control message.

Abstract: Techniques for real-time encrypted over-the-top (OTT) data quality analysis are presented. For instance, the present disclosure includes an example method performed by a device in a recurrent neural network (RNN) implemented in a data communication system. The method includes periodically obtaining information corresponding to one or more OTT data sessions in the data communication system, the information being obtained from one or more of a packet probe, a test terminal, and a network node. The method also includes generating at least one quality metric associated with the one or more OTT data sessions based on the periodically obtained information. Related devices, processor and memory arrangements, methods, and computer programs are also presented.

Abstract: According to the present disclosure, a technique for controlling reporting of network events by one or more network functions, NF, of a wireless communication network is provided. A method implementation of this technique comprises receiving, from at least one network analytics component, a network analytics request indicative of at least one event reporting requirement of the at least one network analytics component, and receiving, from at least one IMF, one or multiple NF reports indicative of at least one of an event reporting capability, a load and a capacity of the at least one NF. The method further comprises generating an event reporting request based on the at least one event reporting requirement and at least one of the event reporting capability, the load, and the capacity of the at least one NF, and sending the event reporting request to the at least one NF so as to control event reporting by that at least one NF.

Abstract: For each of a plurality of wireless devices, signal strength measurements performed by the wireless device are collected. The signal strength measurements are collected with respect to a plurality of cells of the wireless communication network. Further, based on the signal strength measurements, a plurality of zones of the wireless communication network is determined. Each zone indicates a position of the wireless device with respect to the cells when performing a respective one of the signal strength measurements. Further, for each of the wireless devices, a respective trajectory is determined from a sequence of the zones passed by the wireless device. Further, performance data related to the wireless devices are collected, and the performance data are filtered based on the trajectories.

Abstract: Traffic forwarding policy determination in a wireless communication system A node (310) of the wireless communication network receives first data indicative of estimated QoE levels of data traffic in the wireless communication network. The data traffic is subject to QoS rules enforced by one or more nodes of the wireless communication network. Further, the node (310) receives second data indicative of QoS statistics observed in association with the QoE levels. Based on the first data and the second data, the node (310) determines a traffic forwarding policy for the data traffic. The traffic forwarding policy defines QoS rules which, according to the observed QoS statistics, are expected to ensure that a QoE target is met.

Abstract: The dynamically generation and evaluation of User Activity Records (UARs) is presented herein to determine which UARs to forward for analytics processing, and how much information to include with the forwarded UARs. To that end, UARs are identified as normal, e.g., those UARs satisfy an evaluation condition, e.g., a threshold condition, and or as abnormal, e.g., those UARs that do not satisfy an evaluation condition, e.g., the threshold condition. For those UARS identified as normal, only a small subset of the normal UARs are forwarded for further analysis to reduce the data volume associated with these normal UARs. For those UARs identified as abnormal, enrichment data is appended to the generated UAR to generate a detailed UAR, all which is forwarded for further analysis.

Abstract: A node of the wireless communication network receives data indicative of a measured QoS, level of data traffic assigned to different configured traffic forwarding policies each defining one or more target parameters. Based on the data and the target parameters, the node detects violations of the traffic forwarding policies. Based on the detected violations for each the traffic forwarding policies, the node detects at least one anomaly in the wireless communication network.

Abstract: A technique for performing segment-wise analysis of a Real-Time Transport Protocol, RTP, flow carried from a first User Equipment, UE, to a second UE via a mobile network is disclosed. The RTP flow is monitored by a plurality of probes in the mobile network, wherein each of the plurality of probes is configured to calculate at least one performance indicator indicative of a performance associated with the RTP flow observed between the first UE and the respective probe. A method implementation of the technique includes deriving at least one segment performance indicator for a segment of the RTP flow between a first probe of the plurality of probes and an endpoint of the segment by deducting the at least one performance indicator calculated by the first probe from at least one corresponding performance indicator associated with the endpoint.

Abstract: A method for determining the quality of a media stream transmitted via a communication network, including at least the quality of the media stream as it is transmitted via a radio access network to a receiving device, based on data which is obtained prior to that transmission via the radio access network. The method utilizes a predictive model which is developed using a machine-learning algorithm.

Abstract: According to an aspect, there is provided a method for monitoring a communication network, the method comprising: monitoring (701) user plane information and control plane information for a first session provided by the communication network for a first wireless device; and correlating (703) the user plane information and the control plane information to determine if the first session was ended due to a soft drop, wherein a soft drop corresponds to a user of the wireless device intentionally terminating the first session due to service quality issues.

Abstract: A technique of triggering transition control between different RRC states of wireless terminal devices is described. A method aspect of this technique comprises receiving a request for an RRC state transition control for a terminal device, wherein the request includes at least one identifier associated with the terminal device. The method further comprises obtaining a temporal inactivity parameter associated with the at least one identifier, wherein the temporal inactivity parameter depends on an estimated period of time between two traffic activities of the terminal device. Further still, the method comprises triggering, based on the temporal inactivity parameter or a parameter derived on the basis of the temporal inactivity parameter, the RRC state transition control for the terminal device.

Abstract: The present disclosure relates to a first Web server (102, 204, 60, 70) and a second Web server (108, 214, 80, 90), and methods therein for controlling of a robot device over a cloud interface. A hyper-text transfer protocol, HTTP, request for a trajectory between a start position and a goal position is sent (S120, S230, 302, 402) towards the second Web server. One or more calculated trajectories are obtained (S122, 304) based on information as received encoded in the request. A HTTP response is sent (306) towards the first WEB server, comprising one or more calculated trajectories. Executing (S126, S266; 308, 406) of a trajectory at least based said one or more of the received trajectories is performed by the first Web server (102, 204, 60, 70). A scalable robot device control method is thus proposed, which is advantageously uses stored calculated trajectories between start and goal positions, for the robot device.

Abstract: A technique for analyzing Quality of Experience, QoE, of a delay critical robotic application in a cloud robotics system is disclosed, the robotic application involving use of a cloud based service by a robot, the service being provided to the robot from a cloud using a connection over a mobile communication network. A method implementation of the technique comprises triggering (S202) determining whether a QoE measure associated with the robotic application exceeds a threshold to assess whether QoE degradation is present, and, when it is determined that QoE degradation is present, triggering (S204) identifying a root cause for the QoE degradation based on one or more performance indicators observed within the mobile communication network and associated with the connection.

Abstract: A technique for acquiring and correlating session-related information from an Internet Protocol Multimedia Subsystem, IMS, is described. The technique comprises the acquisition of control plane information from control plane signalling tapped at an IMS control entity, the acquisition of user plane information from user plane traffic tapped at an IMS user plane entity, and the acquisition of context information from tapped signalling between the IMS control entity and the IMS user plane entity. The acquired context information permits to correlate the control plane information and the user plane information acquired for a particular session.

Abstract: A method for determining the quality of a media stream transmitted via a communication network, including at least the quality of the media stream as it is transmitted via a radio access network to a receiving device, based on data which is obtained prior to that transmission via the radio access network. The method utilizes a predictive model which is developed using a machine-learning algorithm.

Abstract: An apparatus for parameter transformation between a robotic device and a controller for the robotic device is presented. The apparatus is configured to receive at least one non-transformed parameter indicative of at least one of a position and a velocity of or for the robotic device, wherein the non-transformed parameter is received from the robotic device or the controller, respectively. The apparatus is further configured to transform the received non-transformed parameter to a transformed parameter using a transformation between an ideal parameter domain of the controller and a real parameter domain of the robotic device, the ideal parameter domain including ideal parameters processable by the controller and the real parameter domain including real parameters measurable at the robotic device and capable of deviating from the associated ideal parameters.

Abstract: An aspect of the present disclosure is directed to a method for initiating a voice call in a mobile communication network. The method comprises detecting that a user device performs a call attempt of initiating a voice call over the mobile communication network while being wirelessly connected to a WiFi access point, determining at least one call attempt parameter indicative of a situation and/determining or environment in which the call attempt is performed, and deciding, based on a decision criterion, whether the voice call to be initiated shall be forced to be used for training a prediction model.