Abstract: Methods, apparatuses and systems performed and configured to operate in a wireless communication network are presented. In example implementations, the methods, apparatuses and systems are configured for use in a conditional handover for a user equipment in the wireless communication network. Based on a known first location of the user equipment in a first cell of the wireless communication network at a first point in time, a second location of the user equipment at a second point in time is predicted. The prediction is based on applying a movement prediction to the user equipment relative to the known first location at the first point in time. A probability for the second location to be located in at least one of the first cell and any one of one or more second cells in the wireless convocation network is thereby obtained. The one or more second cells are different from the first cell.

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: 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: 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: There is provided a method for estimating play out resolution of a video delivered to a client device by an encrypted video stream communicated over a network. The method selects a current chunk of the encrypted video stream comprising data packets expected to carry video data of the same level of playout resolution and determines values for a predetermined set of features indicative of conditions in the network. By accessing a pregenerated model, a corresponding set of state transition probabilities is obtained, defining a Markov chain whose states comprise the different levels of resolution. The determined state transition probabilities are then used to calculate, from a first probability distribution arising from a first or previous step in the Markov chain, a second probability distribution for the plurality of states of the Markov chain expected to result from the indicated network conditions.

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: 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.

Abstract: The invention is a data management method for an anonymous data sharing system, comprising the steps of receiving a data supply from a data source (10), the data supply comprising an anonymous data source identifier, an entity identifier encrypted with the private encryption key of the data source (10), and data associated with the entity. The method further comprises mapping the encrypted entity identifier to a common anonymous entity identifier by applying a classifier key associated with the data source identifier in such a manner that for every entity identifier the following applies: by encrypting said entity identifier with the private encryption key of any data source (10) and by mapping it using the classifier key associated with the identifier of the data source, the same common anonymous entity identifier is obtained, wherein the data associated with the entity are stored in a database (12) in a manner that said data are assigned to the common anonymous identifier.

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: 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: A management node (100) obtains indications of network events occurring at a plurality of nodes (210-1, 210-2, 210-3, 210-4, 220-1, 220-2 , 230-1, 230-2) of the communication network. Further, the management node (100) performs a correlation of times of the indicated network events. On the basis of the correlation, the management node (100) identifies clusters of nodes (210-1, 210-2 , 210-3, 210-4, 220-1, 220-2, 230-1, 230-2) with correlated network events. On the basis of the clusters, the management node (100) determines a topology model of the communication network.

Abstract: The invention is a data management method for an anonymous data sharing system, comprising the steps of receiving a data supply from a data source (10), the data supply comprising an anonymous data source identifier, an entity identifier encrypted with the private encryption key of the data source (10), and data associated with the entity. The method further comprises mapping the encrypted entity identifier to a common anonymous entity identifier by applying a classifier key associated with the data source identifier in such a manner that for every entity identifier the following applies: by encrypting said entity identifier with the private encryption key of any data source (10) and by mapping it using the classifier key associated with the identifier of the data source, the same common anonymous entity identifier is obtained, wherein the data associated with the entity are stored in a database (12) in a manner that said data are assigned to the common anonymous identifier.

Abstract: A management node (100) obtains indications of network events occurring at a plurality of nodes (210-1, 210-2, 210-3, 210-4, 220-1, 220-2 , 230-1, 230-2) of the communication network. Further, the management node (100) performs a correlation of times of the indicated network events. On the basis of the correlation, the management node (100) identifies clusters of nodes (210-1, 210-2 , 210-3, 210-4, 220-1, 220-2, 230-1, 230-2) with correlated network events. On the basis of the clusters, the management node (100) determines a topology model of the communication network.

Abstract: The present disclosure relates to a technique for configuring and collecting network performance measurements in a mobile communications network, the mobile communications network comprising at least one network node and at least one mobile terminal 208 connected to the at least one network node, implementing a Minimization of Drive Tests (MDT) trace measurement configuration and collection.

Abstract: A technique for creating a knowledge base for alarm management in a communications network is disclosed. In a method aspect, the method comprises the steps of defining a set of alarm properties observable for at least one managed element of the communications network; grouping incoming alarms into at least one alarm group based on heuristics; correlating the set of alarm properties with the at least one alarm group to thus generate at least one correlated alarm record; and constructing the knowledge base on the basis of the at least one correlated alarm record.

Abstract: A network management system (100) and a method are described herein that are capable of identifying and accessing Quality of Service (QoS) issues within a communications network (104, 106). In one application, the network management system (100) includes a service performance unit (108), a service performance database (110), a factor scoring system (112), a factor score database (114) and a factor strength analysis module (116).

Abstract: A method and apparatus for controlling data traffic in a communications network. The server determines that network conditions are suitable for sending delay tolerant data traffic, and as a result of the determination, it transmits a grant message to at least one client device, the grant message informing the client device that it is permitted to send or receive delay tolerant data traffic.

Abstract: A method of determining one or more Key Performance Indicators, KPIs, indicative of the performance of a communications network and calculated as an aggregation of performance measurement values in the communications network. The method comprises receiving a set of performance measurement samples each of which comprises a performance measurement value and an identity of an associated source, and performing a statistical analysis of the set of performance measurement samples in order to identify any source that contributes performance measurement samples that would result in a distorting effect on a KPI. This allows performance measurement samples associated with the identified sources to be separated from other samples to obtain an undistorted performance measurement sample set. The undistorted performance measurement sample set is used as a basis for calculating the one or each KPI.

Abstract: The present disclosure relates to a technique for configuring and collecting network performance measurements in a mobile communications network, the mobile communications network comprising at least one network node and at least one mobile terminal 208 connected to the at least one network node, implementing a Minimization of Drive Tests (MDT) trace measurement configuration and collection.

Abstract: A subscriber portfolio model is created by forming mutually exclusive and completely exhaustive groups of subscribers in a way that maximizes the intra-group similarity and inter-group dissimilarity of the value of a target attribute among subscribers in the groups. The subscriber groups thus generated are self-descriptive, as the groups are defined by the attributes used to form them. A segmenting algorithm groups subscribers along permutations of attributes. Relevant data about subscribers is collected from various sources, correlated, and subscriber identities removed to ensure privacy. After analyzing the aggregated data, a subscriber portfolio model is built. The subscriber portfolio model is created in an iterative process; in each step, a selected subscriber group is subdivided into smaller subscriber groups along different value ranges of a statistically decisive attribute that is selected and evaluated based on specific methods.