Abstract: A first apparatus and a second apparatus (128) that are configured to manage or orchestrate network resources, or network services, or a machine learning model, or a composition of a machine learning model for a first stakeholder and a second stakeholder respectively, and first method comprising receiving, at the first apparatus (120), a requirement regarding a network intent, or for a network resource, or a network service, or a machine learning model, or a composition of a machine learning model, determining, at the first apparatus (120), a message regarding the requirement, sending the message to the second apparatus (128), and a second method comprising receiving, from the first apparatus (120) a first message regarding a requirement, and sending a second message regarding the requirement, to the first apparatus (120) or a first message regarding a network intent, and sending a second message regarding the network intent to the first apparatus (120).

Abstract: Methods and apparatuses for providing a geographic location of a sensor (104) for acquiring data, wherein a first method in a first apparatus (112) comprises to receive (204) a request for a geographic location of a sensor (104) for acquiring data from a first apparatus, to request (206) the geographic location from a second apparatus (102) that is configured to operate a core of a communication network (100), to receive (212) the geographic location from the second apparatus (102), and to send (214) the geographic location, wherein a second method comprises to receive (206) a request from the first apparatus (112) for a geographic location of a sensor (104) for acquiring data, to request (208) the geographic location from the sensor (104), to receive (210) the geographic location from the sensor (104), and to send (212) the geographic location to the first apparatus (112).

Abstract: It may be that data collected, and retrieved, for a model training is not sufficient, and hence additional data may be needed. When it is determined that additional data is needed to complement the data retrieved, synthetic data is generated, and training data is obtained by combining the synthetic data with the data retrieved, and the model training is performed. A ratio of the synthetic data to the training data is determined and the ratio is indicated in a response to a request that caused the model to be trained.

Abstract: Two competing machine learning based models, a first model for generating synthetic data, and a second model for classifying input data to synthetic data and real data, are trained by training the second model until its accuracy meets a preset rule, and then the first model is trained. After training the first model, training of models is repeated until an end criterium is met.

Abstract: In accordance with an example embodiment of the present disclosure Ethernet communication over IP transport is enabled. The following is performed: Ethernet communication for transmitting and receiving Ethernet frames; IP communication for transmitting and receiving IP data packets over a cellular network; transforming Ethernet frames to IP data packets and vice versa for enabling Ethernet communication over IP transport; and maintaining a header transformation table between Ethernet and IP traffic flows. The transforming comprises using the header transformation table and performing header transformation by removing Ethernet headers from received Ethernet frames and including Ethernet payload in IP data packets, and by reconstructing Ethernet headers for received IP data packets for transmission of payload from the IP data packets in Ethernet frames, wherein the transforming comprises using IPv6 headers of IP data packets to carry dynamic information from the removed Ethernet headers.

Abstract: According to an example aspect of the present disclosure, there is provided a method, comprising, receiving input data comprising data points, applying a conditional variational autoencoder to the received data points to generate features associated with the received data points, wherein said applying the conditional variational autoencoder comprises using a label corresponding to a type of network traffic as a conditional variable of the conditional variational autoencoder, applying a classifier to the features to classify the received data points into categories and performing at least one action based on the categories.

Abstract: According to an example aspect of the present invention, there is provided an apparatus, comprising means for performing, receiving input data comprising data points, applying N initial clustering algorithms at least to a subset of said data points to generate N initial clustering matrices, generating a co-association matrix from the N initial clustering matrices, generating a distance matrix from the co-association matrix, applying a density based clustering algorithm to the distance matrix to generate data clusters, determining a subset of the generated data clusters as anomalous clusters, wherein at least some of the data points in each anomalous cluster are anomalous data points and performing at least one action based on the anomalous clusters.

Abstract: In accordance with an example embodiment of the present disclosure Ethernet communication over IP transport is enabled. The following is performed: Ethernet communication for transmitting and receiving Ethernet frames; IP communication for transmitting and receiving IP data packets over a cellular network; transforming Ethernet frames to IP data packets and vice versa for enabling Ethernet communication over IP transport; and maintaining a header transformation table between Ethernet and IP traffic flows. The transforming comprises using the header transformation table and performing header transformation by removing Ethernet headers from received Ethernet frames and including Ethernet payload in IP data packets, and by reconstructing Ethernet headers for received IP data packets for transmission of payload from the IP data packets in Ethernet frames, wherein the transforming comprises using IPv6 headers of IP data packets to carry dynamic information from the removed Ethernet headers.

Abstract: A network apparatus of a communication system classifies traffic flows containing packets based on packet features. The network apparatus provides a copy of a packet contained in a traffic flow to a cluster node, and controls the cluster node to select at least one detector node based on the features of the packet and to forward said copy to the selected detector node to find out based on said copy whether the packet is malicious or not. In response to receiving from the detector node a flow indication on the traffic flow, the network apparatus controls a switch node to perform at least one flow control action on the traffic flow, the action including one or more of flow removal, flow modification and flow installation.

Abstract: Various communication systems may benefit from increased security. For example, communication systems that include machine type communications may benefit from improved security and fault detection. A method, in certain embodiments, may include receiving data at an internet of things module in a mobile network from a robot controller. The data includes sensor information from a plurality of machine type communication devices. The method may also include detecting an attack on the mobile network based on the sensor information. In addition, the method may include determining a preventive action to prevent the attack. Further, the method may include sending an indication of the attack to at least one of the robot controller, another robot controller, or another internet of things module. The indication includes the preventive action.

Abstract: A network apparatus of a communication system classifies traffic flows containing packets based on packet features. The network apparatus provides a copy of a packet contained in a traffic flow to a cluster node, and controls the cluster node to select at least one detector node based on the features of the packet and to forward said copy to the selected detector node to find out based on said copy whether the packet is malicious or not.