Abstract: According to embodiments herein e.g. a method performed by an orchestration agent unit for handling a service in a communications network is provided. The orchestration agent unit evaluate a number of intent types of the service based on a performance of one or more performance metrics related to intent of respective intent type when performed in the communications network including a plurality of orchestration agent units. The orchestration agent unit selects an intent type of the service based on the evaluation; and sends to at least one of the plurality of orchestration agent units, an indication indicating the selected intent type of the service.

Abstract: A computer-implemented model for dynamic congestion control for network slices is provided. The method includes obtaining a recommendation from a network node for a congestion control process for a plurality of interfaces of a network slice based on at least one condition related to the network slice. Application of the congestion control process addresses the at least one condition related to the network slice. The method further includes applying the congestion control process in a protocol stack for the plurality of interfaces of the network slice.

Abstract: A method, performed by a first node (111). The first node (111) operates in a communications network (10). The first node (111) determines (202) a predictive model of a future need to page a device (133) operating in the communications network (10). The first node (111) then outputs (204) a first indication. The first indication is based on the determined predictive model. A second node (112) operating in the communications network (10) obtains (301) the first indication, and predicts (302), based on the obtained first indication, the future need to page the device (133). A third node (113) obtains (402) a third indication from the second node (112). The third indication indicates the predicted future need to page the device (133) operating in the communications network (10). The third node (113) then determines (403), based on the obtained third indication, whether or not to page the device (133).

Abstract: Methods and apparatus for implementing reinforcement learning are provided. A method in a client node that instructs actions in an environment in accordance with a policy includes identifying one or more critical states of the environment for which a current policy provides unreliable actions. The method further includes initiating transmission to a server of a retraining request, the retraining request having information relating to the one or more critical states. The method further includes receiving a new policy from the server, wherein the new policy is generated by the server using reinforcement learning based on the information relating to the one or more critical states, and instructing actions in the environment in accordance with the new policy.

Abstract: A management node for use with a cognitive layer (CL) having agents. The agents have respective agent information indicating type(s) of input data required by a model implemented by the agent, parameter(s) of the system that are to be improved by the agent, type(s) of output data provided by the model and a data distribution for the agent. A method includes (i) selecting a set of similar agents that improve a first parameter of the system: (ii) for a first agent and a second agent in the selected set of similar agents, comparing the data distribution for the first agent to the data distribution for the second agent to determine a relationship: (iii) initiating generation of the candidate agent(s) based on the relationship; and (iv) determining whether to replace one or both of the first agent and the second agent with the one or more candidate agents.

Abstract: A computer-implemented method for acquiring new data samples and for maintaining a set of data samples in a database, wherein the set of data samples are configured to form input to a function associated with a predictive performance, the method including obtaining at least one relevance metric (M), where the relevance metric is indicative of an increase in the predictive performance of the function when using a data sample as input together with the set of data samples compared to when not using the data sample, obtaining a relevance criterion (C), where the relevance criterion identifies relevant data samples in a set of data samples based on the at least one relevance metric, signaling the at least one relevance metric (M) and the relevance criterion (C) to a data collecting network node.

Abstract: A functional model of a business process which is annotated with security requirements is provided. Platform-specific executable code and at least one configuration file for a given security enforcement component to enforce the security requirements of the model are then generated automatically.

Abstract: A functional model of a business process which is annotated with security requirements is provided. Platform-specific executable code and at least one configuration file for a given security enforcement component to enforce the security requirements of the model are then generated automatically.