Abstract: A method performed by a control node for a radio access network. The control node may select an energy source from a plurality of energy sources connected to a base station based on selecting an energy rate of one of the energy sources correlated in time with a radio traffic power usage of the base station. The selection may be made from a plurality of energy rates for the plurality of energy rates correlated in time for each energy source with a radio traffic power usage of the base station. The selected energy rate may improve at least one operating parameter of the selected energy source. The control node may activate the selected energy source for use by the base station. A further method performed by a global control node may be provided.

Abstract: In implementation of techniques for generating video from an image based on variable speed, a computing device implements a variable speed system to receive a static digital image displayed in a user interface, an indication of a movement direction, and an indication of a variable rate of speed. The variable speed system generates a digital video based on the static digital image, the digital video having pixels that move in the movement direction at a speed that varies based on the variable rate of speed based on pixels from the static digital image. The variable speed system then displays the digital video in the user interface.

Abstract: Techniques are described herein for a secure access to an online service based on a token exchange. In an example, a first user interface associated with a first user account is presented on a first user device and is used to indicate a set of restrictions associated with use of a function of the online service by the first user account. A security credential can be generated and associated with the set of restrictions. Upon receiving the security credential from a second user device from which a login to the first user account has not occurred, a determination can be made that the function is accessible to the second user device. This access can use the first user account subject to the restrictions. A token associated with the set of restrictions and the function can be sent to the second user device to enable the use of the function.

Abstract: A method performed by a control node for a radio access network. The control node may select an energy source from a plurality of energy sources connected to a base station based on selecting an energy rate of one of the energy sources correlated in time with a radio traffic power usage of the base station. The selection may be made from a plurality of energy rates for the plurality of energy rates correlated in time for each energy source with a radio traffic power usage of the base station. The selected energy rate may improve at least one operating parameter of the selected energy source. The control node may activate the selected energy source for use by the base station. A further method performed by a global control node may be provided.

Abstract: Methods, nodes, computer programs and communication networks are disclosed. The disclosure provides a method performed by a network node for controlling traffic in a communications network, the communications network comprising a wireless access node adapted to serve a plurality of wireless devices. The method comprises obtaining network operation data for at least one of the plurality of wireless devices, the network operation data comprising location of the respective wireless device and performance data correlated with the location, the network operation data being indicative of a plurality of attributes corresponding to the operation of the respective wireless device in the communications network. The method also comprises grouping the at least one wireless device of the plurality of wireless devices by partitioning the network operation data into one or more service clusters wherein each service cluster defines a geographical area based on the obtained location.

Abstract: A method of performing federated feature selection for a machine learning model in a federated learning environment includes obtaining, at a first resolution, a global set of selector neural network weights. At a second resolution, the method selects, for a plurality of first data subsets, a first set of features from a feature space by iteratively applying a first selector neural network that is initialized with the global set of selector neural network weights to the first data subset to obtain a first set of selector neural network weights. The first data subsets are divided into a plurality of second data subsets, and, at a third resolution, a second set of features is selected from the feature space.