Abstract: A method and agent for reinforcement learning. The method may include evaluating a consequence of a previous action. Evaluating the consequence may include performing a comparison of one or more current monitored parameters (e.g., immediate reward, accumulated reward, average reward, and/or current key performance parameters) to one or more previous monitored parameters. The method may include, based on the evaluated consequence of the previous action, determining a subset of potential next actions. For a positive consequence, the determined subset of potential next actions may include only potential next actions that are likely to have the consequence as the previous action (e.g., based on a dot product of or angle between vectors of the previous action and the potential next action). The method may include selecting an action from the determined subset of potential next actions. The method may include performing the selected action.

Abstract: A method (400) for dynamic RL. The method includes using an RL algorithm to select a first action and triggering performance of the selected first action. The method also includes after the first action is performed, obtaining a first reward value (R1) associated with the first action. The method also includes using R1 and/or a performance indicator (P1) to determine whether an algorithm modification condition is satisfied. The method further includes, as a result of determining that the algorithm modification condition is satisfied, modifying the RL algorithm to produce a modified RL algorithm. In this way, the RL algorithm adapts to changes in the environment.

Abstract: There is provided mechanisms for enabling time synchronized and coordinated downlink transmission of data from a radio unit. A method is performed by a network node. The method comprises configuring at least two baseband units. The at least two baseband units are operatively connected to the radio unit for downlink transmission of data. The at least two baseband units are configured with time synchronization information for compensating for a difference in time delay between each of the at least two baseband units and the radio unit for the downlink transmission of data. The at least two baseband units are configured with time scheduling information identifying which transmission slots per frame that are allowed to be used by the at least two baseband units for the downlink transmission of data.

Abstract: A first aspect provides in a supply voltage control module, a method of providing instructions for setting a supply voltage comprising obtaining information on a supply voltage need of a load and based on that information, determining a supply voltage that is to be provided to the load. Subsequently, an instruction is sent to a power supply module to supply the determined supply voltage to the load. A need for a supply voltage of a load, like an integrated circuit, may not only depend on design of the load, but also on parameters of the manufacturing process and the level of activity of the load. By obtaining information on a supply voltage need of the load and using that information to determine a supply voltage to be provided to the load, a feedback loop is created by instructing a point of load power supply to provide the supply voltage determined.

Abstract: A first aspect provides in a supply voltage control module, a method of providing instructions for setting a supply voltage comprising obtaining information on a supply voltage need of a load and based on that information, determining a supply voltage that is to be provided to the load. Subsequently, an instruction is sent to a power supply module to supply the determined supply voltage to the load. A need for a supply voltage of a load, like an integrated circuit, may not only depend on design of the load, but also on parameters of the manufacturing process and the level of activity of the load. By obtaining information on a supply voltage need of the load and using that information to determine a supply voltage to be provided to the load, a feedback loop is created by instructing a point of load power supply to provide the supply voltage determined.

Abstract: The present invention relates to a power converter system (1) comprising at least a first power converter (2) and a second power converter (3), where each power converter (2, 3) comprises a corresponding power converter input (4, 7), a corresponding power converter output (5, 8) and a corresponding power converter control connection (6, 9). The first power converter output (5) is connected to the second power converter input (7). Each power converter (2, 3) is arranged to output a certain predetermined voltage (U1, U2), where furthermore at least one power converter (2, 3) is arranged to generate a corresponding system signal (204) which is output from the corresponding power converter output (5, 8) together with the corresponding predetermined voltage (U1, U2). The system signal (204) comprises identification information (201) that enables determination of which power converter that has generated said system signal (204) when said system signal (204) is detected in the system (1).

Abstract: A system and method is disclosed for measuring mass of hydrocarbons from point source contributions to overall hydrocarbon emissions from an automotive vehicle at rest.