Abstract: One component of time domain protection in a power system is estimating the location of a fault. In an embodiment, a multi-objective problem is formulated that comprises a non-smoothness penalization function that drives the primary objective function for fault location estimation towards a solution that respects smoothness between the inputs and outputs of a machine-learning model. This technique improves the accuracy, blind zone, and speed of state-of-the-art techniques, in the context of time domain protection, as well as for other regression tasks. In an additional or alternative embodiment that is specific to time domain protection, the multi-objective problem may comprise a phasor-deviation penalization function that drives the primary objective function towards a solution that minimizes deviations in phasor values. The trained machine-learning model may be executed in a line protection system to determine whether or not to trip a circuit breaker of a power line.

Abstract: To generate a decision logic for a controller of an Industrial Automation Control System, IACS, an iterative process is performed in which a decision logic candidate for the decision logic is generated, and a performance of the decision logic candidate in response to scenarios is computed.

Abstract: To determine a three-dimensional layout of electrical connections of an electric component, a processor executes a path optimization routine to determine three-dimensional routes for a plurality of electrical connections of the electric component. A conflict management is performed to generate conflict-free three-dimensional routes for the plurality of electrical connections.

Abstract: An asset protection, monitoring, or control device is operative to execute a decision-making logic to process inputs and generate a decision-making logic output that comprises one or more time series, process the decision-making logic output using a machine learning model, and cause an action to be performed responsive to a machine learning model output.

Abstract: A battery management system for a rechargeable battery is disclosed which includes a control system configured to control, a numerical battery model, including a parametrized electric model; a parametrized thermal model; an aging model configured to provide stress parameters indicative of an instantaneous consumption of an expected lifetime of the battery in dependence on an internal temperature of the battery, and one or more of momentary state of charge, current, voltage and power delivered; updated electric parameters and/or updated thermal parameters based on a chronological sequence of internal temperature as obtained from the parametrized thermal model; a control system settings update unit configured to adapt controller settings based on stress parameters.

Abstract: A method can be used to perform a state of health (SoH) estimation for a rechargeable battery energy storage system during operation of the rechargeable battery energy storage system. The rechargeable battery energy storage system includes a plurality of parallel strings that are individually controllable. The method includes selecting at least one string from the plurality of parallel strings, placing the selected at least one string into a SoH calibration mode for performing a SoH calibration while concurrently maintaining at least one other string of the plurality of parallel strings in operative mode, and causing the selected at least one string to return to the operative mode after the SoH calibration has been completed for the selected at least one string.

Abstract: Machine learning, ML, using labeled data is performed to thereby train a ML model to generate decision logic for a controller of an IACS, in particular a power system controller. The ML model has ML model inputs and ML model outputs. The ML model is decomposed into a plurality of computational sub-processes, wherein intermediate signals output by one of the computational sub-processes are input into a consecutive one of the computational sub-processes. Information on the trained ML model is generated based on the intermediate signals and is output for interpretation, verification, visualization, and/or inspection of at least one of the computational sub-processes.

Abstract: To determine a three-dimensional layout of electrical connections of an electric component, a processor executes a path optimization routine to determine three-dimensional routes for a plurality of electrical connections of the electric component. A conflict management is performed to generate conflict-free three-dimensional routes for the plurality of electrical connections.

Abstract: Techniques for determining a configuration for deployment of a public transportation system including a plurality of electric public transportation vehicles, in particular electric buses, are disclosed. At least one processor may determine, prior to deployment of the public transportation system and based on received information on timetables and geographical route profiles, a fleet size of a fleet of electric public transportation vehicles, on-board battery parameters of on-board batteries to be installed in electric public transportation vehicles, and charging infrastructure parameters associated with a charging infrastructure to be installed for charging the on-board batteries of the electric public transportation vehicles.

Abstract: A method can be used to perform a state of health (SoH) estimation for a rechargeable battery energy storage system during operation of the rechargeable battery energy storage system. The rechargeable battery energy storage system includes a plurality of parallel strings that are individually controllable. The method includes selecting at least one string from the plurality of parallel strings, placing the selected at least one string into a SoH calibration mode for performing a SoH calibration while concurrently maintaining at least one other string of the plurality of parallel strings in operative mode, and causing the selected at least one string to return to the operative mode after the SoH calibration has been completed for the selected at least one string.

Abstract: A battery management system for a rechargeable battery is disclosed which includes a control system configured to control, a numerical battery model, including a parametrized electric model; a parametrized thermal model; an aging model configured to provide stress parameters indicative of an instantaneous consumption of an expected lifetime of the battery in dependence on an internal temperature of the battery, and one or more of momentary state of charge, current, voltage and power delivered; updated electric parameters and/or updated thermal parameters based on a chronological sequence of internal temperature as obtained from the parametrized thermal model; a control system settings update unit configured to adapt controller settings based on stress parameters.

Abstract: The present invention relates to a method of operating a wind farm comprising an upstream and a downstream turbine, wherein the upstream turbine is operated with current operation parameters under current wind conditions, wherein the method comprises the steps of: receiving future wind conditions for a time period for the wind farm, and evaluating required operation parameters for minimising wake effect of the downstream turbine under the future wind conditions, and determining a cost coefficient for changing the operation parameters to required operation parameters under consideration of fatigue effect of the wind turbine, calculating power productions P0 and Pc, in the predetermined time period, by the wind farm if operated with the current operation parameters under the current wind conditions and if operated with the required operation parameters under the future wind conditions, respectively, and operating the upstream turbine with the required operation parameters if the cost coefficient is lower than a

Abstract: The present invention is concerned with an operation of a wind farm with a plurality of wind turbines in view of a dynamic frequency response. According to the invention, dynamic frequency support and power production for all wind turbines in a wind farm are handled concurrently in a single optimization step and taking into account wake effects within the wind farm as well as optional wind forecast information. The dynamic frequency support capability of the entire wind farm is planned in advance according to grid requirements and power system condition changes. While existing methods de-load wind turbines with a static percentage in order to supply additional power when needed, the proposed method incorporates the dynamic frequency support into the optimal operation system of wind farm.

Abstract: Techniques for determining a configuration for deployment of a public transportation system including a plurality of electric public transportation vehicles, in particular electric buses, are disclosed. At least one processor may determine, prior to deployment of the public transportation system and based on received information on timetables and geographical route profiles, a fleet size of a fleet of electric public transportation vehicles, on-board battery parameters of on-board batteries to be installed in electric public transportation vehicles, and charging infrastructure parameters associated with a charging infrastructure to be installed for charging the on-board batteries of the electric public transportation vehicles.

Abstract: The present invention is concerned with an operation of a wind farm with a plurality of wind turbines in view of a dynamic frequency response. According to the invention, dynamic frequency support and power production for all wind turbines in a wind farm are handled concurrently in a single optimization step and taking into account wake effects within the wind farm as well as optional wind forecast information. The dynamic frequency support capability of the entire wind farm is planned in advance according to grid requirements and power system condition changes. While existing methods de-load wind turbines with a static percentage in order to supply additional power when needed, the proposed method incorporates the dynamic frequency support into the optimal operation system of wind farm.

Abstract: The present invention relates to a method of operating a wind farm comprising an upstream and a downstream turbine, wherein the upstream turbine is operated with current operation parameters under current wind conditions, wherein the method comprises the steps of: receiving future wind conditions for a time period for the wind farm, and evaluating required operation parameters for minimising wake effect of the downstream turbine under the future wind conditions, and determining a cost coefficient for changing the operation parameters to required operation parameters under consideration of fatigue effect of the wind turbine, calculating power productions Po and Pc, in the predetermined time period, by the wind farm if operated with the current operation parameters under the current wind conditions and if operated with the required operation parameters under the future wind conditions, respectively, and operating the upstream turbine with the required operation parameters if the cost coefficient is lower than a

Abstract: A model-based control of an industrial process using a merged MLD system model is provided for the estimation and subsequent control of the process. An optimization of an objective function is performed. The objective function includes a difference between an observed quantity and an output variable of a Mixed Logical Dynamic (MLD) system model of the process. The optimization is performed as a function of state variables of the MLD system model, over a number of time steps in the past, and subject to constraints defined by the MLD system model's dynamics. The optimizing values of the state variables are retained as estimated initial states for subsequent control of the process in a model-based manner including the same MLD system model. The single MLD system model is a combination or merger of individual MLD subsystem models representing the sub-processes of the process, and may be elaborated during a customization step.

Abstract: A model-based control of an industrial process using a merged MLD system model is provided for the estimation and subsequent control of the process. An optimization of an objective function is performed. The objective function includes a difference between an observed quantity and an output variable of a Mixed Logical Dynamic (MLD) system model of the process. The optimization is performed as a function of state variables of the MLD system model, over a number of time steps in the past, and subject to constraints defined by the MLD system model's dynamics. The optimizing values of the state variables are retained as estimated initial states for subsequent control of the process in a model-based manner including the same MLD system model. The single MLD system model is a combination or merger of individual MLD subsystem models representing the sub-processes of the process, and may be elaborated during a customization step.

Abstract: A control system for controlling an industrial process includes an indicator generator configured to determine at least one fuzzy logic based indicator from measured process variables. The control system also includes a state estimator configured to determine estimated physical process states based on the fuzzy indicator. For controlling the industrial process, the process controller is configured to calculate manipulated variables based on (i) defined set-points and (ii) a physical model of the process using the estimated physical process states. Combining a fuzzy logic indicator with a model based process controller provides robust indicators of the process states for controlling an industrial process in a real plant situation in which measured process variables may possibly contradict each other.