Abstract: In various embodiments of the present disclosure, there is provided a method for increasing the reactive power capability of a wind power plant, in controlling a wind power plant. According to an embodiment, the method includes receiving a reactive power requirement from an electrical grid. The method further includes determining an active power generated by the wind power plant. According to an embodiment, the method includes checking if the reactive power requirement is satisfied by the wind power plant based on the active power generated by the wind power plant. The method further includes controlling the wind power plant to curtail the active power generated by the wind power plant by a curtailment amount when the reactive power requirement is not satisfied, and in response to a grid event. A corresponding wind power plant is further provided.

Abstract: In various embodiments of the present disclosure, there is provided a method for controlling a reactive current injection in a wind power plant during a grid fault. According to an embodiment, the method includes measuring an amount of reactive current to be provided by the wind power plant to the grid during the grid fault. The method further includes determining a difference between a given required reactive current contribution from the wind power plant and the amount of reactive current to be provided by the wind power plant to the grid during the grid fault. According to an embodiment, the method includes controlling a plurality of wind turbine generators in the wind power plant to generate additional reactive current according to a reactive current reference generated based on the difference. A corresponding wind power plant is further provided.

Abstract: In various embodiments of the present disclosure, there is provided a method for controlling a reactive current injection in a wind power plant during a grid fault. According to an embodiment, the method includes measuring an amount of reactive current to be provided by the wind power plant to the grid during the grid fault. The method further includes determining a difference between a given required reactive current contribution from the wind power plant and the amount of reactive current to be provided by the wind power plant to the grid during the grid fault. According to an embodiment, the method includes controlling a plurality of wind turbine generators in the wind power plant to generate additional reactive current according to a reactive current reference generated based on the difference. A corresponding wind power plant is further provided.

Abstract: In various embodiments of the present disclosure, there is provided a method for increasing the reactive power capability of a wind power plant, in controlling a wind power plant. According to an embodiment, the method includes receiving a reactive power requirement from an electrical grid. The method further includes determining an active power generated by the wind power plant. According to an embodiment, the method includes checking if the reactive power requirement is satisfied by the wind power plant based on the active power generated by the wind power plant. The method further includes controlling the wind power plant to curtail the active power generated by the wind power plant by a curtailment amount when the reactive power requirement is not satisfied, and in response to a grid event. A corresponding wind power plant is further provided.

Abstract: A method and framework are described for detecting changes in a multivariate data stream. A training set is formed by sampling time windows in a data stream containing data reflecting normal conditions. A histogram is created to summarize each window of data, and data within the histograms are clustered to form test distribution representatives to minimize the bulk of training data. Test data is then summarized using histograms representing time windows of data and data within the test histograms are clustered. The test histograms are compared to the training histograms using nearest neighbor techniques on the clustered data. Distances from the test histograms to the test distribution representatives are compared to a threshold to identify anomalies.

Abstract: A method and framework are described for detecting changes in a multivariate data stream. A training set is formed by sampling time windows in a data stream containing data reflecting normal conditions. A histogram is created to summarize each window of data, and data within the histograms are clustered to form test distribution representatives to minimize the bulk of training data. Test data is then summarized using histograms representing time windows of data and data within the test histograms are clustered. The test histograms are compared to the training histograms using nearest neighbor techniques on the clustered data. Distances from the test histograms to the test distribution representatives are compared to a threshold to identify anomalies.