Abstract: Devices and techniques are generally described for detection of abusive computational nodes. In various examples, first input data describing a first plurality of computational nodes and first data identifying a dimension along which to parse the first plurality of computational nodes may be received. A first computing device may generate input graph data representing the first plurality of computational nodes. The computational nodes of the first plurality of computational nodes may share a same value for the dimension are connected to one another in the input graph data. In various examples, a first graph machine learning model and at least one known abusive computational node may be used to determine a first set of candidate computational nodes for further evaluation. In some cases, network access of a first computational node of the first set of candidate computational nodes may be terminated.

Abstract: The present discussion relates to generating power generation forecasts both on-site and remote to a wind farm, or other intermittent power generation asset, so as to increase the reliability of providing a forecast to interested parties, such as regulatory authorities. Forecasts may be separately generated at both the on-site and remote locations and, if both are available, one is selected for transmission to interested parties, such as regulatory authorities. If, due to circumstances, one forecast is unavailable, the other forecast may be used in its place locally and remotely, communications permitting.

Abstract: Disclosed are systems and methods for handling categorical field values in machine learning applications, and particularly neural networks. Categorical field values are generally transformed into vectors prior to being passed to a neural network. However, low-dimensionality vectors limit the ability of the network to understand correlations between contextually, semantically, or characteristically similar values. High-dimensionality vectors, in contrast, can overwhelm neural networks, causing the network to seek correlations with respect to individual dimensional values, which correlations may be illusory. The present disclosure relates to a hierarchical neural network that includes a main network as well as one or more auxiliary networks. Categorical field values are processed in an auxiliary network, to reduce a dimensionality of the value before being processed by the main network.

Abstract: A wind power generation system includes one or both of a memory or storage device storing one or more processor-executable executable routines, and one or more processors configured to execute the one or more executable routines which, when executed, cause acts to be performed. The acts include receiving weather data, wind turbine system data, or a combination thereof; transforming the weather data, the wind turbine system data, or the combination thereof, into a data subset, wherein the data subset comprises a first time period data; selecting one or more wind power system models from a plurality of models; transforming the one or more wind power system models into one or more trained models at least partially based on the data subset; and executing the one or more trained models to derive a forecast, wherein the forecast comprises a predicted electrical power production for the wind power system.

Abstract: A method, medium, and system to receive a baseline airline schedule including details associated with at least one flight; optimize the baseline airline schedule in accordance with at least one specified optimization objective to generate an optimized airline schedule; evaluate a robustness of the optimized airline schedule based on an execution of a simulation based process to generate a set of quantitative metrics; and generate a record of the set of quantitative metrics.

Abstract: The present disclosure is directed to a system and method for controlling a wind farm. The method includes operating the wind farm based on multiple control settings over a plurality of time intervals. A next step includes collecting one or more wind parameters of the wind farm over the plurality of time intervals and one or more operating data points for each of the wind turbines in the wind farm for the plurality time intervals. The method also includes calculating a contribution of the operating data points for each of the wind turbines as a function of the one or more wind parameters. Further steps of the method include estimating an energy production for the wind farm for each of the control settings based at least in part on the contribution of the operating data points and controlling the wind farm based on optimal control settings.

Abstract: The present discussion relates to generating power generation forecasts both on-site and remote to a wind farm, or other intermittent power generation asset, so as to increase the reliability of providing a forecast to interested parties, such as regulatory authorities. Forecasts may be separately generated at both the on-site and remote locations and, if both are available, one is selected for transmission to interested parties, such as regulatory authorities. If, due to circumstances, one forecast is unavailable, the other forecast may be used in its place locally and remotely, communications permitting.

Abstract: A wind power generation system includes one or both of a memory or storage device storing one or more processor-executable executable routines, and one or more processors configured to execute the one or more executable routines which, when executed, cause acts to be performed. The acts include receiving weather data, wind turbine system data, or a combination thereof; transforming the weather data, the wind turbine system data, or the combination thereof, into a data subset, wherein the data subset comprises a first time period data; selecting one or more wind power system models from a plurality of models; transforming the one or more wind power system models into one or more trained models at least partially based on the data subset; and executing the one or more trained models to derive a forecast, wherein the forecast comprises a predicted electrical power production for the wind power system.

Abstract: A method, medium, and system to receive a baseline airline schedule including details associated with at least one flight; optimize the baseline airline schedule in accordance with at least one specified optimization objective to generate an optimized airline schedule; evaluate a robustness of the optimized airline schedule based on an execution of a simulation based process to generate a set of quantitative metrics; and generate a record of the set of quantitative metrics.

Abstract: Embodiments allow data cleaning of industrial data gathered from at least one sensor. The data cleaning utilizes a workflow that defines at least one cleaning step to be performed. Each cleaning step comprises detecting defects based on at least one constraint such as various models and/or statistics. Potential defects are presented to a user for feedback. The data is cleaned based on the feedback. Multiple copies of the data are stored to track all the various cleaning choices. All choices can be rolled back at will so that cleaning decisions made can be eliminated and different choices applied. Intermediate data is captured to allow reporting and auditing of the cleaning process.

Abstract: The present disclosure is directed to a system and method for controlling a wind farm. The method includes operating the wind farm based on multiple control settings over a plurality of time intervals. A next step includes collecting one or more wind parameters of the wind farm over the plurality of time intervals and one or more operating data points for each of the wind turbines in the wind farm for the plurality time intervals. The method also includes calculating a contribution of the operating data points for each of the wind turbines as a function of the one or more wind parameters. Further steps of the method include estimating an energy production for the wind farm for each of the control settings based at least in part on the contribution of the operating data points and controlling the wind farm based on optimal control settings.