Abstract: An example method comprises receiving first historical meso-scale numerical weather predictions (NWP) and power flow information for a geographic distribution area, correcting for overfitting of the historical NWP predictions, reducing parameters in the first historical NWP predictions, training first power flow models using the first reduced, corrected historical NWP predictions and the historical power flow information for all or parts of the first geographic distribution area, receiving current NWP predictions for the first geographic distribution area, applying any number of first power flow models to the current NWP predictions to generate any number of power flow predictions, comparing one or more of the any number of power flow predictions to one or more first thresholds to determine significance of reverse power flows, and generating a first report including at least one prediction of the reverse power flow and identifying the first geographic distribution area.

Abstract: An example method comprises receiving first historical meso-scale numerical weather predictions (NWP) and power flow information for a geographic distribution area, correcting for overfitting of the historical NWP predictions, reducing parameters in the first historical NWP predictions, training first power flow models using the first reduced, corrected historical NWP predictions and the historical power flow information for all or parts of the first geographic distribution area, receiving current NWP predictions for the first geographic distribution area, applying any number of first power flow models to the current NWP predictions to generate any number of power flow predictions, comparing one or more of the any number of power flow predictions to one or more first thresholds to determine significance of reverse power flows, and generating a first report including at least one prediction of the reverse power flow and identifying the first geographic distribution area.

Abstract: An example method comprises receiving first historical meso-scale numerical weather predictions (NWP) and power flow information for a geographic distribution area, correcting for overfitting of the historical NWP predictions, reducing parameters in the first historical NWP predictions, training first power flow models using the first reduced, corrected historical NWP predictions and the historical power flow information for all or parts of the first geographic distribution area, receiving current NWP predictions for the first geographic distribution area, applying any number of first power flow models to the current NWP predictions to generate any number of power flow predictions, comparing one or more of the any number of power flow predictions to one or more first thresholds to determine significance of reverse power flows, and generating a first report including at least one prediction of the reverse power flow and identifying the first geographic distribution area.

Abstract: An example method comprises receiving first historical meso-scale numerical weather predictions (NWP) and power flow information for a geographic distribution area, correcting for overfitting of the historical NWP predictions, reducing parameters in the first historical NWP predictions, training first power flow models using the first reduced, corrected historical NWP predictions and the historical power flow information for all or parts of the first geographic distribution area, receiving current NWP predictions for the first geographic distribution area, applying any number of first power flow models to the current NWP predictions to generate any number of power flow predictions, comparing one or more of the any number of power flow predictions to one or more first thresholds to determine significance of reverse power flows, and generating a first report including at least one prediction of the reverse power flow and identifying the first geographic distribution area.

Abstract: An example method comprises receiving an initial topology of an electrical, receiving a selection of a region of interest, determining one or more external equivalents of the electrical network that are external to the region of interest, determining one or more internal equivalents of the region of interest, calculating a sensitivity matrix based on electrical impedances of at least one of the one or more internal equivalents and based on an amount of power exchanged when in operation, determining a subset of the sensitivity matrix as indicating highly sensitive buses, receiving historical data regarding power flows, predicting power flow for each highly sensitive buses, comparing the predicted power flow to at least one predetermined threshold to determine possible network congestion, and generating a report regarding network congestion and locations of possible network congestion in the region of interest based on the comparison.

Abstract: A method includes training a prediction model to forecast a likelihood of curtailment for at least one wind turbine. The prediction model is trained, by a processor system, using historical information and historical instances of curtailment. The method also includes forecasting the likelihood of curtailment for the at least one wind turbine using the trained prediction model. The method also includes outputting the forecasted likelihood.

Abstract: An example method comprises receiving an initial topology of an electrical, receiving a selection of a region of interest, determining one or more external equivalents of the electrical network that are external to the region of interest, determining one or more internal equivalents of the region of interest, calculating a sensitivity matrix based on electrical impedances of at least one of the one or more internal equivalents and based on an amount of power exchanged when in operation, determining a subset of the sensitivity matrix as indicating highly sensitive buses, receiving historical data regarding power flows, predicting power flow for each highly sensitive buses, comparing the predicted power flow to at least one predetermined threshold to determine possible network congestion, and generating a report regarding network congestion and locations of possible network congestion in the region of interest based on the comparison.

Abstract: An example method comprises receiving first historical meso-scale numerical weather predictions (NWP) and power flow information for a geographic distribution area, correcting for overfitting of the historical NWP predictions, reducing parameters in the first historical NWP predictions, training first power flow models using the first reduced, corrected historical NWP predictions and the historical power flow information for all or parts of the first geographic distribution area, receiving current NWP predictions for the first geographic distribution area, applying any number of first power flow models to the current NWP predictions to generate any number of power flow predictions, comparing one or more of the any number of power flow predictions to one or more first thresholds to determine significance of reverse power flows, and generating a first report including at least one prediction of the reverse power flow and identifying the first geographic distribution area.

Abstract: Embodiments herein relate to improving a stochastic forecast for uncertain power generations and demands to quantify an effect on an electrical power grid. To improve the stochastic forecast, a method includes fitting marginal distributions to data of the uncertain power generation and demand by power generation and demand nodes of the electrical power grid. The power generation and demand nodes provide corresponding uncertain power generation and demand based on a renewable energy source. The method also includes determining a correlation structure between the power generation and demand nodes by transforming the data from marginal distributions to a second distribution and by fitting a multivariate time series on transformed data. The method also includes simulating multivariate stochastic forecast with an improved correlation structure.

Abstract: An example method comprises receiving an initial topology of an electrical, receiving a selection of a region of interest, determining one or more external equivalents of the electrical network that are external to the region of interest, determining one or more internal equivalents of the region of interest, calculating a sensitivity matrix based on electrical impedances of at least one of the one or more internal equivalents and based on an amount of power exchanged when in operation, determining a subset of the sensitivity matrix as indicating highly sensitive buses, receiving historical data regarding power flows, predicting power flow for each highly sensitive buses, comparing the predicted power flow to at least one predetermined threshold to determine possible network congestion, and generating a report regarding network congestion and locations of possible network congestion in the region of interest based on the comparison.

Abstract: A method includes training a prediction model to forecast a likelihood of curtailment for at least one wind turbine. The prediction model is trained, by a processor system, using historical information and historical instances of curtailment. The method also includes forecasting the likelihood of curtailment for the at least one wind turbine using the trained prediction model. The method also includes outputting the forecasted likelihood.

Abstract: Embodiments herein relate to improving a stochastic forecast for uncertain power generations and demands to quantify an effect on an electrical power grid. To improve the stochastic forecast, a method includes fitting marginal distributions to data of the uncertain power generation and demand by power generation and demand nodes of the electrical power grid. The power generation and demand nodes provide corresponding uncertain power generation and demand based on a renewable energy source. The method also includes determining a correlation structure between the power generation and demand nodes by transforming the data from marginal distributions to a second distribution and by fitting a multivariate time series on transformed data. The method also includes simulating multivariate stochastic forecast with an improved correlation structure.