Systems and methods for wind forecasting and grid management

{
  "publication_number": "US2012185414A1",
  "country": "US",
  "kind": "A1",
  "title": "Systems and methods for wind forecasting and grid management",
  "abstract": "In one embodiment, a wind power ramp event nowcasting system includes a wind condition analyzer for detecting a wind power ramp signal; a sensor array, situated in an area relative to a wind farm, the sensor array providing data to the wind condition analyzer; a mesoscale numerical model; a neural network pattern recognizer; and a statistical forecast model, wherein the statistical model receives input from the wind condition analyzer, the mesoscale numerical model, and the neural network pattern recognizer; and the statistical forecast model outputs a time and duration for the wind power ramp event (WPRE) for the wind farm.",
  "claims": [
    "1. A wind power ramp event nowcasting system comprising: a wind condition analyzer for detecting a wind power ramp signal; a sensor array, situated in an area relative to a wind farm, the sensor array providing data to the wind condition analyzer; a physical numerical model; a neural network pattern recognizer; and a statistical forecast model, wherein the statistical model receives input from the wind condition analyzer, the physical numerical model, and the neural network pattern recognizer; and the statistical forecast model outputs a time and duration for the wind power ramp event (WPRE) for the wind farm. 2. The system of claim 1 wherein the wind condition analyzer includes: a surface observation analyzer; and a vertical atmospheric analyzer. 3. The system of claim 2 wherein the surface observation analyzer detects a significant change in wind speed, strong vertical and horizontal wind shears, a pressure drop or surge at the surface, a temperature increase or decrease, and shifts in atmospheric stability; the data is provided from an Atmospheric Observation Network (AON), which is part of the sensor array; and the surface observation analyzer includes a module for detecting and calculating winds, pressure, temperature, and humidity. 4. The system of claim 2 wherein the vertical atmospheric analyzer provides vertical profiles of horizontal wind speed and direction and boundary and mixing layer heights and atmospheric instability. 5. The system of claim 1 wherein the neural network pattern recognizer is trained by providing it teaching patterns. 6. The system of claim 5 wherein the neural network pattern recognizer changes according to a learning rule. 7. The system of claim 5 wherein the teaching patterns are upwind meteorological variables. 8. The system of claim 7 wherein the upwind meteorological variables are wind speed, wind direction, pressure, temperature, and humidity. 9. The system of claim 5 wherein the teaching patterns are data sets which involve wind power ramp events (WPREs). 10. The system of claim 1, further comprising: a radar analyzer, which provides input to the statistical forecast model. 11. The system of claim 1, further comprising: a Lagrangian Scalar Integration analyzer, which provides input to the statistical forecast model. 12. The system of claim 1 wherein the physical numerical model is a mesoscale numerical model. 13. A wind forecasting system comprising: a wind condition analyzer for detecting a wind event signal; a sensor array situated in an area, the sensor array providing data to the wind condition analyzer; a mesoscale numerical model; a neural network pattern recognizer; and a statistical forecast model, wherein the statistical model receives input from the wind condition analyzer, the mesoscale numerical model, and the neural network pattern recognizer, and the statistical forecast model outputs a wind event for the area. 14. The system of claim 13 wherein the neural network pattern recognizer is trained by providing it teaching patterns, and the neural network pattern recognizer changes according to a learning rule. 15. The system of claim 13 wherein the teaching patterns are upwind meteorological variables and the upwind meteorological variables are wind speed, wind direction, pressure, temperature, and humidity. 16. The system of claim 13 wherein the teaching patterns are data sets which involve prior occurrences of wind events similar to the wind event, and the prior occurrences of wind events are selected from the group consisting of events that caused a wind power ramp event (WPRE), tornados, thunderstorms, and storms with damaging winds. 17. A graphical user interface system for managing a wind farm, the system comprising: (a) a wind power ramp event (WPRE) prediction window, showing predicted wind and WPRE events; (b) an Atmospheric Observation Network (AON) monitoring window, showing the AON network and the wind farm; (c) a ramp event message window showing ramp event alerts; (d) a ramp event classification screen, providing for classification of ramp events; and (e) a history window, providing a history of past events and wind generation statistics. 18. A method of providing a wind event forecast, the method comprising: (a) detecting a footprint of a wind event that will occur in the future for an area of interest with a first module; (b) determining a duration and intensity of the wind event with a second module; and (c) providing the wind event forecast. 19. The method of claim 18, further comprising: (d) providing sensor data from a sensor array to the first module that is upwind of the area of interest, wherein the sensor data is used to detect the footprint; (e) providing the sensor data from the sensor array to the second module, wherein the sensor data is used in the determining of (d), wherein the first module includes a surface observation analyzer and a vertical atmospheric analyzer and the first module detects fronts as part of detecting the footprint, the fronts are marked by changes in temperature, moisture, wind speed and direction, atmospheric pressure, and a change in the precipitation pattern; the first module detects mesoscale features as part of detecting the footprint, wherein the mesoscale features are marked by an increase in cumuliform clouds and rain showers; and the first module detects dry lines, outflow boundaries/squall lines, lee troughs, and sea/lake breezes as part of detecting the footprint. 20. The method of claim 19 wherein the second module includes a neural network, a mesoscale numerical model, and a physical numerical model. 21. The method of claim 19, further comprising (d) training the neural network by providing weather data, wherein the weather data is data sets which involve WPREs only."
  ],
  "cpc": [
    "G01W 1/10",
    "F05B 2260/8211",
    "G01W 2203/00",
    "Y02A 90/10"
  ],
  "assignees": [
    "PYLE RICHARD",
    "WILSON NICHOLAS",
    "SHAO JIANMIN",
    "VAISALA INC"
  ],
  "filing_date": "2011-12-15",
  "publication_date": "2012-07-19",
  "priority_date": "2010-12-15",
  "application_number": "US-201113327527-A",
  "family_id": "46491530",
  "citations": [
    "US2006173623A1",
    "US5517193A"
  ]
}