Wind Turbine Power Forecasting Using Local Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current power forecasting methods for wind turbines in wind farms are inaccurate due to reliance on general meteorological data, ignoring local conditions, leading to unstable output power and potential punitive sanctions for power plants.
Innovation Solution
A method and apparatus that generate a corrected data set from in-situ environmental data within the wind farm, correct a weather forecasting model, and forecast wind information and output power using a power forecasting model tailored to specific wind turbines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If general-purpose weather forecasts from third parties are used, then forecasting cost is reduced, but forecasting accuracy deteriorates due to inability to capture local meteorological conditions
Solution Approach 1:
The patent applies local quality by deploying meteorological sensors specifically at the wind farm location to capture local meteorological conditions (wind speed, direction, temperature, humidity, pressure) that differ from general regional weather patterns. This localized measurement approach directly resolves the contradiction by improving forecasting accuracy through site-specific data while avoiding the need for complex third-party weather model integration.
Solution Approach 2:
The wind farm becomes self-sufficient in meteorological data collection by installing its own sensor network, eliminating dependence on external weather services. The system serves its own forecasting needs through self-collected data, processing and analyzing local measurements independently to generate accurate power forecasts without requiring complex external weather model corrections.
2Measurement precision
If in-situ meteorological sensors are deployed at wind farm, then forecasting accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The meteorological sensor system is designed with multi-functionality to justify its deployment. Sensors simultaneously measure multiple parameters (wind speed, wind direction, temperature, humidity, atmospheric pressure) that all contribute to power forecasting. This universal approach consolidates what would otherwise require separate measurement systems, reducing overall complexity while maintaining high forecasting accuracy through comprehensive local data collection.
3Measurement precision
If historical power data analysis is used, then forecasting method simplicity is maintained, but forecasting accuracy deteriorates due to non-linear and fast-changing characteristics of wind power
Solution Approach 1:
The patent replaces simple historical data analysis (statistical/mechanical approach) with a physics-based meteorological model driven by real-time sensor data. Instead of relying on past power output patterns that fail to capture non-linear wind characteristics, the system uses fundamental meteorological measurements (wind speed, direction, temperature) fed into a power curve model, achieving superior accuracy while maintaining reasonable computational simplicity.
4Measurement precision
If weather forecasting model is corrected using local data, then power forecasting accuracy is improved, but data processing complexity increases
Solution Approach 1:
The patent applies parameter changes by using real-time meteorological parameters (wind speed, wind direction, temperature, humidity, pressure) from local sensors to dynamically adjust the power forecasting model. Instead of complex model corrections, the system changes input parameters to reflect current local conditions, then applies these updated parameters to the power curve to generate accurate forecasts. This approach simplifies data processing while maintaining high accuracy through parameter-driven adaptation.
Data Source
AI summary
A method and apparatus for forecasting output power of wind turbine in a wind farm. The present invention provides a method for forecasting output power of a wind turbine in a wind farm, including: generating a corrected data set based on environmental data collected from at least one sensor in the wind farm; correcting a weather forecasting model by using the corrected data set; obtaining a forecast value of wind information at the wind turbine based on the corrected weather forecasting model; and forecasting the output power of the wind turbine based on the forecast value and a power forecasting model.