Wind Farm Performance Validation Using Multi-Feature Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for validating wind farm performance improvements are hindered by imprecision in nacelle anemometer measurements and the high cost of external meteorological masts, making it difficult to accurately assess the benefits of upgrades such as wake minimization technologies, which affect the power output and longevity of downwind turbines.
Innovation Solution
A system and method that uses multi-feature estimation to generate baseline models of wind farm performance from operating data, selecting an optimal baseline model to compare with actual performance after upgrades, leveraging multiple sensors and machine learning algorithms to normalize uncertainty estimates and improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If nacelle anemometer measurements are used to baseline power output, then the approach is cost-effective and widely applicable, but measurement precision deteriorates due to imprecision in anemometer readings and projection errors into AEP estimates
Solution Approach 1:
The patent combines data from multiple nacelle anemometers across different turbines to create a collective baseline model. By merging measurements from multiple sources, the system compensates for individual anemometer imprecision while maintaining cost-effectiveness of using existing turbine sensors rather than installing external met masts.
Solution Approach 2:
The system creates a virtual copy of external met mast functionality by using machine learning algorithms to model the relationship between nacelle anemometer readings and actual wind conditions. This virtual model replicates the precision benefits of external masts without the associated costs.
2Measurement precision
If external meteorological masts are deployed to improve measurement accuracy, then power output validation precision improves, but device complexity and cost increase significantly
Solution Approach 1:
The patent introduces machine learning algorithms as an intermediary layer between existing nacelle anemometer data and performance validation needs. This computational intermediary extracts precise wind condition information from imperfect sensor readings, achieving met-mast-level accuracy without physical infrastructure complexity.
Solution Approach 2:
The system replaces the mechanical/physical met mast infrastructure with a computational model that processes electrical sensor data. This substitution eliminates the need for tall towers, external sensor installations, and associated maintenance while achieving comparable or superior measurement precision through data fusion and machine learning.
3Ease of operation
If individual wind turbine power curves are used to assess upgrade benefits, then the approach is simple to implement, but reliability deteriorates because individual curves cannot discern benefits of wake minimization technologies that create more wind for the farm
Solution Approach 1:
The patent creates a universal baseline model that serves multiple functions: it validates individual turbine upgrades, assesses farm-wide wake minimization technologies, and provides a consistent framework for different upgrade types. This multi-functional model replaces multiple individual power curves with a single robust validation system.
Solution Approach 2:
The system segments the wind farm into multiple measurement zones using data from different nacelle anemometers, allowing independent analysis of local wind conditions and upgrade impacts. This segmentation enables accurate attribution of performance changes to specific upgrades while accounting for spatial variations in wake effects and wind resources.
Data Source
AI summary
The present disclosure is directed to systems and methods for validating and/or identifying wind farm performance measurements so as to optimize wind farm performance. The method includes measuring operating data from one or more wind turbines of the farm. Another step includes generating a plurality of baseline models of performance of the wind farm from at least a portion of the operating data. Thus, each of the baseline models of performance is developed from a different portion of operating data so as to provide comparable models. The method also includes selecting an optimal baseline model and comparing the optimal baseline model with actual performance of the wind farm. In a particular embodiment, the actual performance of the wind farm is determined after one or more wind turbines of the wind farm is modified by one or more upgrades.