Cloud Coverage Prediction via Back-Propagation Velocity Field
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting solar energy output are inadequate due to the variability caused by cloud coverage, as they fail to accurately forecast future cloud positions and their impact on solar irradiance.
Innovation Solution
A method using a ground-based all-sky imaging camera calculates an estimated cloud velocity field from sky images, applies a back-propagation algorithm to predict cloud coverage for future sun locations, and determines cloud coverage by segmenting images and applying probability calculations based on propagated sun pixel locations and segmented cloud models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional solar energy prediction methods are used, then the system is simple to operate, but the prediction accuracy deteriorates due to inability to forecast cloud coverage
Solution Approach 1:
The sky image is segmented into multiple regions around the sun position, and the velocity field is divided into discrete components at different spatial locations. This segmentation allows the complex prediction problem to be broken down into manageable parts, improving accuracy while maintaining computational feasibility.
Solution Approach 2:
A cloud velocity field model serves as an intermediary between the observed cloud positions and the predicted sun coverage. The velocity field acts as a mediator that transforms current cloud states into future predictions, enabling accurate forecasting without directly modeling complex cloud-sun interactions.
2Measurement precision
If real-time sky imaging analysis is performed, then the cloud coverage prediction accuracy improves, but the computational time and processing complexity increase
Solution Approach 1:
The system performs preliminary processing by pre-calculating the cloud velocity field from historical sky images and pre-determining the sun's future position using astronomical algorithms. This preliminary action reduces the computational burden during real-time prediction, improving accuracy while minimizing processing time.
Solution Approach 2:
The patent replaces complex mechanical cloud tracking systems with an optical flow-based velocity field model. This substitution uses image processing techniques to derive cloud motion from pixel intensity changes, achieving accurate predictions with reduced computational complexity compared to traditional mechanical tracking methods.
3Measurement precision
If the sun position is predicted using astronomical data, then the accuracy of solar irradiance prediction improves, but the system complexity increases due to integration requirements
Solution Approach 1:
The system uses a universal sun position calculation module that integrates astronomical algorithms with the cloud velocity field model. This multi-functional approach allows the same framework to handle both astronomical data processing and cloud dynamics, improving solar irradiance prediction accuracy while managing integration complexity through unified processing.
Data Source
AI summary
A method for predicting short-term cloud coverage includes a computer calculating an estimated cloud velocity field at a current time value based on sky images. The computer determines a segmented cloud model based on the sky images, a future sun location corresponding to a future time value, and sun pixel locations at the future time value based on the future sun location. Next, the computer applies a back-propagation algorithm to the sun pixel locations using the estimated cloud velocity field to yield propagated sun pixel locations corresponding to a previous time value. Then, the computer predicts cloud coverage for the future sun location based on the propagated sun pixel locations and the segmented cloud model.