Solar Power Prediction Using Weather Coefficients Without Pyranometers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solar power generation prediction methods require a pyranometer for accurate insolation measurement, which is limited and costly, and do not account for weather conditions beyond insolation.
Innovation Solution
A prediction method that uses past weather and power generation data to create a sunny power generation model without a pyranometer, incorporating weather coefficients and a sunny power generation curve expressed as an axisymmetric function, allowing for accurate prediction of solar power generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a pyranometer is installed to obtain accurate insolation measurement, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual pyranometer by using a camera to capture sky images and processing these images through image recognition algorithms to calculate insolation values. This copying approach replaces the physical pyranometer sensor with a computational model that processes visual data, thereby achieving accurate insolation measurement without installing additional hardware devices.
Solution Approach 2:
The patent substitutes the mechanical/pyrical measurement system of a pyranometer with an optical-computational system. Instead of using a pyranometer to directly measure solar radiation, the system uses a camera to capture sky images and employs image processing algorithms to calculate insolation, replacing the physical measurement mechanism with a digital computational approach.
2Device complexity
If only insolation data is used for prediction, then device complexity is reduced, but measurement precision and prediction accuracy deteriorate
Solution Approach 1:
The patent merges multiple data sources including sky images, weather data, and historical power generation data into a unified prediction model. By combining these diverse data types, the system achieves comprehensive prediction accuracy that accounts for various factors affecting solar power generation, overcoming the limitation of using only insolation data.
Solution Approach 2:
The patent adds new dimensions to the prediction model by incorporating sky image analysis and weather condition data alongside traditional insolation measurements. This multi-dimensional approach enables the system to capture a more complete picture of factors influencing power generation, thereby improving prediction accuracy without relying on a single data source.
3Measurement precision
If weather coefficients are incorporated into the prediction model, then prediction accuracy is improved, but device complexity increases
Solution Approach 1:
The patent introduces weather coefficients as adjustable parameters in the prediction model that quantify the impact of different weather conditions on power generation. By changing and optimizing these parameters based on historical data and weather patterns, the system improves prediction accuracy while maintaining a manageable model structure through parameterized representations of complex weather effects.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate prediction of solar power generation without a pyranometer, improving prediction accuracy through increased data points and finer weather-based predictions, even in peak shaving scenarios.
Implementation Method 1
a solar power generation system including a solar cell and a power conditioning system
Data Source
AI summary
A prediction method of solar-generated power includes: storing past data obtained by associating weather data and power generation data of a solar cell output via a PCS for at least one year before a prediction target day; calculating a sunny power generation curve from the past data; obtaining an annual transition curved line indicating an annual transition of a total power generation amount; obtaining a sunny power generation model from the sunny power generation curve so as to match the annual transition curved line; obtaining a the sunny power generation model for the entire year; obtaining a weather coefficient; and acquiring a weather forecast and obtaining prediction generated power from the sunny power generation model and the weather coefficient.