Solar Radiation Estimation via ML Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating solar radiation energy resources are inaccurate and time-consuming, leading to inefficiencies in solar power plant design and operation due to discrepancies between estimated and actual solar radiation data, which can result in underperformance or inefficiency of solar power plants.
Innovation Solution
A system using a machine learning model trained with a training dataset comprising satellite weather data and measured solar data to continuously estimate solar radiation energy resources, allowing for real-time adjustments and improvements in accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to estimate solar radiation energy resources, then the estimation process is simple, but the accuracy is low and time-consuming
Solution Approach 1:
The patent replaces traditional mechanical/manual estimation methods with a machine learning-based automated system. The ML model processes satellite weather data and measured solar data to generate accurate solar radiation estimates, eliminating the need for time-consuming manual analysis while significantly improving accuracy through continuous learning and calibration.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between raw data (satellite weather data and measured solar data) and the final solar radiation estimation. This intermediary processes and synthesizes multiple data sources to produce accurate predictions, resolving the contradiction between accuracy and time efficiency.
2Reliability
If traditional estimation methods are used, then the system is simple to implement, but discrepancies between estimated and actual solar radiation data occur
Solution Approach 1:
The patent implements a feedback mechanism where the machine learning model is continuously trained and calibrated using measured solar data from pyranometers. This feedback loop ensures that the model's predictions remain consistent with actual solar radiation data, improving reliability while the automated nature of the system manages the complexity.
Solution Approach 2:
The patent creates a multi-functional system that performs data collection, processing, model training, calibration, and prediction within a single integrated platform. This universal system handles multiple tasks that would otherwise require separate tools, managing complexity while ensuring consistent and reliable solar radiation estimates.
3Productivity
If manual estimation processes are used, then the system requires minimal computational resources, but the productivity is low
Solution Approach 1:
The patent performs preliminary actions by pre-training the machine learning model on historical data and continuously calibrating it with measured solar data. This preliminary preparation enables the model to generate rapid, accurate predictions without requiring intensive real-time computational resources, thus improving productivity while managing energy consumption.
Solution Approach 2:
The patent uses satellite weather data as a proxy or copy of actual ground conditions, which can be processed computationally with relatively low energy requirements. This copied data, when combined with measured solar data and processed by the trained ML model, enables fast predictions without requiring direct, energy-intensive real-time measurements for every estimation.
Data Source
AI summary
Apparatus, methods, and non-transitory computer readable medium for estimating solar radiation energy resources. The method includes receiving a request for estimating solar radiation energy resources for a solar site; obtaining metadata about the solar site; obtaining satellite weather data corresponding to the solar site; obtaining measured solar data on the solar site; generating a training dataset based on the satellite weather data and the measured solar data; training a machine learning model by the training dataset; and synthesizing solar radiation energy resource data corresponding to the solar site using the machine learning model.