Solar Radiation Estimation Using PV Output and Terrain Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for estimating global solar radiation amount using meteorological satellite images lack accuracy due to insufficient consideration of cloud and terrain influences, leading to inadequate estimation precision.
Innovation Solution
A global solar radiation amount estimation system utilizing machine learning with power generation actual data, including factors like temperature, humidity, and installation details, to enhance estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a meteorological satellite image method is used to estimate global solar radiation amount, then the estimation can be performed with available satellite data, but the observation accuracy is not high and cloud influence is not sufficiently considered
Solution Approach 1:
The patent combines multiple data sources including satellite images, ground observation data, and power generation data into a unified machine learning model. This integration allows the system to leverage the strengths of each data source while compensating for their individual limitations, thereby improving measurement precision without requiring a single complex device
Solution Approach 2:
The patent introduces power generation data as an intermediary variable that indirectly reflects cloud cover and atmospheric conditions. This intermediary data helps bridge the gap between satellite observations and actual ground-level solar radiation, improving accuracy without directly measuring cloud properties
2Measurement precision
If a meteorological satellite image method is used to estimate global solar radiation amount, then the estimation can be performed remotely, but terrain influence such as altitude and mountain shadow is not taken into consideration
Solution Approach 1:
The patent incorporates terrain data (altitude, topography, mountain shadow information) into the machine learning model in advance. By pre-integrating this terrain information with satellite and power generation data, the system can account for terrain effects before performing the solar radiation estimation, preventing information loss
Solution Approach 2:
The patent creates a multi-functional estimation system that processes diverse data types including satellite imagery, terrain data, meteorological observations, and power generation records. This universal approach allows a single system to handle multiple information sources and account for various factors affecting solar radiation simultaneously
3Measurement precision
If power generation actual data is used as learning data for machine learning, then the estimation accuracy is improved, but the device complexity increases due to data collection and processing requirements
Solution Approach 1:
The patent leverages power generation data that is already being collected by solar power facilities for their operational purposes. By utilizing this existing data for training the machine learning model, the system avoids the need for separate dedicated measurement devices and reduces overall system complexity while improving accuracy
Solution Approach 2:
The patent transforms power generation data into useful training features by applying appropriate preprocessing and feature engineering. This parameter transformation converts operational data into meaningful inputs for the machine learning model, reducing the complexity of data collection while maintaining high estimation accuracy
Data Source
AI summary
A global solar radiation amount estimation device includes: a feature amount acquisition unit that acquires power generation actual data including a power generation amount at a power generation point; and an estimation unit that estimates a global solar radiation amount corresponding to the power generation actual data acquired by the feature amount acquisition unit using a learned model that is generated by machine learning, as learning data, a set of the power generation actual data prepared in advance and a corresponding global solar radiation amount of ground observation, receives the power generation actual data as an input, and outputs the global solar radiation amount.