Renewable Power Forecasting With Mesh-Based Weather Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to accurately predict renewable energy power generation amounts due to unknown installation sites, installation requirements, and engineering characteristics of renewable energy power generators.
Innovation Solution
A power generation amount management system that utilizes actual power generation and weather data to create a power generation conversion model, predicting renewable energy power generation amounts by dividing areas into meshes and using weather element values as inputs to calculate output power generation amounts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If weather prediction data and power generation conversion factors are used to predict renewable energy power generation amounts, then prediction capability is improved, but accuracy deteriorates when installation sites and engineering characteristics are unknown
Solution Approach 1:
The patent divides the prediction approach into two segments: (1) using detailed installation data when available for high-precision individual predictions, and (2) using aggregated weather data and learned conversion models when installation details are unknown for area-level predictions. This segmentation allows the system to adapt its methodology based on data availability, resolving the contradiction between prediction capability and accuracy.
Solution Approach 2:
The patent changes the parameters used for prediction based on data availability. When installation sites and engineering characteristics are unknown, it transitions from using detailed generator-specific parameters to using aggregated weather elements and empirically learned power generation conversion factors, enabling predictions at the area level rather than individual generator level.
2Measurement precision
If detailed installation data of each renewable energy power generator is collected, then prediction accuracy is improved, but data management complexity increases
Solution Approach 1:
The patent segments the data management approach into two pathways: collecting detailed installation data when possible for high-precision predictions, and using publicly available aggregated weather data with learned conversion models when detailed data is unavailable. This reduces the overall data management burden while maintaining prediction capability at appropriate levels.
Solution Approach 2:
The patent introduces power generation conversion factors as an intermediary that bridges the gap between readily available weather data and power generation outputs. These conversion factors are learned from historical data and enable predictions without requiring direct access to detailed installation specifications, thus reducing data management complexity.
3Ease of operation
If publicly available weather data is used for prediction, then ease of operation is improved, but prediction accuracy deteriorates due to lack of site-specific information
Solution Approach 1:
The patent changes the granularity of weather data parameters from detailed site-specific measurements to aggregated area-level weather elements. By using publicly available weather data at the area level combined with learned power generation conversion factors, the system maintains ease of operation while achieving sufficient prediction accuracy for area-level renewable energy forecasting.
Data Source
AI summary
A system refers to actual weather data made publicly available by a first institution, and creates a model that uses a value of a weather element for each section as an input and uses a value of a renewable energy power generation amount of the area as an output based on the actual value of the weather element calculated for each section, and the actual value of the renewable energy power generation amount of the area. The system refers to weather prediction data made publicly available by the second institution, and calculates an actual value of the weather element regarding each of the plurality of sections including the area based on a prediction value of the weather element for each segment in the corresponding section, and calculates a prediction value of the renewable energy power generation amount based on the prediction value of the weather element for each section.