"solar power forecasting"

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current solar power systems face challenges in predicting solar irradiance due to the intermittent nature of solar radiation, primarily caused by cloud occlusion, leading to suboptimal operation and delays in adapting electrical grid responses.

Innovation Solution

A method involving a distributed network of digital cameras with wide-angle or fisheye lenses captures sky images, generates 3D object data to model occluding objects, and predicts solar radiation by computing light paths and occlusion levels, enabling accurate forecasting and control signal generation for solar power systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If solar power systems operate without accurate solar irradiance prediction, then system operation is simple, but solar radiation prediction accuracy deteriorates due to cloud occlusion

Engineering Contradiction:
Improvesolar radiation prediction accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transitions from 2D sky image analysis to 3D cloud structure reconstruction. By processing sky images through multiple dimensions (spatial coordinates, altitude, volumetric density), the system creates a comprehensive 3D model of occluding objects, significantly improving solar irradiance prediction accuracy while managing complexity through systematic dimensionality addition

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent introduces a distributed network of sky imagers and a centralized processing system as intermediaries. These intermediaries capture, transmit, and process sky images to generate occlusion forecasts, acting as a bridge between direct solar radiation measurement and predictive control, thereby improving accuracy without requiring direct complex measurement at the solar source

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If solar irradiance prediction is improved using multiple sky imagers, then prediction accuracy is improved, but device complexity increases

Engineering Contradiction:
Improvesolar irradiance prediction accuracyVSAvoidcamera network complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the sky monitoring task into multiple segments by deploying a distributed network of sky imagers at different locations. Each imager captures a specific portion of the sky, and the system processes these segmented views to create a comprehensive occlusion forecast, improving prediction accuracy through spatial distribution while managing complexity through modular segmentation

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent combines data from multiple sky imagers into a unified 3D occlusion model. By merging individual sky views, cloud trajectory data, and volumetric information into a single comprehensive forecast system, the patent achieves improved prediction accuracy while consolidating complexity into a centralized processing framework

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If cloud occlusion is detected earlier, then solar radiation prediction accuracy is improved, but response time requirements increase

Engineering Contradiction:
Improveocclusion detection accuracyVSAvoidforecast lead time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary analysis of sky images to detect and track clouds before they reach the solar collector. By identifying occluding objects early in their trajectory and predicting their future positions, the system provides advance warning of solar irradiance changes, improving prediction accuracy while managing time loss through proactive detection

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent accelerates the detection and processing of cloud movements by using high-frame-rate sky imaging and rapid 3D reconstruction algorithms. This allows the system to skip through multiple potential occlusion scenarios quickly, providing timely predictions without excessive lead time requirements

Inventive Principle:
Principle #21Skipping (Rushing through)

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

This approach enhances the accuracy of solar radiation prediction, allowing for timely adjustments in solar power system operations and electrical grid management, improving stability and reliability by predicting future shading events and optimizing energy storage and consumption.

Implementation Method 1

A distributed network of digital cameras with wide-angle or fisheye lenses captures sky images

Methodology Applied
Scientific EffectElectromagnetic radiation detection: Photoelectric Effect

Implementation Method 2

computing a light path between the POI and a location of the sun based on the sun location parameters; determining if the one or more objects modelled in the 3D sky model occludes the light path

Methodology Applied
Scientific EffectLight propagation: Light

Data Source

PatentEP3455657B1"solar power forecasting"
Publication Date: 2024.12.11 COMMONWEALTH SCI & IND RES ORG
  • EP3455657B1 patent drawingFigure 1a~1b
  • EP3455657B1 patent drawingFigure 2~3
  • EP3455657B1 patent drawingFigure 4

AI summary

A method for determining a level of solar radiation at a point of interest (POI). Multiple sky images are captured by a distributed network of digital cameras. Sun location parameters are determined. A three-dimensional (3D) sky model is generated based on the sky images. Generating the 3D sky model includes generating 3D object data based on the sky images to model one or more objects in a region of sky, and generating position data to model a position of the one or more objects in the region of sky. A level of solar radiation at the POI is determined based on the position data and 3D object data of the 3D sky model and the sun location parameters.