SteadyEye 

Solar forecasts for the next minutes 

ABOUT

Forecasts based on real-time all sky images for intrahour solar forecasting needs 

SteadyEye provides advanced solar irradiance and production forecasts up to 30 minutes ahead. This unique nowcasting product combines on-site sky imagery processing with weather forecast, physical models and artificial intelligence. The product is designed to anticipate solar power ramp events and to guarantee PV production.

SteadyEye solution is tailored for industrial applications such as hybrid energy systems and storage control (i.e. PV-diesel-battery), utility scale PV and CSP plants operations as well as grid management.

Sky and weather conditions above solar power plants are continuously monitored using SW-X all sky imager(s) and predicted locally, improving the accuracy of solar forecasts for the next minutes and anticipating the risks of variability.

Sky imager coverage

Intrahour GHI forecast for 1 site (France) 

Intrahour power forecast for a 3.2MWp PV-Diesel plant (Australia) 

Sky imager-based cloud forecast above one site in France

30 min 

Max time horizon  

1440 times a day 

Update frequency  

1 min 

Forecast time-step  

Power, GHI, DNI, DHI, GTI, Temperature 

Available parameters  

Site, Portfolio 

Coverage  

PV, Trackers, Bifacial, CSP 

Technology

API, SFTP or Modbus 

Data Delivery  

P10, P20,… , P80, P90 

Confidence levels  

KEY BENEFITS

OPTIMIZE PV POWER RAMP MANAGEMENT 

Thanks to 1 minute forecast update frequency. 

REDUCE HYBRID PLANT OPERATION COSTS 

By increasing the use of solar energy. 

FACILITATE BALANCING OF POWER GRIDS 

And manage spinning reserves.  

IMPROVE OFF-GRID ENERGY SYSTEM OPERATION 

By fostering balancing of the system.  

CUSTOMERS NEEDS  

Particularly suitable for insular networks and hybrid systems. It favors real time management and decision making in order to optimize the alternative energy production methods to implement

METHODOLOGY

Local cloud information is acquired by one or several ground-based sky imager at a high frequency (up to 15 seconds) (step 1). The combination of these images and local weather measurement information are processed to simulate cloud motion vectors and optical depth to obtain forecasts up to 30 minutes ahead (step 2).

Forecasts are then optimized (step 3), by using production/irradiance observations, to take into account local phenomena, and by leveraging artificial intelligence technologies.

Ready-to-use forecasts, in a customized format, are then disseminated (step 4) through our proprietary web interface, csv files delivered via (S)FTP platforms or API. 

Step 1

DATA ACQUISITION

From Steadysun SW-X series sky imager(s).

Visible images and atmospheric measurements.

Every 30 seconds.

Step 2

MODELING 

Cloud detection, classification and motion prediction.

Accurate estimation of clear sky conditions using real-time aerosols prediction.

Calculation of direct and diffuse irradiance components in cloudy conditions.

PV modeling based on physical models and plant features.

Probabilistic forecasting using physical and statistical approaches.

Step 3

OPTIMIZATION 

Based on historical and/or real-time on-site measurements.

Continuous accuracy improvements using state-of-the-art machine learning techniques.

To take into account local weather phenomena and power plants’ behavior.

Step 4

DELIVERY 

Flexible sending (API, SFTP, etc..).

Customized format (csv, txt, etc.).

Dedicated and secured Steadysun’s web interfaces (visualization, data analytics and warnings).

Forecast performance monitoring.

HYBRID SYSTEMS & STORAGE

Microgrid studies, solar and wind forecasts to optimize the sizing and the management of hybrids systems (PV/Wind/Storage/Genset).

GRID MANAGEMENT

Solar and wind forecasts to reduce spinning reserve, and avoid grid instability.

INSULAR SYSTEM MANAGEMENT

Studies to anticipate the meteorological impact on the grid during transition to renewable energies, solar and wind forecasts to reduce spinning reserve, and avoid grid instability.

PLANT OPERATIONS

Products and services for solar plant operators allowing you to maximize the profitability of your plants.

MICROGRIDS

Solar, Wind and Load forecast to define the best control strategy and maximize self-consumption.

METHODOLOGY  

Local cloud information is acquired by one or several ground-based sky imager at a high frequency (up to 15 seconds) (step 1). The combination of these images and local weather measurement information are processed to simulate cloud motion vectors and optical depth to obtain forecasts up to 30 minutes ahead (step 2).

Forecasts are then optimized (step 3), by using production/irradiance observations, to take into account local phenomena, and by leveraging artificial intelligence technologies.

Ready-to-use forecasts, in a customized format, are then disseminated (step 4) through our proprietary web interface, csv files delivered via (S)FTP platforms or API. 

Step 1

Step 2

Step 3

Step 4

DATA ACQUISITION 

MODELING 

OPTIMIZATION 

DELIVERY 

From Steadysun SW-X series sky imager(s).

Visible images and atmospheric measurements.

Every 30 seconds.

Cloud detection, classification and motion prediction.

Accurate estimation of clear sky conditions using real-time aerosols prediction.

Calculation of direct and diffuse irradiance components in cloudy conditions.

PV modeling based on physical models and plant features.

Probabilistic forecasting using physical and statistical approaches.

Based on historical and/or real-time on-site measurements.

Continuous accuracy improvements using state-of-the-art machine learning techniques.

To take into account local weather phenomena and power plants’ behavior.

Flexible sending (API, SFTP, etc..).

Customized format (csv, txt, etc.).

Dedicated and secured Steadysun’s web interfaces (visualization, data analytics and warnings).

Forecast performance monitoring.

Benefit from a presentation of our products & services and discover how they can help you.  

OUR PRODUCTS AND SERVICES  

Solar forecasts for the coming days, based on meteorological models. Avoid penalties. Plan and decrease spinning reserve. Sell energy at best price.  

Solar forecasts for the coming hours, based on satellite imagery, dedicated to avoiding penalties, planify and decrease spinning reserve and sell energy at better prices.  

Electricity load forecast for the coming hours and days, based on deep learning technologies.   

A range of customized studies to help fostering renewable energies into the grid and maximize profitability of renewable energy assets  

FOLLOW US