ABOUT
SteadyMet provides weather and production forecasts up to 15 days ahead. This product combines several sources of Numerical Weather Predictions (NWP) data with physical models and artificial intelligence.
SteadyMet can be configured at very high resolution (1 km) using the Weather Research and Forecasting (WRF) model, providing highly accurate forecasts at local scale. Steadysun is able to implement and optimize this model anywhere in the world to meet the need of high-quality day-ahead forecasts.
Up to 1 hour
Update frequency
1 min
Forecast time-step
Power, GHI, DNI, DHI, GTI, Temperature, Wind Speed, Wind Direction, etc.
Available parameters
Site, Portfolio, City, Region or Country
Coverage
PV, CSP, onshore, offshore
Technology
API, SFTP, etc.
Data delivery
P10, P20,…, P80, P90
Confidence levels
KEY BENEFITS
Thanks to a large number of global and regional NWP data from several weather operators.
An approach combining ensemble predictions from the leading weather models, real-time on-site measurements and cutting-edge technologies to offer accurate probabilistic forecasts.
An in-house regional model at very high spatio-temporel resolution, providing realistic and precise forecasts in areas where local effects are significant and public regional weather models are not available.
In terms of weather parameters, update frequency, granularity and format.
METHODOLOGY
Step 1
DATA ACQUISITION
From several external and internal sources
Global and Regional Numerical Weather Prediction (NWP) models
Numerous parameters (clouds, radiation, wind speed/direction, temperature, aerosols, etc.)
Step 2
MODELING
Optimal combination of NWP models’ outputs
Power modeling based on physical models and plant features
High-resolution topographical corrections (down to 90m)
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 web interfaces (visualization, data analytics and warnings)
Forecast performance monitoring
From several external and internal sources
Global and Regional Numerical Weather Prediction (NWP) models
Numerous parameters (clouds, radiation, wind speed/direction, temperature, aerosols, etc.)
Optimal combination of NWP models’ outputs
Power modeling based on physical models and plant features
High-resolution topographical corrections (down to 90m)
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 web interfaces (visualization, data analytics and warnings)
Forecast performance monitoring
OTHER PRODUCTS AND SERVICES
Reduce penalties & optimize storage management
Manage spinning reserve in real time
Sell electricity at the best price on intraday markets
Anticipate intra-hour variations of production
Minimize and manage spinning reserves in real time
Reduce genset consumption and increase their lifetime
Assessment of gains brought by forecasting
Solar resource and yield assessment
Sizing and control of hybrid systems
Development of grid codes