Predico: collaborative forecasting platform

• Balance out bias and overfitting
• Combine information
• Minimize extreme errors
• Are more reliable for the buyer through redundancy, and less demanding for the individual forecasters (no SLAs)

• Reward accurate outside views 
  
• Align remuneration with outcomes through performance-based compensation: 
  
  • Increases competition and innovation 
    
  • Incentivizes continuous improvement 
    
  • Incentivize accuracy 
    
  • Lower overhead costs for everyone.  
    
• Provide larger upside to accurate forecasters than bilateral contracts at a lower cost to buyers 
  
• Are able to adapt dynamically to changing circumstances, e.g. energy market dynamics for interconnector forecasts 
  
• Enable scale diversity. Small and large providers compete equally 

• For Buyers: Create a market or participate in an existing one to receive skill-weighted aggregate market forecasts.
  
• For Forecasters: Submit forecasts to the market and be remunerated.  Non-commercial forecasters may also participate. 

If you are a forecast buyer interested in participating in a market, contact predico@elia.be. For the moment, Predico is at proof-of-concept stage, meaning that participants cannot create markets independently.

If you are a forecaster interested in participating in a market, you can register by contacting us on predico@elia.be. After registering, you will be able to submit forecasts via an HTTP request. The API documentation can be found at Predico REST API (inesctec.pt). There is also a Python client which simplifies the interaction with the platform.

• The historical values are available on Predico or Elia's Open Data Portal here 
• The near-real time values are available on Elia's Open Data Portal here 
• Wind turbines are unavailable sometimes. The schedules can be found here and here  
• Note that on 22/05/2024 the data format for the above links changed: older data are also available on the portal. 
• Wind generation seems less correlated with system imbalance than solar. This means that the wind turbine operators don't react to imbalance markets as much (although the BRPs might have wind and solar in their portfolios and co-optimize). But in general this is a good thing for wind generation forecasting. But do be aware of the balancing market and how that affects operations. 
• Bear in mind that above a certain wind speed, the turbines cut out as a safety measure. How this is done depends on the wind farm operator but is important for wind generation. 
• Wind gusts or gustiness are often useful to include as a feature.