Our products

pave the way for renewables

Precise intraday, day-ahead, and long-term forecasts

Accurate power and yield forecasts for wind energy and photovoltaic plants

We use a self-learning algorithm to produce power and yield forecasts for wind energy and photovoltaic plants, giving you a realistic idea of how much energy your wind or solar park will produce on a particular day (intraday), the following day (day-ahead), or over a longer period (long-term). We offer these forecasts as part of customized service packages that are tailored to your needs.

Our strategy

Supported by our machine learning models, we produce power and yield forecasts on the basis of weather data as well as historical and current production data. Our calculations incorporate meteorological parameters such as atmospheric pressure, temperature, solar irradiance, clouds, and wind speed and direction from different heights. Micro factors such as topography, icing, and other effects that have an impact on a park are also taken into account to make the forecasts more precise. By regularly retraining the machine learning models, the forecasts are continuously optimized. Our forecasts can be customized to meet the specific requirements of our customers. We offer forecasts for various timeframes, including intraday, day-ahead, and long-term predictions. Additionally, our forecasts are designed to serve different application purposes, such as construction, maintenance, or trade optimization.

Better forecasts pay off – a calculation example

Better forecasts pay off – a calculation example If the forecasted electricity yield deviates from the actual production, transmission system operators impose a balancing energy price. By optimizing the forecasts, even by a small margin, significant savings of thousands of euros can be achieved. This optimization leads to increased reliability of day-ahead contracts and improved revenue planning for plant operators.

Beispielgrafik Solarenergievorhersage

Your benefits

  • Optimal calculation of the production quantity and yields
  • Higher yields by incorporating relevant market data
  • Improved data basis for securing grid stability
  • Avoidance of contractual penalties by accurately reporting the feed-in of electricity
  • Identification of ideal time windows for plant maintenance
  • Optimized plant operation

Day-ahead and long-term forecasts

Our day-ahead and long-term forecasts are calculated using gradient boosting models trained on historical weather data and your production data. We deliver these forecasts every morning for the next day(s). They start at 00:00 the following day with a temporal resolution of 15 minutes and can cover up to four days.
If you order a time period of more than 24 hours in succession, you’ll receive multiple forecasts for the same time due to overlapping in the forecast windows. In this case, we recommend using the most up-to-date forecasts. On request, we can also overwrite the outdated forecasts if the data transmission method you have agreed on with us allows this.

Intraday forecasts

To calculate our short-term intraday forecasts, we train a neural network using historical weather and production data and also stream current live data into our system to deliver continuous intraday predictions.

So that we can retrieve your live data and feed it into our forecasts, you need to conclude a binding agreement with us. In general, all conventional data transmission methods are possible. If you ever want to change how your data is transmitted, we ask you to give us one week’s notice so that we can reconfigure our system. On request, the connection can also be encrypted to ensure secure transmission.

Modules for complete flexibility in yield forecasting

Forecast modules

The power curve of your wind energy plant is adjusted according to the air density and is combined with the weather forecast to predict yields. We also have the right solution for your solar plant.

The machine learning model is trained using historical production data and weather predictions to apply the learned patterns to current weather predictions and thus produce yield forecasts.

We use live production data to optimize yield forecasts for short time windows, as used for trading on the electricity exchange market.

Optimization modules

We monitor the output of your wind or solar plants to identify influencing factors and refine the forecasts.

The machine learning model is retrained using new production data.


How does your machine learning work?

We use machine learning to identify patterns and correlations in various datasets. After training the model, these patterns are applied to the unknown datasets to produce the forecasts. We’d be happy to provide more details.

Where do you get your weather data?

Our production forecasts are based on numerical weather predictions (NWPs) from a range of providers. We consider and process a combination of these NWPs on a case-by-case basis.

Can a contract be enhanced during an existing term?

We’re your partner for any concern or request you have. Please reach out to us and we’ll be sure to find a solution together.

Can newly built turbines be integrated into an existing contract?

Yes, existing contracts can be expanded.

How do I communicate with your team?

You’ll be assigned a dedicated contact person who will be on hand to answer all your questions.

Our experts are here for you

Simply get in touch