CALIBSUN Dropdown Services Dropdown NEXT: Solar & power forecast Dropdown NEXT : Algorithm technology

NEXT : Algorithm technology

Image Image

 

A Machine Learning Algorithm

 

K-NN Method

NEXT utilizes an ensemble statistical learning methodology developed in-house.

The NEXT algorithm is based on an ensemble statistical learning methodology of the k-nearest neighbors (kNN) type.

The NEXT algorithm combines several complementary input data sources relevant to different spatial and temporal scales (NWP, satellite, in-situ measurements). It searches for similar patterns to the current meteorological situation in the data history, using an advanced method of estimating similarity between two meteorological situations developed in-house.

The algorithm aims to push the limits of the state-of-the-art by taking not only the raw data from different sources but also the transformed data using standard models usually offered as such on the market.

Thus, NEXT natively takes a combination of several weather models as input, as well as irradiance map forecasts from satellite imagery combined with robust and proven forecasting techniques such as Cloud Motion Vector (CMV).

 

 

An algorithm capable of making direct production forecasts.

NEXT can make forecasts of horizontal or tilted irradiance, as well as direct production data.

NEXT Advanced, its most powerful version, integrates real-time site measurements. These measurements are utilized by the algorithm, allowing constantly updated forecasts based on the latest observations.

All of this enables NEXT Advanced to combine the precision provided by the state-of-the-art single-source data forecast into a unique algorithm capable of assigning relevant weights to its sources for all time horizons in a seamless manner, while being constantly calibrated on the real data collected by on-site sensors.

 

In its standard version, NEXT operates without site data feedback, with performance equivalent to Next Advanced, for medium to long-term horizons.

PROBABILISTIC

Access to prediction quantiles

NEXT generates probabilistic ensemble forecasts from P5 to P95.

The technology used by NEXT works by searching for similarity in the history of the combination of input data. It allows generating probabilistic ensemble forecasts by nature calibrated on the target value to predict.

Indeed, this method identifies a set of moments in history for which the predictors indicated a similar meteorological situation. Consequently, all the uncertainty related to the variability of the observations that can be obtained for the same situation is contained in this set of observations. Thus, it does not simply model the uncertainty related to the error on the parameters of the model as is classically done by bootstrap or ensemble NWP methods but rather the total uncertainty of the model, including that related to model bias.

The algorithm is set to natively provide probabilistic quantiles ranging from P5 to P95 in increments of 5%, very well calibrated on the real quantiles observed in the measurements (or satellite data in the case of the mode without in-situ data).

By using NEXT, an asset manager is guaranteed to have access to reliable prediction quantiles representing the true variability and uncertainty of on-site data, allowing for realistic production scenarios to be constructed.

 

Associated Publications 

Evaluate NEXT's Performance

Take a free trial or request a comprehensive evaluation