New article on the journal Energies

Members of the Clim2power consortium have published a new article on the journal Energies. The paper, which is part of the special issue Modelling of Variable Renewable Generation: Wind and Solar Photovoltaic Power Plant, assessed how time series generated by machine learning models (MLMs) compare to models (RN) in terms of their ability to replicate the characteristics of observed nationally aggregated wind power generation for Germany. The authors demonstrated that MLM models show a similar performance to RN, even when information on turbine locations and turbine types is unavailable.

Title: Less Information, Similar Performance: Comparing Machine Learning-Based Time Series of Wind Power Generation of

Authors: Johann Baumgartner, Katharina Gruber, Sofia G. Simoes, Yves-Marie Saint-Drenan and Johannes Schmidt

Scatterplot of modelled generation time series compared with observations ( time series abbreviated as RN and machine learning model time series abbreviated as MLM1 and MLM2 versus observations on the X-axis)