European harmonisation of electricity markets is advancing for Day-Ahead Markets, but it is still far from being achieved in the case of Balancing Markets.

Therefore, one of the first steps of this project will be to analyse the different European markets and their opportunities for the participation of wind power producers.

The main objective is to develop a framework that proposes combined strategies for the day-ahead and balancing markets bidding of a wind farm or a fleet analysing aggregation approaches of farms dispersed spatially and with different turbine technologies.

This project will combine all the available data from wind farms and markets with machine learning and probabilistic techniques considering turbine control features, wind power, and market price forecasting to maximise benefits and reduce risks.

The fellow will be trained on the use of machine learning techniques in order to obtain and develop research and industrial results.

Research results will include the analysis of European markets, especially balancing markets and provision of the different types of reserve (frequency- controlled reserve, automatic-activated frequency restoration reserve and/or manually activated frequency restoration reserve) by wind power plants depending on their control capabilities.

As an industrial result, the developed framework will help in decision taking to provide coordinated strategies covering day-ahead and balancing market offers.

Academic secondment at TUM (Prof. Carlo Bottasso M24-M26) working on the benefits of smart farm control for participating in secondary and day-ahead market offers. Industrial secondment at CETASA (J. Gracia M35-M37), to test results in real situations.