AUTHORS:
Michela Moschella, Alessandro Betti, Emanuele Crisostomi and Mauro Tucci.
ABSTRACT:
The increasing penetration level of energy generation from renewable sources is demanding for more accurate and reliable forecasting tools to support classic power grid operations (e.g., unit commitment, electricity market clearing or maintenance planning). For this purpose, many physical models have been employed, and more recently many statistical or machine learning algorithms, and data-driven methods in general, are becoming subject of intense research. While generally the power research community focuses on power forecasting at the level of single plants, in a short future horizon of time, in this time we are interested in aggregated macro-area power generation (i.e., in a territory of size greater than 100000 km2) with a future horizon of interest up to 15 days ahead. Real data are used to validate the proposed forecasting methodology on a test set of several months.
Solar Asset Manager
A Decision Support System based on Earth observation exploitation for renewable energy plants management
AUTHORS:
Andrea Masini, Ciro Lanzetta, Giuseppe Leotta, Gian Lorenzo Giuliattini Burbui, Pasquale Guerrisi and Maria Luisa Lo Trovato.
ABSTRACT:
Nowadays remote sensing information can be exploited to support the management of renewable energy plants during all its life cycles. Earth observation satellite can provide a continuous monitoring of each location of the earth. Low-resolution and high-resolution imagery can be exploited to obtain accurate descriptions of the monitored scenarios/plants. Moreover, the use of unmanned air vehicle can provide complementary information to monitor important features not detectable with satellite sensors. i-EM and Flyby developed and tested a system, called 4D-REDSS (4D Renewable plants Decision Support System) aimed to exploit remote sensed data to advantage and support the management of solar plant during the construction and pre-commissioning phase.
Photovoltaic power forecasting with ensemble of learners: large test case from PV plants in Italy, Zambia and Australia
AUTHORS:
Lorenzo Gigoni, Alessandro Betti, Fabrizio Ruffini, Ciro Lanzetta, Antonio Piazzi, Mauro Tucci e Michela Moschella.
ABSTRACT:
An innovative ensamble-based forecasting method based on a number of machine learning techniques independently trained and combined in a cooperative ensemble fashion.