Insights of the DYDAS Project: The Use Case Energy

In the current energy transition, Renewable Energy Sources are identified as key enablers for the achievement of the ambitious European target of climate neutrality by 2050; among them, solar and wind energy play a crucial role. The evolution of production, storage and end users’ technologies goes hand in hand with the rapid development of the information sector, where High Performance Computing (HPC) infrastructures allow the exploitation of Internet of Things devices and Artificial Intelligence techniques. The use of HPCs in the energy field enables the use, processing and sharing of large volumes of energy data. The funded by the CEF TELECOM 2018 DYDAS (Dynamic Data Analytics Services) Project is carried out in the above-mentioned framework, aiming to create a collaborative platform, called DYDAS, that, using high-performing computers, will offer data, algorithms and data analysis services to a wide range of final users, both private and public. More specifically the paper will focus on the Use Case Energy, whose objective is to test and validate the DYDAS platform, by exploiting meteorological forecast techniques and using satellite information to facilitate and boost up the assessment of both energy demand and power production. Considering the strong dependency on resource availability, the localization of the resources and the related infrastructure is essential for an efficient and strategic energy planning. Therefore, the mix of traditional algorithms, climatic variables and remote sensing techniques represents an added value for supporting decision-makers in the energy planning processes at local and national scales, taking advantage of the geomatics instruments to visualize and monitor decision strategies. Given the role of electricity in the energy transition, the current paper deepens the Use Case Energy focusing on power generation from photovoltaic plants and on-shore and off-shore wind farms located in Italy. The aim of the use case is to estimate the potential local power production, by collecting information about technical features and geo-localization of real plants, and integrating them with georeferenced climatic variables, which can influence the electricity production (e.g., air temperature, solar irradiance, etc.).