The need to have a tool able to foresee with a good accuracy the level of solar irradiation on the ground is linked to the need of balancing power on the electricity grids by the energy managers. In particular, energy authorities require each energy producer to provide every day an estimate of the amount of energy that will be produced. In a free energy market context, a possible imbalance between declared energy and energy actually produced can create serious problems for producers.
The managing body of the network will ask the producer to pay for the purchase of the energy that has not been produced, but at the same time it will not pay the surplus of energy if not necessary for the balancing of the network. From this, we can see the importance of a short-term forecasting system for the energy production. While this estimate can easily be obtained for non-renewable sources, on the other side it becomes extremely difficult for unstable sources such as wind and photovoltaics.
The Sol-Invictus startup offers an innovative forecasting system based on the synergistic use of meteorological satellite images and deep learning algorithms.