Title:	Deep Learning Methods for Solar Power Plants Nowcasting: Systems for Grid-stability and Energy Market Operations
Author(s):	J. Baldacci, C. Lanzetta, A. Piazzi, F. Ruffini
Keywords:	Software, Grid Integration, Grid Management, Grid Stability, Photovoltaic
Topic:	PV Systems Engineering, Integrated/Applied PV
Subtopic:	Solar Resource and Forecasting
Event:	8th World Conference on Photovoltaic Energy Conversion
Session:	4BV.4.9
ISBN:	3-936338-86-8
Price:	0,00 EUR
Document(s):	poster

Abstract/Summary:

---

This document describes the results of a novel deep machine learning system able to perform a short term prediction of the power produced by photovoltaic plants with the goal of supporting the intraday energy market. This topic is currently being assessed both by operational systems, which are available to the customers, and by academics’ activities. In general, we found a few works using deep learning techniques. More traditional research areas uses satellite-based data, such as Cloud Motion Vector techniques often combined with Numerical Weather Predictions.