A deep learning model for intra-day forecasting of solar irradiance using satellite-based estimations in the vicinity of a PV power plant.

Citation metadata

From: Solar Energy(Vol. 218)
Publisher: Elsevier Science Publishers
Document Type: Report; Brief article
Length: 254 words

Document controls

Main content

Abstract :

Keywords Irradiance forecasting; Deep learning; Neural networks; Satellite data Highlights * Satellite-based irradiance estimations in the vicinity as main input for the model. * State-of-the-art performance even when no irradiance measurements are available. * Model without real data outperforms ECMWF forecast for the studied location. * Operational 6-h forecasts which can be updated every 15 min. Abstract This work proposes an intra-day forecasting model, which does not require to be trained or fed with real-time data measurements, for global horizontal irradiance (GHI) at a given location. The proposed model uses a series of time-dependant irradiance estimates near the target location as the main input. These estimates are derived from satellite images and are combined with other secondary inputs in an advanced neural network, which features convolutional and dense layers and is trained using a deep learning approach. For the various input combinations, the performance of the model is validated with a quantitative analysis on the forecast accuracy using different error metrics. Accuracies are compared with a commercial solution for irradiance forecasting made by the European Centre for Medium-Range Weather Forecasts (ECMWF) and publications with similar approaches and forecasting horizons, showing state-of-the-art performance even without irradiance measurements. Author Affiliation: (a) Department of Industrial Systems Engineering and Design, Universitat Jaume I, Castelló de la Plana, Spain (b) Instituto Tecnológico de Informática (ITI), Universidad Politécnica de Valencia, Valencia, Spain Article History: Received 29 October 2020; Revised 21 January 2021; Accepted 10 February 2021 Byline: Emilio Pérez [pereze@uji.es] (a), Javier Pérez (b), Jorge Segarra-Tamarit (a), Hector Beltran (a)

Source Citation

Source Citation   

Gale Document Number: GALE|A657002940