Convolutional Neural Networks applied to sky images for short-term solar irradiance forecasting

TL;DR

This paper explores the use of deep Convolutional Neural Networks to improve short-term solar irradiance forecasting by analyzing sky images and past data, achieving around 10% better accuracy over baseline models.

Contribution

It demonstrates the application of CNNs to sky images for irradiance prediction and shows that incorporating same-day past data enhances forecast accuracy.

Findings

CNN models achieved around 10% error reduction over baseline.

Visualisation techniques reveal patterns recognized by neural networks.

Including past same-day data improves short-term forecast accuracy.

Abstract

Despite the advances in the field of solar energy, improvements of solar forecasting techniques, addressing the intermittent electricity production, remain essential for securing its future integration into a wider energy supply. A promising approach to anticipate irradiance changes consists of modeling the cloud cover dynamics from ground taken or satellite images. This work presents preliminary results on the application of deep Convolutional Neural Networks for 2 to 20 min irradiance forecasting using hemispherical sky images and exogenous variables. We evaluate the models on a set of irradiance measurements and corresponding sky images collected in Palaiseau (France) over 8 months with a temporal resolution of 2 min. To outline the learning of neural networks in the context of short-term irradiance forecasting, we implemented visualisation techniques revealing the types of patterns recognised by trained algorithms in sky images. In addition, we show that training models with past samples of the same day improves their forecast skill, relative to the smart persistence model based on the Mean Square Error, by around 10% on a 10 min ahead prediction. These results emphasise the benefit of integrating previous same-day data in short-term forecasting. This, in turn, can be achieved through model fine tuning or using recurrent units to facilitate the extraction of relevant temporal features from past data.