KloudNet: Deep Learning for Sky Image Analysis and Irradiance Forecasting

• Published in: Pattern Recognition pp. 535 - 551
• Main Authors: Pothineni, Dinesh, Oswald, Martin R., Poland, Jan, Pollefeys, Marc
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing
• Series: Lecture Notes in Computer Science
• ISBN: 9783030129385; 3030129381
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-12939-2_37

We present a novel image-based approach for estimating irradiance fluctuations from sky images. Our goal is a very short-term prediction of the irradiance state around a photovoltaic power plant 5–10 min ahead of time, in order to adjust alternative energy sources and ensure a stable energy network. To this end, we propose a convolutional neural network with residual building blocks that learns to predict the future irradiance state from a small set of sky images. Our experiments on two large datasets demonstrate that the network abstracts upon local site-specific properties such as day- and month-dependent sun positions, as well as generic properties about moving, creating, dissolving clouds, or seasonal changes. Moreover, our approach significantly outperforms the established baseline and state-of-the-art methods.