Jump to main content
Jump to site search


Solar PV output prediction from video streams using convolutional neural networks

Abstract

Solar photovoltaic (PV) installation is growing rapidly across the world, but the variability of solar power hinders its further penetration into the power grid. Part of the short-term variability stems from sudden changes in meteorological conditions, i.e., change in cloud coverage, which can vary PV output significantly in time scales of minutes. Images of the sky provide information on current and future cloud coverage, and are potentially useful in inferring PV generation. This work uses convolutional neural networks (CNN) to correlate PV output to contemporaneous images of the sky (a ''now-cast''). The CNN achieves test-set relative-root-mean-squre error (rRMSE) of 26.0% to 30.2% when applied to power outputs from two solar PV systems. We explore the sensitivity of model accuracy to a variety of CNN structures, with different width, depth, and input image resolution among other hyper-parameters. This success at ''now-cast'' prediction points to possible future uses for short-term forecast.

Back to tab navigation

Publication details

The article was received on 01 Dec 2017, accepted on 09 Apr 2018 and first published on 20 Apr 2018


Article type: Paper
DOI: 10.1039/C7EE03420B
Citation: Energy Environ. Sci., 2018, Accepted Manuscript
  •   Request permissions

    Solar PV output prediction from video streams using convolutional neural networks

    Y. Sun, G. Szucs and A. R. Brandt, Energy Environ. Sci., 2018, Accepted Manuscript , DOI: 10.1039/C7EE03420B

Search articles by author

Spotlight

Advertisements