气候变化领域集成服务门户(CCPortal): Solar PV output prediction from video streams using convolutional neural networks

CCPortal

DOI	10.1039/c7ee03420b
	Solar PV output prediction from video streams using convolutional neural networks
	Sun Y.; Szucs G.; Brandt A.R.
发表日期	2018
ISSN	17545692
起始页码	1811
结束页码	1818
卷号	11 期号:7
英文摘要	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 over timescales 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-square error values (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 widths, depths, and input image resolutions among other hyper-parameters. This success at "now-cast" prediction points to possible future uses for short-term forecasts. © 2018 The Royal Society of Chemistry.
英文关键词	Convolution; Electric power transmission networks; Forecasting; Image resolution; Mean square error; Neural networks; Photovoltaic cells; Solar energy; Video streaming; Convolutional neural network; Convolutional Neural Networks (CNN); Meteorological condition; Possible futures; Root mean square errors; Short-term forecasts; Solar photovoltaics; Solar PV systems; Solar power generation; accuracy assessment; climate conditions; error analysis; installation; parameterization; photovoltaic system; prediction; smart grid; solar power; videography
语种	英语
来源期刊	Energy & Environmental Science
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/190193
作者单位	Department of Energy Resources Engineering, Stanford UniversityCA, United States; Department of Mathematics, Stanford UniversityCA, United States
推荐引用方式 GB/T 7714	Sun Y.,Szucs G.,Brandt A.R.. Solar PV output prediction from video streams using convolutional neural networks[J],2018,11(7).
APA	Sun Y.,Szucs G.,&Brandt A.R..(2018).Solar PV output prediction from video streams using convolutional neural networks.Energy & Environmental Science,11(7).
MLA	Sun Y.,et al."Solar PV output prediction from video streams using convolutional neural networks".Energy & Environmental Science 11.7(2018).