Stanford Digital Repository

2017-2019 Sky Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting (Stanford Benchmark)

Placeholder Show Content

Abstract/Contents

Abstract
Large-scale integration of photovoltaics (PV) into electricity grids is challenged by the intermittent nature of solar power. Sky image-based solar forecasting has been recognized as a promising approach to predicting the short-term fluctuations. Here, we present a curated dataset from Stanford University in a format ready-to-use for deep-learning- based solar forecasting research and applications. The dataset consists of 3 years (2017-2019) of processed down-sampled sky images (64x64) taken by a ground-based fish-eye camera and power output measurements from a 30-kW rooftop PV array approximately 125 meters away from the camera at Stanford Campus, both of which are logged in 1-min frequency. More details of the dataset can be found in our dataset GitHub repository with link shown in the “Related link” elsewhere on this page. We hope that the dataset will facilitate the research of image-based solar forecasting using deep learning and contribute to a standardized benchmark for evaluating and comparing different solar forecasting models. We also encourage the users to explore on other related areas with this dataset, such as cloud classification, cloud image segmentation and cloud movement forecasting. High resolution raw data from 2017 to 2019 are also available. See links to related items elsewhere on this page.

Description

Type of resource mixed material, Dataset, still image
Date modified July 1, 2022; July 2, 2022; December 5, 2022
Publication date June 22, 2022

Creators/Contributors

Author Nie, Yuhao
Author Li, Xiatong
Author Scott, Andea
Contributor Sun, Yuchi
Contributor Venugopal, Vignesh
Research team head Brandt, Adam

Subjects

Subject Solar forecasting
Subject PV output prediction
Subject Fish-eye camera
Subject Sky images
Subject Deep learning
Subject Machine learning
Subject Computer vision
Genre Mixed materials
Genre Data
Genre Image
Genre Data sets
Genre Dataset

Bibliographic information

Related item
Title
SUNSET Model GitHub Repo
Title
Stanford University Sky Images and PV Power Generation Dataset GitHub Repo
Title
2017 Sky Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting (Stanford Raw)
Title
2018 Sky Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting (Stanford Raw)
Title
2019 Sky Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting (Stanford Raw)
Preferred citation
Sun, Y., Szűcs, G., Brandt, A.R., 2018. Solar PV output prediction from video streams using convolutional neural networks. Energy Environ. Sci. 11, 1811–1818. https://doi.org/10.1039/C7EE03420B
Preferred citation
Sun, Y., Venugopal, V., Brandt, A.R., 2019. Short-term solar power forecast with deep learning: Exploring optimal input and output configuration. Sol. Energy 188, 730–741. https://doi.org/10.1016/j.solener.2019.06.041
Preferred citation
Venugopal, V., Sun, Y., Brandt, A.R., 2019. Short-term solar PV forecasting using computer vision: The search for optimal CNN architectures for incorporating sky images and PV generation history. J. Renew. Sustain. Energy 11, 066102. https://doi.org/10.1063/1.5122796
Preferred citation
Sun, Y., 2019. Short-term Solar Forecast Using Convolutional Neural Networks with Sky Images. Stanford University.Venugopal, V., 2019. Search for Optimal CNN Architectures Incorporating Heterogeneous Inputs for Short- term Solar PV Forecasting. Stanford University.
Preferred citation
Nie, Y., Sun, Y., Chen, Y., Orsini, R., Brandt, A., 2020. PV power output prediction from sky images using convolutional neural network: The comparison of sky-condition-specific sub-models and an end-to-end model. J. Renew. Sustain. Energy 12, 046101. https://doi.org/10.1063/5.0014016
Preferred citation
Nie, Y., Zamzam, A.S., Brandt, A., 2021. Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks. Sol. Energy 224, 341–354. https://doi.org/10.1016/j.solener.2021.05.095
DOI https://doi.org/10.25740/dj417rh1007
Location https://purl.stanford.edu/dj417rh1007

Access conditions

Use and reproduction
User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
License
This work is licensed under a Creative Commons Attribution 4.0 International license (CC BY).

Preferred citation

Nie, Y., Li, X., Scott, A., Sun, Y., Venugopal, V., and Brandt, A. (2022). 2017-2019 Sky Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting (Stanford Benchmark). Stanford Digital Repository. Available at https://purl.stanford.edu/dj417rh1007

Collection

Stanford Research Data

View other items in this collection in SearchWorks

Contact information

abrandt@stanford.edu

Also listed in

View in SearchWorks

Loading usage metrics...