3D cloud detection and tracking system for solar forecast using multiple sky imagers
Abstract
We propose a system for forecasting short-term solar irradiance based on multiple total sky imagers (TSIs). The system utilizes a novel method of identifying and tracking clouds in three-dimensional space and an innovative pipeline for forecasting surface solar irradiance based on the image features of clouds. First, we develop a supervised classifier to detect clouds at the pixel level and output cloud mask. In the next step, we design intelligent algorithms to estimate the block-wise base height and motion of each cloud layer based on images from multiple TSIs. Thus, this information is then applied to stitch images together into larger views, which are then used for solar forecasting. We examine the system’s ability to track clouds under various cloud conditions and investigate different irradiance forecast models at various sites. We confirm that this system can 1) robustly detect clouds and track layers, and 2) extract the significant global and local features for obtaining stable irradiance forecasts with short forecast horizons from the obtained images. Finally, we vet our forecasting system at the 32-megawatt Long Island Solar Farm (LISF). Compared with the persistent model, our system achieves at least a 26% improvement for all irradiance forecasts between one and fifteenmore »
- Authors:
-
- Stony Brook Univ., Stony Brook, NY (United States); Brookhaven National Lab. (BNL), Upton, NY (United States)
- Brookhaven National Lab. (BNL), Upton, NY (United States)
- Publication Date:
- Research Org.:
- Brookhaven National Laboratory (BNL), Upton, NY (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (SC-21); USDOE
- OSTI Identifier:
- 1193237
- Alternate Identifier(s):
- OSTI ID: 1245220
- Report Number(s):
- BNL-108159-2015-JA
Journal ID: ISSN 0038-092X
- Grant/Contract Number:
- SC00112704; AC02-98CH10886
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Solar Energy
- Additional Journal Information:
- Journal Volume: 118; Journal Issue: C; Journal ID: ISSN 0038-092X
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; sky imagery; cloud detecting; cloud tracking; short-term forecast
Citation Formats
Peng, Zhenzhou, Yu, Dantong, Huang, Dong, Heiser, John, Yoo, Shinjae, and Kalb, Paul. 3D cloud detection and tracking system for solar forecast using multiple sky imagers. United States: N. p., 2015.
Web. doi:10.1016/j.solener.2015.05.037.
Peng, Zhenzhou, Yu, Dantong, Huang, Dong, Heiser, John, Yoo, Shinjae, & Kalb, Paul. 3D cloud detection and tracking system for solar forecast using multiple sky imagers. United States. https://doi.org/10.1016/j.solener.2015.05.037
Peng, Zhenzhou, Yu, Dantong, Huang, Dong, Heiser, John, Yoo, Shinjae, and Kalb, Paul. Tue .
"3D cloud detection and tracking system for solar forecast using multiple sky imagers". United States. https://doi.org/10.1016/j.solener.2015.05.037. https://www.osti.gov/servlets/purl/1193237.
@article{osti_1193237,
title = {3D cloud detection and tracking system for solar forecast using multiple sky imagers},
author = {Peng, Zhenzhou and Yu, Dantong and Huang, Dong and Heiser, John and Yoo, Shinjae and Kalb, Paul},
abstractNote = {We propose a system for forecasting short-term solar irradiance based on multiple total sky imagers (TSIs). The system utilizes a novel method of identifying and tracking clouds in three-dimensional space and an innovative pipeline for forecasting surface solar irradiance based on the image features of clouds. First, we develop a supervised classifier to detect clouds at the pixel level and output cloud mask. In the next step, we design intelligent algorithms to estimate the block-wise base height and motion of each cloud layer based on images from multiple TSIs. Thus, this information is then applied to stitch images together into larger views, which are then used for solar forecasting. We examine the system’s ability to track clouds under various cloud conditions and investigate different irradiance forecast models at various sites. We confirm that this system can 1) robustly detect clouds and track layers, and 2) extract the significant global and local features for obtaining stable irradiance forecasts with short forecast horizons from the obtained images. Finally, we vet our forecasting system at the 32-megawatt Long Island Solar Farm (LISF). Compared with the persistent model, our system achieves at least a 26% improvement for all irradiance forecasts between one and fifteen minutes.},
doi = {10.1016/j.solener.2015.05.037},
journal = {Solar Energy},
number = C,
volume = 118,
place = {United States},
year = {Tue Jun 23 00:00:00 EDT 2015},
month = {Tue Jun 23 00:00:00 EDT 2015}
}
Web of Science
Works referenced in this record:
Cloud motion vectors from a network of ground sensors in a solar power plant
journal, September 2013
- Bosch, J. L.; Kleissl, J.
- Solar Energy, Vol. 95
Comparison of Block Matching and Differential Methods for Motion Analysis of the Carotid Artery Wall From Ultrasound Images
journal, September 2012
- Golemati, S.; Stoitsis, J. S.; Gastounioti, A.
- IEEE Transactions on Information Technology in Biomedicine, Vol. 16, Issue 5
Cloud-tracking methodology for intra-hour DNI forecasting
journal, April 2014
- Quesada-Ruiz, S.; Chu, Y.; Tovar-Pescador, J.
- Solar Energy, Vol. 102
Least squares quantization in PCM
journal, March 1982
- Lloyd, S.
- IEEE Transactions on Information Theory, Vol. 28, Issue 2
A tutorial on support vector regression
journal, August 2004
- Smola, Alex J.; Schölkopf, Bernhard
- Statistics and Computing, Vol. 14, Issue 3
Stereographic methods for cloud base height determination using two sky imagers
journal, September 2014
- Nguyen, Dung (Andu); Kleissl, Jan
- Solar Energy, Vol. 107
Three-Dimensional Motion Estimation of Atmospheric Layers From Image Sequences
journal, August 2008
- Heas, P.; Memin, E.
- IEEE Transactions on Geoscience and Remote Sensing, Vol. 46, Issue 8
A Simple Method for the Assessment of the Cloud Cover State in High-Latitude Regions by a Ground-Based Digital Camera
journal, March 2006
- Souza-Echer, M. P.; Pereira, E. B.; Bins, L. S.
- Journal of Atmospheric and Oceanic Technology, Vol. 23, Issue 3
Retrieving Cloud Characteristics from Ground-Based Daytime Color All-Sky Images
journal, May 2006
- Long, C. N.; Sabburg, J. M.; Calbó, J.
- Journal of Atmospheric and Oceanic Technology, Vol. 23, Issue 5
Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention
journal, December 1993
- Lindeberg, Tony
- International Journal of Computer Vision, Vol. 11, Issue 3
Forecasting of Global Horizontal Irradiance Using Sky Cover Indices
journal, October 2012
- Marquez, Ricardo; Gueorguiev, Vesselin G.; Coimbra, Carlos F. M.
- Journal of Solar Energy Engineering, Vol. 135, Issue 1
Using a Sky Imager for aerosol characterization
journal, April 2008
- Cazorla, A.; Olmo, F.; Aladosarboledas, L.
- Atmospheric Environment, Vol. 42, Issue 11
Cloud detection, classification and motion estimation using geostationary satellite imagery for cloud cover forecast
journal, June 2013
- Escrig, H.; Batlles, F. J.; Alonso, J.
- Energy, Vol. 55
Cloud-Base-Height Estimation from Paired Ground-Based Hemispherical Observations
journal, August 2005
- Kassianov, Evgueni; Long, Charles N.; Christy, Jason
- Journal of Applied Meteorology, Vol. 44, Issue 8
Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type Recognition
journal, January 2008
- Calbó, Josep; Sabburg, Jeff
- Journal of Atmospheric and Oceanic Technology, Vol. 25, Issue 1
A method for cloud detection and opacity classification based on ground based sky imagery
journal, January 2012
- Ghonima, M. S.; Urquhart, B.; Chow, C. W.
- Atmospheric Measurement Techniques, Vol. 5, Issue 11
Solar irradiance forecasting using a ground-based sky imager developed at UC San Diego
journal, May 2014
- Yang, Handa; Kurtz, Ben; Nguyen, Dung
- Solar Energy, Vol. 103
Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed
journal, November 2011
- Chow, Chi Wai; Urquhart, Bryan; Lave, Matthew
- Solar Energy, Vol. 85, Issue 11
The computation of optical flow
journal, September 1995
- Beauchemin, S. S.; Barron, J. L.
- ACM Computing Surveys, Vol. 27, Issue 3
LIBSVM: A library for support vector machines
journal, April 2011
- Chang, Chih-Chung; Lin, Chih-Jen
- ACM Transactions on Intelligent Systems and Technology, Vol. 2, Issue 3
Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning
journal, December 2013
- Chu, Yinghao; Pedro, Hugo T. C.; Coimbra, Carlos F. M.
- Solar Energy, Vol. 98
Automated ground-based cloud recognition
journal, October 2005
- Singh, Maneesha; Glennen, Matt
- Pattern Analysis and Applications, Vol. 8, Issue 3
A Hybrid Thresholding Algorithm for Cloud Detection on Ground-Based Color Images
journal, October 2011
- Li, Qingyong; Lu, Weitao; Yang, Jun
- Journal of Atmospheric and Oceanic Technology, Vol. 28, Issue 10
Cloud detection and classification with the use of whole-sky ground-based images
journal, September 2012
- Kazantzidis, A.; Tzoumanikas, P.; Bais, A. F.
- Atmospheric Research, Vol. 113
Cloud Coverage Based on All-Sky Imaging and Its Impact on Surface Solar Irradiance
journal, October 2003
- Pfister, G.; McKenzie, R. L.; Liley, J. B.
- Journal of Applied Meteorology, Vol. 42, Issue 10
Operational Cloud-Motion Winds from Meteosat Infrared Images
journal, July 1993
- Schmetz, Johannes; Holmlund, Kenneth; Hoffman, Joel
- Journal of Applied Meteorology, Vol. 32, Issue 7
Proposal for a Standard Default Color Space for the Internet—sRGB
journal, January 1996
- Anderson, Matthew; Motta, Ricardo; Chandrasekar, Srinivasan
- Color and Imaging Conference, Vol. 4, Issue 1
Works referencing / citing this record:
A Novel Hybrid Model of WRF and Clearness Index-Based Kalman Filter for Day-Ahead Solar Radiation Forecasting
journal, September 2019
- Che, Yuzhang; Chen, Lewei; Zheng, Jiafeng
- Applied Sciences, Vol. 9, Issue 19
Real-Time Uncertainty Specification of All Sky Imager Derived Irradiance Nowcasts
journal, May 2019
- Nouri, Bijan; Wilbert, Stefan; Kuhn, Pascal
- Remote Sensing, Vol. 11, Issue 9
ELIFAN, an algorithm for the estimation of cloud cover from sky imagers
journal, January 2019
- Lothon, Marie; Barnéoud, Paul; Gabella, Omar
- Atmospheric Measurement Techniques, Vol. 12, Issue 10
Comparison of Implicit vs. Explicit Regime Identification in Machine Learning Methods for Solar Irradiance Prediction
journal, February 2020
- McCandless, Tyler; Dettling, Susan; Haupt, Sue Ellen
- Energies, Vol. 13, Issue 3
ELIFAN, an algorithm for the estimation of cloud cover from sky imagers
posted_content, February 2019
- Lothon, Marie; Barnéoud, Paul; Gabella, Omar
- Atmospheric Measurement Techniques
A 3D multi-threshold, region-growing algorithm for identifying dust storm features from model simulations
journal, November 2016
- Yu, Manzhu; Yang, Chaowei
- International Journal of Geographical Information Science, Vol. 31, Issue 5
Validation of All-Sky Imager Technology and Solar Irradiance Forecasting at Three Locations: NREL, San Antonio, Texas, and the Canary Islands, Spain
journal, February 2019
- Richardson, Walter; Cañadillas, David; Moncada, Ariana
- Applied Sciences, Vol. 9, Issue 4
Automatic Cloud-Type Classification Based On the Combined Use of a Sky Camera and a Ceilometer: Cloud class using ceilometer and camera
journal, October 2017
- Huertas-Tato, J.; Rodríguez-Benítez, F. J.; Arbizu-Barrena, C.
- Journal of Geophysical Research: Atmospheres, Vol. 122, Issue 20