Convolutional neural networks for intra-hour solar forecasting based on sky image sequences

Feng, Cong; Zhang, Jie; Zhang, Wenqi; Hodge, Bri-Mathias

doi:10.1016/j.apenergy.2021.118438

Convolutional neural networks for intra-hour solar forecasting based on sky image sequences

Journal Article · Fri Jan 28 23:00:00 EST 2022 · Applied Energy

DOI:https://doi.org/10.1016/j.apenergy.2021.118438· OSTI ID:1845678

^[1]; Zhang, Jie ^[2]; Zhang, Wenqi ^[3]; ^[4]

National Renewable Energy Lab. (NREL), Golden, CO (United States); Univ. of Texas at Dallas, TX (United States)
Univ. of Texas at Dallas, TX (United States)
National Renewable Energy Lab. (NREL), Golden, CO (United States)
National Renewable Energy Lab. (NREL), Golden, CO (United States); Univ. of Colorado, Boulder, CO (United States)

Accurate and timely solar forecasts play an increasingly critical role in power systems. Compared to longer forecasting timescales, very short-term solar forecasting has lagged behind in both research and practice. In this paper, we propose deep convolutional neural networks (CNNs) to provide operational intra-hour (10-minute-ahead to 60-minute-ahead) solar forecasts. We develop two CNN structures inspired by a widely-used CNN architecture. The CNNs are tailored to our solar forecasting regression tasks and rely solely on sky image sequences. Case studies based on six years of data (over 150,000 data points) demonstrate that the best CNN model has forecast skill scores of 20%-39% over the naive persistence of cloudiness benchmark, even at these very short timescales. The CNNs also have consistently superior performance when compared to shallow machine learning models with meteorological predictors, where the improvement averages around 7%. The sensitivity analyses show that the sky image length, resolution, and weather conditions have impacts on the deep learning model accuracy. In our intra-hour problem with specific setups, two sky images with a 10-minute 128 x 128 resolution yield the most accurate forecasts. Current limitations, future work, and deployment challenges and solutions are also discussed.

View Accepted Manuscript (DOE)

Research Organization:: National Renewable Energy Laboratory (NREL), Golden, CO (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC36-08GO28308

OSTI ID:: 1845678

Alternate ID(s):: OSTI ID: 1842859

Report Number(s):: NREL/JA--5D00-80681; MainId:77465; UUID:770fbe9d-31e9-4102-8abc-85ef3752fa11; MainAdminID:63787

Journal Information:: Applied Energy, Journal Name: Applied Energy Vol. 310; ISSN 0306-2619

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (35)

Deep learning methods and applications for electrical power systems: A comprehensive review Ozcanli, Asiye K.; Yaprakdal, Fatma; Baysal, Mustafa International Journal of Energy Research, Vol. 44, Issue 9 https://doi.org/10.1002/er.5331	journal	March 2020
Comparative analysis of data-driven methods online and offline trained to the forecasting of grid-connected photovoltaic plant production Ferlito, S.; Adinolfi, G.; Graditi, G. Applied Energy, Vol. 205 https://doi.org/10.1016/j.apenergy.2017.07.124	journal	November 2017
Short-term peer-to-peer solar forecasting in a network of photovoltaic systems Elsinga, Boudewijn; van Sark, Wilfried G. J. H. M. Applied Energy, Vol. 206 https://doi.org/10.1016/j.apenergy.2017.09.115	journal	November 2017
Probabilistic solar power forecasting based on weather scenario generation Sun, Mucun; Feng, Cong; Zhang, Jie Applied Energy, Vol. 266 https://doi.org/10.1016/j.apenergy.2020.114823	journal	May 2020
Hybrid approaches based on deep whole-sky-image learning to photovoltaic generation forecasting Kong, Weicong; Jia, Youwei; Dong, Zhao Yang Applied Energy, Vol. 280 https://doi.org/10.1016/j.apenergy.2020.115875	journal	December 2020
A minutely solar irradiance forecasting method based on real-time sky image-irradiance mapping model Wang, Fei; Xuan, Zhiming; Zhen, Zhao Energy Conversion and Management, Vol. 220 https://doi.org/10.1016/j.enconman.2020.113075	journal	September 2020
Deep learning in electrical utility industry: A comprehensive review of a decade of research Mishra, Manohar; Nayak, Janmenjoy; Naik, Bighnaraj Engineering Applications of Artificial Intelligence, Vol. 96 https://doi.org/10.1016/j.engappai.2020.104000	journal	November 2020
Solar forecasting methods for renewable energy integration Inman, Rich H.; Pedro, Hugo T. C.; Coimbra, Carlos F. M. Progress in Energy and Combustion Science, Vol. 39, Issue 6 https://doi.org/10.1016/j.pecs.2013.06.002	journal	December 2013
Quantitative evaluation of the impact of cloud transmittance and cloud velocity on the accuracy of short-term DNI forecasts Li, Mengying; Chu, Yinghao; Pedro, Hugo T. C. Renewable Energy, Vol. 86 https://doi.org/10.1016/j.renene.2015.09.058	journal	February 2016
Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting Aguiar, L. Mazorra; Pereira, B.; Lauret, P. Renewable Energy, Vol. 97 https://doi.org/10.1016/j.renene.2016.06.018	journal	November 2016
Review of solar irradiance forecasting methods and a proposition for small-scale insular grids Diagne, Maimouna; David, Mathieu; Lauret, Philippe Renewable and Sustainable Energy Reviews, Vol. 27 https://doi.org/10.1016/j.rser.2013.06.042	journal	November 2013
Solar irradiation nowcasting by stochastic persistence: A new parsimonious, simple and efficient forecasting tool Voyant, Cyril; Notton, Gilles Renewable and Sustainable Energy Reviews, Vol. 92 https://doi.org/10.1016/j.rser.2018.04.116	journal	September 2018
Worldwide performance assessment of 75 global clear-sky irradiance models using Principal Component Analysis Sun, Xixi; Bright, Jamie M.; Gueymard, Christian A. Renewable and Sustainable Energy Reviews, Vol. 111 https://doi.org/10.1016/j.rser.2019.04.006	journal	September 2019
Intra-hour DNI forecasting based on cloud tracking image analysis Marquez, Ricardo; Coimbra, Carlos F. M. Solar Energy, Vol. 91, p. 327-336 https://doi.org/10.1016/j.solener.2012.09.018	journal	May 2013
Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning Chu, Yinghao; Pedro, Hugo T. C.; Coimbra, Carlos F. M. Solar Energy, Vol. 98 https://doi.org/10.1016/j.solener.2013.10.020	journal	December 2013
Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data Wolff, Björn; Kühnert, Jan; Lorenz, Elke Solar Energy, Vol. 135 https://doi.org/10.1016/j.solener.2016.05.051	journal	October 2016
Review of photovoltaic power forecasting Antonanzas, J.; Osorio, N.; Escobar, R. Solar Energy, Vol. 136 https://doi.org/10.1016/j.solener.2016.06.069	journal	October 2016
History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining Yang, Dazhi; Kleissl, Jan; Gueymard, Christian A. Solar Energy, Vol. 168 https://doi.org/10.1016/j.solener.2017.11.023	journal	July 2018
3D-CNN-based feature extraction of ground-based cloud images for direct normal irradiance prediction Zhao, Xin; Wei, Haikun; Wang, Hai Solar Energy, Vol. 181 https://doi.org/10.1016/j.solener.2019.01.096	journal	March 2019
Short-term solar power forecast with deep learning: Exploring optimal input and output configuration Sun, Yuchi; Venugopal, Vignesh; Brandt, Adam R. Solar Energy, Vol. 188 https://doi.org/10.1016/j.solener.2019.06.041	journal	August 2019
OpenSolar: Promoting the openness and accessibility of diverse public solar datasets Feng, Cong; Yang, Dazhi; Hodge, Bri-Mathias Solar Energy, Vol. 188 https://doi.org/10.1016/j.solener.2019.07.016	journal	August 2019
SolarNet: A sky image-based deep convolutional neural network for intra-hour solar forecasting Feng, Cong; Zhang, Jie Solar Energy, Vol. 204 https://doi.org/10.1016/j.solener.2020.03.083	journal	July 2020
Verification of deterministic solar forecasts Yang, Dazhi; Alessandrini, Stefano; Antonanzas, Javier Solar Energy, Vol. 210 https://doi.org/10.1016/j.solener.2020.04.019	journal	November 2020
Human-level control through deep reinforcement learning Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David Nature, Vol. 518, Issue 7540 https://doi.org/10.1038/nature14236	journal	February 2015
Mastering the game of Go with deep neural networks and tree search Silver, David; Huang, Aja; Maddison, Chris J. Nature, Vol. 529, Issue 7587 https://doi.org/10.1038/nature16961	journal	January 2016
Solar PV output prediction from video streams using convolutional neural networks Sun, Yuchi; Szűcs, Gergely; Brandt, Adam R. Energy & Environmental Science, Vol. 11, Issue 7 https://doi.org/10.1039/C7EE03420B	journal	January 2018
A guideline to solar forecasting research practice: Reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES) Yang, Dazhi Journal of Renewable and Sustainable Energy, Vol. 11, Issue 2 https://doi.org/10.1063/1.5087462	journal	March 2019
Deep Residual Learning for Image Recognition He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2016.90	conference	June 2016
A Comprehensive Analysis of Deep Regression Lathuiliere, Stephane; Mesejo, Pablo; Alameda-Pineda, Xavier IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, Issue 9 https://doi.org/10.1109/TPAMI.2019.2910523	journal	September 2020
Unsupervised Clustering-Based Short-Term Solar Forecasting Feng, Cong; Cui, Mingjian; Hodge, Bri-Mathias IEEE Transactions on Sustainable Energy, Vol. 10, Issue 4 https://doi.org/10.1109/TSTE.2018.2881531	journal	October 2019
Photovoltaic Nowcasting With Bi-Level Spatio-Temporal Analysis Incorporating Sky Images Zhang, Ruiyuan; Ma, Hui; Saha, Tapan Kumar IEEE Transactions on Sustainable Energy, Vol. 12, Issue 3 https://doi.org/10.1109/TSTE.2021.3064326	journal	July 2021
Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition Antipov, Grigory; Berrani, Sid-Ahmed; Ruchaud, Natacha MM '15: ACM Multimedia Conference, Proceedings of the 23rd ACM international conference on Multimedia https://doi.org/10.1145/2733373.2806332	conference	October 2015
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review Rawat, Waseem; Wang, Zenghui Neural Computation, Vol. 29, Issue 9 https://doi.org/10.1162/neco_a_00990	journal	September 2017
Review on the research and practice of deep learning and reinforcement learning in smart grids [Dongxia Zhang ; Xiaoqing Han ; Chunyu Deng] Zhang, Dongxia; Han, Xiaoqing; Deng, Chunyu CSEE Journal of Power and Energy Systems, Vol. 4, Issue 3 https://doi.org/10.17775/CSEEJPES.2018.00520	journal	September 2018
Distracted Driver Detection: Deep Learning vs Handcrafted Features Hssayeni, Murtadha D.; Saxena, Sagar; Ptucha, Raymond Electronic Imaging, Vol. 2017, Issue 10 https://doi.org/10.2352/ISSN.2470-1173.2017.10.IMAWM-162	journal	January 2017

Similar Records

Intra-hour Solar Irradiance Forecast in Multiple Locations using Deep Transfer Learning

Conference · Thu Jul 20 00:00:00 EDT 2023 · OSTI ID:1989796

Integration of Total-Sky Imager Data with a Physics-Based Smart Persistence Model for Intra-Hour Forecasting of Solar Radiation

Conference · Tue Jan 28 23:00:00 EST 2020 · OSTI ID:1597240

Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks

Journal Article · Wed Jun 16 00:00:00 EDT 2021 · Solar Energy · OSTI ID:1805186

Related Subjects

14 SOLAR ENERGY
97 MATHEMATICS AND COMPUTING
computer vision
deep learning
image processing
sky images
solar forecasting

Convolutional neural networks for intra-hour solar forecasting based on sky image sequences

Citation Formats

References (35)

Similar Records

Related Subjects