Evaluation of Various Deep Learning Models for Short-Term Solar Forecasting in the Arctic using a Distributed Sensor Network

Evaluation of Various Deep Learning Models for Short-Term Solar Forecasting
in the Arctic using a Distributed Sensor Network

Volume 9, Issue 3, Page No 12-28, 2024

Author’s Name: Henry Toal1,a), Michelle Wilber¹, Getu Hailu², Arghya Kusum Das³

View Affiliations

¹University of Alaska Fairbanks, Alaska Center for Energy and Power, Fairbanks, 99775, United States
²University of Alaska Anchorage, Mechanical Engineering Department, Anchorage, 99508, United States
³University of Alaska Fairbanks, Department of Computer Science, Fairbanks, 99775, United States

a)whom correspondence should be addressed. E-mail: ehtoal@alaska.edu

Adv. Sci. Technol. Eng. Syst. J. 9(3), 12-28(2024); a  DOI: 10.25046/aj090302

Keywords: Solar Photovoltaics, Sensor Network, Machine Learning, Deep Learning

Share
Download Now!

41 Downloads

Export Citations

Abstract

The solar photovoltaic (PV) power generation industry has experienced substantial, ongoing growth over the past decades as a clean, cost-effective energy source. As electric grids use ever-larger proportions of solar PV, the technology’s inherent variability—primarily due to clouds—poses a challenge to maintaining grid stability. This is especially true for geographically dense, electrically isolated grids common in rural locations which must maintain substantial reserve generation capacity to account for sudden swings in PV power production. Short-term solar PV forecasting emerges as a solution, allowing excess generation to be kept offline until needed, reducing fuel costs and emissions. Recent studies have utilized networks of light sensors deployed around PV arrays which can preemptively detect incoming fluctuations in light levels caused by clouds. This research examines the potential of such a sensor network in providing short-term forecasting for a 575-kW solar PV array in the arctic community of Kotzebue, Alaska. Data from sensors deployed around the array were transformed into a forecast at a 2-minute time horizon using either long short-term memory (LSTM) or gated recurrent unit (GRU) as base models augmented with various combinations of 1-dimensional convolutional (Conv1D) and fully connected (Dense) model layers. These models were evaluated using a novel combination of statistical and event-based error metrics, including Precision, Recall, and Fβ. It was found that GRU-based models generally outperformed their LSTM-based counterparts along statistical error metrics while showing lower relative event-based forecasting ability. This research demonstrates the potential efficacy of a novel combination of LSTM/GRU-based deep learning models and a distributed sensor network when forecasting the power generation of an actual solar PV array. Performance across the eight evaluated model combinations was mostly comparable to similar methods in the literature and is expected to improve with additional training data.

Received: 07 March 2023, Revised: 02 May 2024, Accepted: 03 May 2024, Published Online: 23 May 2024

References (65)

  1. G. Masson, E. Bosch, A. V. Rechem, M. de l’Epine, “Snapshot of Global PV Markets 2023,” 2023.
  2. R.-E. Precup, T. Kamal, S. Z. Hassan, editors, Solar Photovoltaic Power Plants: Advanced Control and Optimization Techniques, Power Systems, Springer Singapore, Singapore, 1st edition, 2019, doi:10.1007/978-981-13-6151-7, published: 07 February 2019 (eBook), 20 February 2019 (Hardcover)
  3. J. Marcos, L. Marroyo, E. Lorenzo, D. Alvira, E. Izco, “Power output fluctuations in large scale pv plants: One year observations with one second resolution and a derived analytic model,” Progress in Photovoltaics: Research and Applications, 19(2), 218–227, 2010, doi:10.1002/pip.1016.
  4. S. Abdollahy, A. Mammoli, F. Cheng, A. Ellis, J. Johnson, “Distributed compensation of a large intermittent energy resource in a distribution feeder,” in 2013 IEEE PES Innovative Smart Grid Technologies Conference (ISGT), 1–6, 2013, doi:10.1109/ISGT.2013.6497911.
  5. R. van Haaren, M. Morjaria, V. Fthenakis, “Empirical assessment of shortterm variability from utility-scale solar PV plants,” Progress in Photovoltaics: Research and Applications, 22(5), 548–559, 2012, doi:10.1002/pip.2302.
  6. H. M. Diagne, P. Lauret, M. David, “Solar irradiation forecasting: state-of-theart and proposition for future developments for small-scale insular grids,” in WREF 2012 – World Renewable Energy Forum, Denver, United States, 2012.
  7. P. Nikolaidis, A. Poullikkas, “A novel cluster-based spinning reserve dynamic model for wind and PV power reinforcement,” Energy, 234, 121270, 2021, doi:https://doi.org/10.1016/j.energy.2021.121270.
  8. N. Green, M. Mueller-Stoffels, E. Whitney, “An Alaska case study: Diesel generator technologies,” Journal of Renewable and Sustainable Energy, 9(6), 061701, 2017, doi:10.1063/1.4986585.
  9. C. S. McCallum, N. Kumar, R. Curry, K. McBride, J. Doran, “Renewable electricity generation for off grid remote communities; Life Cycle Assessment Study in Alaska, USA,” Applied Energy, 299, 117325, 2021, doi: https://doi.org/10.1016/j.apenergy.2021.117325.
  10. S. Achleitner, A. Kamthe, T. Liu, A. E. Cerpa, “SIPS: Solar Irradiance Prediction System,” in IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks, 225–236, 2014, doi: 10.1109/IPSN.2014.6846755.
  11. A. Hussain, V.-H. Bui, H.-M. Kim, “Microgrids as a resilience resource and strategies used by microgrids for enhancing resilience,” Applied energy, 240, 56–72, 2019, doi:10.1016/j.apenergy.2019.02.055.
  12. A. Lagrange, M. de Sim´on-Mart´ın, A. Gonz´alez-Mart´ınez, S. Bracco, E. Rosales-Asensio, “Sustainable microgrids with energy storage as a means to increase power resilience in critical facilities: An application to a hospital,” International Journal of Electrical Power & Energy Systems, 119, 105865, 2020, doi:10.1016/j.ijepes.2020.105865.
  13. D. S. Kumar, G. M. Yagli, M. Kashyap, D. Srinivasan, “Solar irradiance resource and forecasting: a comprehensive review,” IET Renewable Power Generation, 14(10), 1641–1656, 2020, doi:10.1049/iet-rpg.2019.1227. www.astesj.com 26 H. Toal et al., / Advances in Science, Technology and Engineering Systems Journal Vol. 9, No. 3, 12-28 (2024)
  14. P. Sukiˇc, G. ˇStumberger, “Intra-minute cloud passing forecasting based on a low cost IoT sensor—A solution for smoothing the output power of PV power plants,” Sensors, 17(5), 1116, 2017, doi:10.3390/s17051116.
  15. V. P. Lonij, A. E. Brooks, A. D. Cronin, M. Leuthold, K. Koch, “Intra-hour forecasts of solar power production using measurements from a network of irradiance sensors,” Solar energy, 97, 58–66, 2013, doi:10.1016/j.solener.2013. 08.002.
  16. J. L. Bosch, J. Kleissl, “Cloud motion vectors from a network of ground sensors in a solar power plant,” Solar Energy, 95, 13–20, 2013, doi:10.1016/j.solener. 2013.05.027.
  17. R. H. Inman, H. T. Pedro, C. F. Coimbra, “Solar forecasting methods for renewable energy integration,” Progress in Energy and Combustion Science, 39(6), 535–576, 2013, doi:10.1016/j.pecs.2013.06.002.
  18. C. W. Chow, B. Urquhart, M. Lave, A. Dominguez, J. Kleissl, J. Shields, B. Washom, “Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed,” Solar Energy, 85(11), 2881–2893, 2011, doi: 10.1016/j.solener.2011.08.025.
  19. R. Marquez, C. F. Coimbra, “Intra-hour DNI forecasting based on cloud tracking image analysis,” Solar Energy, 91, 327–336, 2013, doi:10.1016/j.solener. 2012.09.018.
  20. D. Yang, Z. Ye, L. H. I. Lim, Z. Dong, “Very short term irradiance forecasting using the lasso,” Solar Energy, 114, 314–326, 2015, doi:10.1016/j.solener.2015. 01.016.
  21. M. Jaihuni, J. K. Basak, F. Khan, F. G. Okyere, T. Sihalath, A. Bhujel, J. Park, D. H. Lee, H. T. Kim, “A novel recurrent neural network approach in forecasting short term solar irradiance,” ISA Transactions, 121, 63–74, 2022, doi:https://doi.org/10.1016/j.isatra.2021.03.043.
  22. P. Kumari, D. Toshniwal, “Deep learning models for solar irradiance forecasting: A comprehensive review,” Journal of Cleaner Production, 318, 128566, 2021, doi:10.1016/j.jclepro.2021.128566.
  23. S. Mishra, P. Palanisamy, “An Integrated Multi-Time-Scale Modeling for Solar Irradiance Forecasting Using Deep Learning,” CoRR, abs/1905.02616, 2019.
  24. A. Mellit, A. M. Pavan, V. Lughi, “Deep learning neural networks for shortterm photovoltaic power forecasting,” Renewable Energy, 172, 276–288, 2021, doi:10.1016/j.renene. 2021.02.166.
  25. A. Bhatt, W. Ongsakul, J. G. Singh, et al., “Sliding window approach with first-order differencing for very short-term solar irradiance forecasting using deep learning models,” Sustainable Energy Technologies and Assessments, 50, 101864, 2022, doi:10.1016/j.seta. 2021.101864.
  26. X. Jiao, X. Li, D. Lin, W. Xiao, “A graph neural network based deep learning predictor for spatio-temporal group solar irradiance forecasting,” IEEE Transactions on Industrial Informatics, 18(9), 6142–6149, 2022, doi: 10.1109/TII.2021.3133289.
  27. J. Haxhibeqiri, E. De Poorter, I. Moerman, J. Hoebeke, “A survey of Lo- RaWAN for IoT: From technology to application,” Sensors, 18(11), 3995, 2018, doi:10.3390/s18113995.
  28. M. Sengupta, A. Andreas, “Oahu solar measurement grid (1-year archive): 1-second solar irradiance; Oahu, Hawaii (data),” 2010.
  29. A. W. Aryaputera, D. Yang, L. Zhao, W. M. Walsh, “Very short-term irradiance forecasting at unobserved locations using spatio-temporal kriging,” Solar Energy, 122, 1266–1278, 2015, doi:10.1016/j. solener.2015.10.023.
  30. J. S. Stein, C. W. Hansen, M. J. Reno, “Global horizontal irradiance clear sky models: implementation and analysis.” Technical report, Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA, 2012.
  31. V. Lara-Fanego, J. Ruiz-Arias, D. Pozo-V´azquez, F. Santos-Alamillos, J. Tovar- Pescador, “Evaluation of the WRF model solar irradiance forecasts in Andalusia (southern Spain),” Solar Energy, 86(8), 2200–2217, 2012, doi: 10.1016/j.solener.2011.02.014.
  32. H. Toal, A. K. Das, “Variability and Trend Analysis of a Grid-Scale Solar Photovoltaic Array above the Arctic Circle,” in 2023 IEEE 24th International Conference on Information Reuse and Integration for Data Science (IRI), 242–247, 2023, doi:10.1109/IRI58017.2023.00049.
  33. J. Stein, C. Hansen, M. J. Reno, “The variability index: A new and novel metric for quantifying irradiance and PV output variability.” Technical report, Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA, 2012.
  34. B. Yegnanarayana, Artificial neural networks, PHI Learning Pvt. Ltd., 2009.
  35. V. Z. Antonopoulos, D. M. Papamichail, V. G. Aschonitis, A. V. Antonopoulos, “Solar radiation estimation methods using ANN and empirical models,” Computers and Electronics in Agriculture, 160, 160–167, 2019, doi: 10.1016/j.compag.2019.03.022.
  36. V. Srikrishnan, G. S. Young, L. T. Witmer, J. R. Brownson, “Using multipyranometer arrays and neural networks to estimate direct normal irradiance,” Solar Energy, 119, 531–542, 2015, doi:10.1016/j. solener.2015.06.004.
  37. F.-V. Gutierrez-Corea, M.-A. Manso-Callejo, M.-P. Moreno-Regidor, M.-T. Manrique-Sancho, “Forecasting short-term solar irradiance based on artificial neural networks and data from neighboring meteorological stations,” Solar Energy, 134, 119–131, 2016, doi: 10.1016/j.solener.2016.04.020.
  38. H. T. Pedro, C. F. Coimbra, “Assessment of forecasting techniques for solar power production with no exogenous inputs,” Solar Energy, 86(7), 2017–2028, 2012, doi:10.1016/j.solener.2012.04.004.
  39. S. Z. Hassan, H. Li, T. Kamal, M. Nadarajah, F. Mehmood, “Fuzzy embedded MPPT modeling and control of PV system in a hybrid power system,” in 2016 International Conference on Emerging Technologies (ICET), 1–6, 2016, doi:10.1109/ICET.2016.7813236.
  40. A. Abbas, N. Mughees, A. Mughees, A. Mughees, S. Yousaf, S. Z. Hassan, F. Sohail, H. Rehman, T. Kamal, M. A. Khan, “Maximum Power Harvesting using Fuzzy Logic MPPT Controller,” in 2020 IEEE 23rd International Multitopic Conference (INMIC), 1–6, 2020, doi:10.1109/INMIC50486.2020.9318188.
  41. S. Z. Hassan, H. Li, T. Kamal, U. Arifo˘glu, S. Mumtaz, L. Khan, “Neuro-Fuzzy Wavelet Based Adaptive MPPT Algorithm for Photovoltaic Systems,” Energies, 10(3), 2017, doi:10.3390/en10030394.
  42. S. Mumtaz, S. Ahmad, L. Khan, S. Ali, T. Kamal, S. Z. Hassan, “Adaptive Feedback Linearization Based NeuroFuzzy Maximum Power Point Tracking for a Photovoltaic System,” Energies, 11(3), 2018, doi:10.3390/en11030606.
  43. C. M. Bishop, Neural networks for pattern recognition, Oxford university press, 1995.
  44. A. Goh, “Back-propagation neural networks for modeling complex systems,” Artificial Intelligence in Engineering, 9(3), 143–151, 1995, doi: 10.1016/0954-1810(94)00011-S.
  45. P. Baldi, “Gradient descent learning algorithm overview: A general dynamical systems perspective,” IEEE Transactions on neural networks, 6(1), 182–195, 1995, doi:10.1109/72.363438.
  46. I. Sutskever, J. Martens, G. E. Hinton, “Generating text with recurrent neural networks,” in Proceedings of the 28th international conference on machine learning (ICML-11), 1017–1024, 2011.
  47. Y. Bengio, P. Simard, P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE transactions on neural networks, 5(2), 157–166, 1994, doi:10.1109/72.279181.
  48. S. Siami-Namini, N. Tavakoli, A. S. Namin, “The performance of LSTM and BiLSTM in forecasting time series,” in 2019 IEEE International conference on big data (Big Data), 3285–3292, IEEE, 2019, doi:10.1109/BigData47090.2019. 9005997.
  49. A. Yadav, C. Jha, A. Sharan, “Optimizing LSTM for time series prediction in Indian stock market,” Procedia Computer Science, 167, 2091–2100, 2020, doi:10.1016/j.procs.2020.03.257. www.astesj.com 27 H. Toal et al., / Advances in Science, Technology and Engineering Systems Journal Vol. 9, No. 3, 12-28 (2024)
  50. X. Qing, Y. Niu, “Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM,” Energy, 148, 461–468, 2018, doi: 10.1016/j.energy.2018. 01.177.
  51. S. Hochreiter, J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, 9(8), 1735–1780, 1997, doi:10.1162/neco.1997.9.8.1735.
  52. A. Sherstinsky, “Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network,” Physica D: Nonlinear Phenomena, 404, 132306, 2020, doi:10.1016/j.physd.2019.132306.
  53. R. Dey, F. M. Salem, “Gate-variants of gated recurrent unit (GRU) neural networks,” in 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS), 1597–1600, IEEE, 2017, doi:10.1109/MWSCAS. 2017.8053243.
  54. R. Zhao, D. Wang, R. Yan, K. Mao, F. Shen, J. Wang, “Machine health monitoring using local feature-based gated recurrent unit networks,” IEEE Transactions on Industrial Electronics, 65(2), 1539–1548, 2018, doi:10.1109/ TIE.2017.2733438.
  55. J. Chung, C. Gulcehre, K. Cho, Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling,” arXiv preprint arXiv:1412.3555,2014.
  56. S. Kiranyaz, A. Gastli, L. Ben-Brahim, N. Al-Emadi, M. Gabbouj, “Real-time fault detection and identification for MMC using 1-D convolutional neural networks,” IEEE Transactions on Industrial Electronics, 66(11), 8760–8771, 2019, doi:10.1109/TIE.2018.2833045.
  57. S. Kiranyaz, T. Ince, M. Gabbouj, “Real-time patient-specific ECG classification by 1-D convolutional neural networks,” IEEE transactions on biomedical engineering, 63(3), 664–675, 2016, doi:10.1109/TBME.2015.2468589.
  58. H. Zhou, Y. Zhang, L. Yang, Q. Liu, K. Yan, Y. Du, “Short-Term Photovoltaic Power Forecasting Based on Long Short Term Memory Neural Network and Attention Mechanism,” IEEE Access, 7, 78063–78074, 2019, doi: 10.1109/ACCESS.2019.2923006
  59.  R. Van Haaren, M. Morjaria, V. Fthenakis, “Empirical assessment of shortterm variability from utility-scale solar PV plants,” Progress in Photovoltaics: Research and Applications, 22(5), 548–559, 2014, doi:10.1002/pip.2302.
  60.  R. Perez, M. David, T. E. Hoff, M. Jamaly, S. Kivalov, J. Kleissl, P. Lauret, M. Perez, et al., “Spatial and temporal variability of solar energy,” Foundations and Trends® in Renewable Energy, 1(1), 1–44, 2016, doi: 10.1561/2700000006.
  61.  M. Abuella, B. Chowdhury, “Forecasting of solar power ramp events: A post-processing approach,” Renewable Energy, 133, 1380–1392, 2019, doi: 10.1016/j.renene.2018.09.005.
  62.  A. Sanfilippo, L. Martin-Pomares, N. Mohandes, D. Perez-Astudillo, D. Bachour, “An adaptive multi-modeling approach to solar nowcasting,” Solar Energy, 125, 77–85, 2016, doi: 10.1016/j.solener.2015.11.041.
  63.  M. Abuella, B. Chowdhury, “Forecasting solar power ramp events using machine learning classification techniques,” in 2018 9th IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG), 1–6, IEEE, 2018, doi:10.1109/PEDG.2018.8447599.
  64.  Y. Wang, C. Purev, H. Barndt, H. Toal, J. Kim, L. Underwood, L. Avalo, A. K. Das, “Toward Energy-Efficient Deep Neural Networks for Forest Fire Detection in an Image,” The Geographical Bulletin, 64(2), 13, 2023.
  65.  F. Huettmann, P. Andrews, M. Steiner, A. K. Das, J. Philip, C. Mi, N. Bryans, B. Barker, “A super SDM (species distribution model)‘in the cloud’for better habitat-association inference with a ‘big data’application of the Great Gray Owl for Alaska,” Scientific Reports, 14(1), 7213, 2024, doi:10.1038/ s41598-024-57588-9.

Cited By

Citations by Dimensions

Citations by PlumX

Crossref Citations

This paper is currently not cited.

Metrics

No. of Downloads Per Month

No. of Downloads Per Country