THERMAL SCIENCE

International Scientific Journal

Omer Dagistanli

,

Hasan Erbay

,

Ahmet Haşim Yurttakal

,

Hakan Kör

SOLAR IRRADIATION FORECASTBY DEEP LEARNING ARCHITECTURES

ABSTRACT
Global solar irradiation data is a crucial component to measure solar energy potential when we plan, size, and design solar photovoltaic fields. Often, due to the absence of measuring equipment at meteorological stations, data for the place of interest are not available. However, solar irradiation can be estimated by ordinary meteorological data such as humidity, and air temperature. Herein we propose two different deep learning methods, one based on a deep neural network regression and the other based on multivariate long short term memory unit networks, to estimate solar irradiation at given locations. Validation criteria include mean absolute error, mean squared error, and coefficient of determination (R2 value). According to the simulation results, multivariate long short term memory unit networks performs slightly better than deep neural network. Even though both have very close R2 values, multivariate long short term memory's R2 values are more consistent. The same is true for mean squared error and mean absolute error.
KEYWORDS
solar irradiation, deep learning, estimation
PAPER SUBMITTED: 2021-06-19
PAPER REVISED: 2021-11-01
PAPER ACCEPTED: 2022-05-06
PUBLISHED ONLINE: 2022-07-23
DOI REFERENCE: https://doi.org/10.2298/TSCI2204895D
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2022, VOLUME 26, ISSUE Issue 4, PAGES [2895 - 2906]
REFERENCES
  1. ***, Opower, 2022. www.oracle.com/industries/utilities/opower-energy-efficiency/
  2. Dincer, I., Renewable Energy and Sustainable Development: A Crucial Review, Renewable and Sustainable Energy Reviews, 4 (2000), 2, pp. 157-175
  3. Panwar, N., et al., Role of Renewable Energy Sources in Environmental Protection: A Review, Renewable and Sustainable Energy Reviews, 15 (2011), 3, pp. 1513-1524
  4. Busic-Sontic, A., et al, The Role of Personality Traits in Green Decision-Making, Journal of Economic Psychology, 62 (2017), Oct., pp 313-328
  5. Gu, Y., Zhang, X., A Solar Photovoltaic/Thermal (pv/t) Concentrator for Building Application in Sweden Using Monte-Carlo Method, in: Data-driven Analytics for Sustainable Buildings and Cities, Springer, Heilberberg, Germany, 2021, pp. 141-161
  6. Varcın, F., et al., End-to-end Computerized Diagnosis of Spondylolisthesis Using Only Lumbar x-Ray, Journal of Digital Imaging, 34 (2021), 1, pp. 85-95
  7. Hayit, T., et al., Determination of the Severity Level of Yellow Rust Disease in Wheat by Using Convolutional Neural Networks, Journal of Plant Pathology, 103 (2021), 3, pp. 923-934
  8. Alterkavı, S., Erbay, H., Design and Analysis of a Novel Authorship Verification Framework for Hijacked Social Media Accounts Compromised by a Human, Security and Communication Networks, 2021 (2021), ID8869681
  9. Alterkavi, S., Erbay, H., Novel Authorship Verification Model for Social Media Accounts Compromised by a Human, Multimedia Tools and Applications, 80 (2021), 9, pp. 13575-13591
  10. Akarslan, E., et al., Novel Short Term Solar Irradiance Forecasting Models, Renewable Energy, 123 (2018), Aug., pp. 58-66
  11. Hochreiter, S., Schmidhuber, J., Long Short-Term Memory, Neural Computation, 9 (1997), 8, pp. 1735-1780
  12. Shakya, A., et al., Solar Irradiance Forecasting in Remote Microgrids Using Markov Switching Model, IEEE Transactions on Sustainable Energy, 8 (2016), 3, pp. 895-905
  13. Reikard, G., Predicting Solar Radiation at High Resolutions: A Comparison of Time Series Forecasts, Solar Energy, 83 (2009), 3, pp. 342-349
  14. Diagne, M., et al., Review of Solar Irradiance Forecasting Methods and a Proposition for Small-Scale Insular Grids, Renewable and Sustainable Energy Reviews, 27 (2013), Nov., pp. 65-76
  15. Voyant, C., et al., Machine Learning Methods for Solar Radiation Forecasting: A Review, Renewable Energy, 105 (2017), May, pp. 569-582
  16. Yang, D., et al., Forecasting of Global Horizontal Irradiance by Exponential Smoothing, Using Decompositions, Energy, 81 (2015), Mar., pp. 111-119
  17. Yang, D., et al., Reconciling Solar Forecasts: Geographical Hierarchy, Solar Energy, 146 (2017), Apr., pp. 276-286
  18. Bailek, N., et al., A New Empirical Model for Forecasting the Diffuse Solar Radiation over Sahara in the Algerian Big South, Renewable Energy, 117 (2018), 3, pp. 530-537
  19. Chu, Y., et al., Real-Time Prediction Intervals for Intra-Hour DNI Forecasts, Renewable Energy, 83 (2015), C, pp. 234-244
  20. Law, E. V., et al., Direct Normal Irradiance Forecasting and Its Application Concentrated Solar Thermal Output Forecasting - A Review, Solar Energy, 108 (2014), Oct., pp. 287-307
  21. Gostein, M., et al., Evaluating a Model to Estimate GHI, DNI, & DHI from POA Irradiance, Proceedings, 2016 IEEE 43rd Photovoltaic Specialists Conference (PVSC), Portland, Org., USA, 2016, pp. 0943-0946
  22. Gustafson, W. T., et al., Global Validation of Rest2 Incorporated into an Operational DNI and GHI Irradiance Model, Proceedings, 2016 IEEE 43rd Photovoltaic Specialists Conference (PVSC), Portland, Ore., USA, 2016, pp. 0947-0952
  23. Gueymard, C. A., Rest2: High-Performance Solar Radiation Model for Cloudlessky Irradiance, Illuminance, and Photosynthetically Active Radiation-Validation with a Benchmark Dataset, Solar Energy, 82 (2008), 3, pp. 272-285
  24. Sengupta, M., et al., Physics-Based Goes Satellite Product for Use in NREL's National Solar Radiation Database, Technical Report, National Renewable Energy Lab. (NREL), Golden, Col., USA, 2014
  25. Liu, W., et al., Use of Physics to Improve Solar Forecast: Physics-Informed Persistence Models for Simultaneously Forecasting GHI, DNI, and DHI, Solar Energy, 215 (2021), Feb., pp. 252-265
  26. Luo, J., et al., Progress in Perovskite Solar Cells Based on ZnO Nanostructures, Solar Energy, 163 (2018), Mar., pp. 289-306
  27. Pazikadin, A. R., et al., Solar Irradiance Measurement Instrumentation and Power Solar Generation Forecasting Based on Artificial Neural Networks (ANN): A Review of Five Years Research Trend, Science of The Total Environment, 715 (2020), 136848
  28. Zang, H., et al., Short-Term Global Horizontal Irradiance Forecasting Based on a Hybrid CNN-LSTM Model with Spatiotemporal Correlations, Renewable Energy, 160 (2020), Nov., pp. 26-41
  29. Benali, L., et al., Solar Radiation Forecasting Using Artificial Neural Network and Random Forest Methods, Application Normal Beam, Horizontal Diffuse and Global Components, Renewable Energy, 132 (2019), Mar., pp. 871-884
  30. Verbois, H., et al., Probabilistic Forecasting of Day-Ahead Solar Irradiance Using Quantile Gradient Boosting, Solar Energy, 173 (2018), Oct., pp. 313-327
  31. Busic-Sontic, A., et al., Personality Trait Effects on Green Household Installations, Collabra: Psychology, 4 (2018), 1, 8
  32. Achleitner, S., et al., Solar Irradiance Prediction System, Proceedings, 13th PSN14 International Symposium on Information Processing in Sensor Networks, IEEE, Berlin, Germany, 2014, pp 225-236
  33. ***, Wipro's sustainability machine learning challenge, 2021, URL www.kaggle.com/datasets/vickeytomer/ wipros-sustainability-machine-learning-challenge, 2022
  34. Goodfellow, I., et al., Deep Learning, MIT Press, Cambridge, Mass., USA, 2016
  35. Komorowski, M., et al., Exploratory Data Analysis, in: Secondary Analysis of Electronic Health Records, Springer, New York, USA, 2016, Chapter 15, pp. 185-203
  36. Dowdy, S., et al., Statistics for Research, John Wiley & Sons, New York, USA, 2011
PDF VERSION [DOWNLOAD]
Solar irradiation forecastby deep learning architectures

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence