Abstract
In order to contribute to the integration of photovoltaic renewable energy into power system, this paper addresses the problem of forecasting solar irradiance or Global Horizontal Irradiation (GHI). The collection, adjustment and processing of meteorological data used as input is carried out, in addition various Deep Neural Networks (DNN) models are implemented and analyzed, among which are the Artificial Neural Networks (ANN) of type as Transformer, LSTM, GRU, and mixed between Convolutional ANN (CNN)-LSTM, and CNN-GRU. These ANN variants are implemented, and a comparative study are made. Finally, the results obtained show that the ANN transformer has less error in the GHI forecasting.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Morales Ramírez, D., Luyando Cuevas, J.R.: Analisis del Consumo de Energia Electrica Residencial en el Area Metropolitana de Monterrey, vol. 31, no. 62, Art. n.o 62
REN21, Renewables Global Status Report, Paris, France, 22 March 2022. https://www.ren21.net/reports/global-status-report/. Accessed 22 Mar 2022
Demanda de energía eléctrica en tiempo real, estructura de generación y emisiones de CO2, REE, 22 March 2022. https://demanda.ree.es/visiona/seleccionar-sistema. Accessed 22 Mar 2022
Robledo Quintero, Á.: Predicción de la radiación global utilizando redes de neuronas artificiales, July 2018). https://e-archivo.uc3m.es/handle/10016/29002. Accessed 22 Mar 2022
de Santos Jr, D.S.O., et al.: Solar irradiance forecasting using dynamic ensemble selection. Appl. Sci. 12(7), 3510 (2022)
Aliberti, A., Fucini, D., Bottaccioli, L., Macii, E., Acquaviva, A., Patti, E.: Comparative analysis of neural networks techniques to forecast global horizontal irradiance. IEEE Access 9, 122829–122846 (2021). https://doi.org/10.1109/ACCESS.2021.3110167
Géron, A.: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O’Reilly Media, Inc., Sebastopol (2019)
Liu, C.-H., Gu, J.-C., Yang, M.-T.: A simplified LSTM neural networks for one day-ahead solar power forecasting. IEEE Access 9, 17174–17195 (2021). https://doi.org/10.1109/ACCESS.2021.3053638
Aslam, M., Lee, S.J., Khang, S.H., Hong, S.: Two-stage attention over LSTM with Bayesian optimization for day-ahead solar power forecasting. IEEE Access 9, 107387–107398 (2021). https://doi.org/10.1109/ACCESS.2021.3100105
Yu, Y., Cao, J., Zhu, J.: An LSTM short-term solar irradiance forecasting under complicated weather conditions. IEEE Access 7, 145651–145666 (2019). https://doi.org/10.1109/ACCESS.2019.2946057
Konstantinou, M., Peratikou, S., Charalambides, A.G.: Solar photovoltaic forecasting of power output using LSTM networks. Atmosphere 12(1), Art. n.o 1 (2021). https://doi.org/10.3390/atmos12010124
Jalali, S.M.J., Ahmadian, S., Kavousi-Fard, A., Khosravi, A., Nahavandi, S.: Automated Deep CNN-LSTM architecture design for solar irradiance forecasting. IEEE Trans. Syst. Man Cybern. Syst. 52(1), Art. n.o 1 (2022). https://doi.org/10.1109/TSMC.2021.3093519
Wang, F., Yu, Y., Zhang, Z., Li, J., Zhen, Z., Li, K.: Wavelet decomposition and convolutional LSTM networks based improved deep learning model for solar irradiance forecasting. Appl. Sci. 8(8), Art. n.o 8 (2018). https://doi.org/10.3390/app8081286
Prado-Rujas, I.-I., García-Dopico, A., Serrano, E., Pérez, M.S.: A flexible and robust deep learning-based system for solar irradiance forecasting. IEEE Access 9, 12348–12361(2021). https://doi.org/10.1109/ACCESS.2021.3051839
Khan, W., Walker, S., Zeiler, W.: Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach. Energy 240, 122812 (2022). https://doi.org/10.1016/j.energy.2021.122812
Abdel-Nasser, M., Mahmoud, K., Lehtonen, M.: HIFA: promising heterogeneous solar irradiance forecasting approach based on kernel mapping. IEEE Access 9, 144906–144915 (2021). https://doi.org/10.1109/ACCESS.2021.3122826
Katrompas, A., Ntakouris, T., Metsis, V.: Recurrence and self-attention vs the transformer for time-series classification: a comparative study. In: International Conference on Artificial Intelligence in Medicine, 2022, pp. 99–109 (2022)
Cristian Arbelaez-Duque, A.D.: Solar Forecasting Elec Eng UdeA. Medellin, 25 July 2022. https://github.com/cdarbelaez/SolarForecastingElecEngUdeA. Accessed 23 Sep 2022
Romero Rodríguez, J.M.: Modelo para predicción de potencia de paneles fotovoltaicos utilizando técnicas de clasificación no supervisada y redes neuronales artificiales (2020). https://manglar.uninorte.edu.co/handle/10584/9049. Accessed 22 Mar 2022
Sharda, S., Singh, M., Sharma, K.: RSAM: robust self-attention based multi-horizon model for solar irradiance forecasting. IEEE Trans. Sustain. Energy 12(2), 1394–1405 (2021). https://doi.org/10.1109/TSTE.2020.3046098
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017). https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Huang, X., Zhang, C., Li, Q., Tai, Y., Gao, B., Shi, J.: A comparison of hour-ahead solar irradiance forecasting models based on LSTM network. Math. Probl. Eng. 2020, e4251517 (2020). https://doi.org/10.1155/2020/4251517
Ashfaq, Q., Ulasyar, A., Zad, H.S., Nisar, S., Khattak, A., Imran, K.: Multi-step forecasting of global horizontal irradiance using long short-term memory network for solving economic dispatch problem. In: 2021 International Conference on Innovative Computing (ICIC), pp. 1–9 (2021). https://doi.org/10.1109/ICIC53490.2021.9693031
Vakitbilir, N., Hilal, A., Direkoğlu, C.: Hybrid deep learning models for multivariate forecasting of global horizontal irradiation. Neural Comput. Appl. ene. (2022). https://doi.org/10.1007/s00521-022-06907-0
GeoSUN Africa: Kenya - Solar Radiation Measurement Data, EnergyData.info (2020). https://energydata.info/dataset/kenya-solar-radiation-measurement-data. Accessed 23 Sep 2022
Funding
This research was funded by the Colombia Scientific Program within the framework of the so-called Ecosistema Científico (Contract No. FP44842-218-2018).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Arbeláez-Duque, C., Duque-Ciro, A., Villa-Acevedo, W., Jaramillo-Duque, Á. (2023). Deep Neural Networks for Global Horizontal Irradiation Forecasting: A Comparative Study. In: Nesmachnow, S., Hernández Callejo, L. (eds) Smart Cities. ICSC-CITIES 2022. Communications in Computer and Information Science, vol 1706. Springer, Cham. https://doi.org/10.1007/978-3-031-28454-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-28454-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28453-3
Online ISBN: 978-3-031-28454-0
eBook Packages: Computer ScienceComputer Science (R0)