ORIGINAL PAPER
A hybrid deep learning framework for modeling the short term global horizontal irradiance prediction of a solar power plant in India
1
National Institute of Construction Management and Research (NICMAR), Hyderabad,Telangana, India
Submission date: 2023-04-17
Acceptance date: 2023-06-11
Publication date: 2023-09-19
Corresponding author
S.V.S. Rajaprasad
Project Engineering and Management, National Institute of Construction Management and Research (NICMAR), Jagganguda, 500101, Hyderabad, India
Project Engineering and Management, National Institute of Construction Management and Research (NICMAR), Jagganguda, 500101, Hyderabad, India
Polityka Energetyczna – Energy Policy Journal 2023;26(3):101-116
KEYWORDS
TOPICS
ABSTRACT
The rapid development of grid integration of solar energy in developing countries like India has created vital concerns such as fluctuations and interruptions affecting grid operations. Improving the consistency and accuracy of solar energy forecasts can increase the reliability of the power grid. Although solar energy is available in abundance around the world, it is viewed as an unpredictable source due to uncertain fluctuations in climate conditions. Global horizontal irradiance (GHI) prediction is critical to efficiently manage and forecast the power output of solar power plants. However, developing an accurate GHI forecasting model is challenging due to the variability of weather conditions over time. This research aims to develop and compare univariate LSTM models capable of predicting GHI in a solar power plant in India over the short term. The present study introduces a deep neural network-based (DNN) hybrid model with a combination of convolutional neural network bi-directional long short-term memory (CNN BiLSTM) to predict the one minute interval GHI of a solar power plant located in the southern region of India. The model’s effectiveness was tested using data for the month of January 2023. In addition, the results of the hybrid model were compared to the long short-term memory (LSTM) and BiLSTM deep-learning (DL) models. It has been observed that the proposed hybrid model framework is more accurate compared to the LSTM and BiLSTM architectures. Finally, a GHI prediction tool was developed to understand the trend of the results.
METADATA IN OTHER LANGUAGES:
Polish
Hybrydowa struktura głębokiego uczenia do modelowania krótkoterminowych prognoz globalnego natężenia napromienienia poziomego elektrowni słonecznej w Indiach
globalne natężenie napromienienia poziomego, energia, głębokie sieci neuronowe, model hybrydowy
Szybki rozwój integracji energii słonecznej z siecią elektroenergetyczną w krajach rozwijających się, takich jak Indie, wywołał istotne obawy, m.in. związane z wahaniami i przerwami wpływającymi na działanie sieci. Poprawa spójności i dokładności prognoz dotyczących energii słonecznej może zwiększyć niezawodność sieci energetycznej. Chociaż energia słoneczna jest dostępna w dużych ilościach na całym świecie, jest ona postrzegana jako nieprzewidywalne źródło ze względu na niepewne wahania warunków klimatycznych. Prognozowanie globalnego natężenia napromienienia horyzontalnego (GHI) ma kluczowe znaczenie dla efektywnego zarządzania i prognozowania mocy elektrowni słonecznych. Jednak opracowanie dokładnego modelu prognozowania GHI jest trudne ze względu na zmienność warunków pogodowych w czasie. Badania te mają na celu opracowanie i porównanie modeli LSTM zdolnych do przewidywania GHI w elektrowni słonecznej w Indiach w krótkim czasie. W niniejszym badaniu wprowadzono hybrydowy model oparty na głębokiej sieci neuronowej (DNN) z kombinacją dwukierunkowej konwolucyjnej sieci neuronowej z długą pamięcią krótkotrwałą (CNN BiLSTM) w celu przewidywania jednominutowych interwałów GHI elektrowni słonecznej zlokalizowanej w południowym regionie Indii. Skuteczność modelu została przetestowana przy użyciu danych za styczeń 2023 roku. Ponadto wyniki modelu hybrydowego porównano z modelami uczenia głębokiego (DL) z długą pamięcią krótkotrwałą (LSTM) i BiLSTM. Zaobserwowano, że proponowany model hybrydowy jest dokładniejszy w porównaniu do architektur LSTM i BiLSTM. Ostatecznie opracowano narzędzie do przewidywania GHI, aby zrozumieć trend wyników.
REFERENCES (24)
1.
Alghamdi, H.A. 2022. A Time Series Forecasting of Global Horizontal Irradiance on Geographical Data of Najran Saudi Arabia. Energies 15(3), pp. 1–19, DOI: 10.3390/en15030928.
2.
Alharbi, F.R. and Csala, D. 2021. Wind Speed and Solar Irradiance Prediction Using a Bidirectional Long Short-Term Memory Model Based on Neural Networks. Energies 14(20), pp. 1–22, DOI: 10.3390/en14206501.
3.
Badr et al. 2020 – Badr, B., Mustapha, O., Imane, A. and Mohamed, B.A. 2020. A Proposed Model to Forecast Hourly Global Solar Irradiation Based on Satellite Derived Data, Deep Learning and Machine Learning Approaches. Journal of Ecological Engineering 21(4), pp. 26–38, DOI: 10.12911/22998993/119795.
4.
Boubaker et al. 2021 – Boubaker, S., Benghanem, M., Mellit, A., Lefza, A., Kahouli, O. and Kolsi, L. 2021. Deep Neural Networks for Predicting Solar Radiation at Hail Region, Saudi Arabia. IEEE Access 9, pp. 36719–36729, DOI: 10.1109/ACCESS.2021.3062205.
5.
Chen, Y. and Fu, Z. 2023. Multi-Step Ahead Forecasting of the Energy Consumed by the Residential and Commercial Sectors in the United States Based on a Hybrid CNN-BiLSTM Model. Sustainability 15(3), pp. 1–21, DOI: 10.3390/su15031895.
6.
Gürel et al. 2020 – Gürel, A.E, Ağbulut, Ü. and Biçen, Y. 2020. Assessment of machine learning, time series, response surface methodology and empirical models in prediction of global solar radiation. Journal of Cleaner Production 277, pp. 1–30, DOI: 10.1016/j.jclepro.2020.122353.
7.
Hirolikar et al. 2022 – Hirolikar, D.D., Satuse, A., Bhalerao, O., Pawar, P. and Thorat, H. 2022. Intelligent Movie Recommendation System Using AI and ML. International Journal for Research in Applied Science and Engineering Technology 10(5), pp. 611–622, DOI: 10.22214/ijraset.2022.42255.
8.
Huang et al. 2019 – Huang, X., Shi, J., Gao, B., Tai, Y., Chen, Z. and Zhang, J. 2019. Forecasting Hourly Solar Irradiance Using Hybrid Wavelet Transformation and Elman Model in Smart Grid. IEEE Access 7, pp. 139909–139923, DOI: 10.1109/ACCESS.2019.2943886.
9.
Huang et al. 2020 – Huang, C., Zhao, Z., Wang, L., Zhang, Z. and Luo, X. 2020. Point and interval forecasting of solar irradiance with an active Gaussian process. IET Renewable Power Generation 14(6), pp. 1020–1030, DOI: 10.1049/iet-rpg.2019.0769.
10.
Huang et al. 2022 – Huang, X., Li, Q., Tai, Y., Chen, Z., Liu, J., Shi, J. and Liu, W. 2022. Time series forecasting for hourly photovoltaic power using conditional generative adversarial network and Bi-LSTM. Energy 246, DOI: 10.1016/j.energy.2022.123403.
11.
Jahani, B. and Mohammadi, B. 2019. A comparison between the application of empirical and ANN methods for estimation of daily global solar radiation in Iran. Theoretical and Applied Climatology 137, pp. 1257–1269, DOI: 10.1007/s00704-018-2666-3.
12.
Liu et al. 2022 – Liu, Y., Meenakshi, V., Karthikeyan, L., Maroušek, J., Krishnamoorthy, N.R., Sekar, M. and Xia, C. 2022. Machine learning based predictive modelling of micro gas turbine engine fueled with microalgae blends on using LSTM networks: An experimental approach. Fuel 322, pp. 1–8, DOI: 10.1016/j.fuel.2022.124183.
13.
Long et al. 2014 – Long, H., Zhang, Z. and Su, Y. 2014. Analysis of daily solar power prediction with data-driven approaches. Applied Energy 126, pp. 29–37, DOI: 10.1016/j.apenergy.2014.03.084.
14.
Metlek et al. 2021 – Metlek, S., Kayaalp, K., Basyigit, I. B., Genc, A. and Dogan, H. 2021. The dielectric properties prediction of the vegetation depending on the moisture content using the deep neural network model. International Journal of RF and Microwave Computer‐Aided Engineering 31(1), pp. 1–10, DOI: 10.1002/mmce.22496.
15.
Metlek, S. 2023. A new proposal for the prediction of an aircraft engine fuel consumption: a novel CNN-BiLSTM deep neural network model. Aircraft Engineering and Aerospace Technology 95(5), pp. 838–848, DOI: 10.1108/AEAT-05-2022-0132.
16.
Pan, C. and Tan, J. 2019. Day Ahead Hourly Forecasting of Solar Generation Based on Analysis and Ensemble Model. IEEE Access 7, pp. 112921–112930, DOI: 10.1109/ACCESS.2019.2935273.
17.
Pardeep et al. 2022 – Pardeep, S., Manoj, D. and Sumit, S. 2022. An ensemble method to forecast 24 h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network. Earth Science Informatics 15, pp. 291–306, DOI: 10.1007/s12145-021-00723-1.
18.
Ullah et al. 2019 – Ullah, F.U.M., Ullah, A., Haq, I.U., Rho, S. and Baik, S.W. 2019. Short-term prediction of residential power energy consumption via CNN and multi-layer bi-directional LSTM networks. IEEE Access 8, pp. 123369–123380, DOI: 10.1109/ACCESS.2019.2963045.
19.
Varghese et al. 2022 – Varghese, J., Anshuman, M., Sowmaye, T., Shruti, M., Sandeepkumar, S. and Sachi, N.M. 2022. A hybrid deep learning framework with CNN and Bi – directional LSTM for store item demand forecasting. Computers and Electrical Engineering 103, pp. 1–14, DOI: 10.1016/j.compeleceng.2022.108358.
20.
Voyant et al. 2016 – Voyant, C., Notton, G., Kalogirou, S., Nivet, M.L., Paoli, C., Motte, F. and Fouilloy, A. 2016. Machine Learning methods for solar radiation forecasting: a review. Renewable Energy 105, pp. 569–582, DOI: 10.1016/j.renene.2016.12.095.
21.
Wang et al. 2021 – Wang, H., Wang, J., Cao, L., Li, Y., Sun, Q. and Wang, J. 2021. A stock closing price prediction model based on CNN BiSLSTM. Complexity 2021, pp. 1–12, DOI: 10.1155/2021/5360828.
22.
Yu et al. 2019 – Yu, Y., Cao, J. and Zhu, J. 2019. An LSTM Short Term Solar Irradiance Forecasting Under Complicated Weather Conditions. IEEE Access 7, pp. 145651–145666, DOI: 10.1109/ACCESS.2019.2946057.
23.
Zhang et al. 2015 – Zhang, J., Florita, A., Hodge, B.M., Lu, S., Hamann, H.F., Banunarayanan, V. and Brockway, A.M. 2015. A suite of metrics for assessing the performance of solar power forecasting. Solar Energy 111, pp. 157–175, DOI: 10.1016/j.solener.2014.10.016.
24.
Zhuang, W. and Cao, Y. 2022. Short-Term Traffic Flow Prediction Based on CNN-BILSTM with Multicomponent Information. Applied Sciences 12(17), pp. 1–15, DOI: 10.3390/app12178714.
Share
RELATED ARTICLE
| eISSN: | 2720-569X |
| ISSN: | 1429-6675 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
