Long-term solar radiation forecasting based on LSTM and attention mechanism: a case study in Algeria

Authors

  • Ali Teta
  • Maissa Medkour
  • Abdelaziz Rabehi
  • Belkacem Korich
  • Derradji Bakria

DOI:

https://doi.org/10.54021/seesv5n1-058

Keywords:

solar radiation, Forecasting, ANN, LSTM, BiLSTM, attention mechanism

Abstract

The growing adoption of photovoltaic (PV) energy in urban areas underscores its capability to meet energy demands effectively. The accurate forecasting of meteorological parameters, particularly global solar radiation, is paramount for the efficient management and utilization of solar energy resources. Solar radiation forecasting methods typically fall into two main categories: cloud imagery combined with physical approaches, and Artificial Intelligence (AI) based methods. Due to the non-stationary nature of solar radiation and the high nonlinearity of atmospheric conditions, conventional forecasting approaches often exhibit poor accuracy. Artificial intelligence based approaches, such as machine learning and deep learning algorithms, are extensively employed in global solar radiation forecasting research, demonstrating impressive accuracy.  In this respect, this paper presents a novel approach for long term monthly forecasting of global solar radiation using a Bidirectional Long Short-Term Memory (LSTM) architecture augmented with an attention mechanism that includes a Squeeze and Excitation (SE) block (SE-BiLSTM). The effectiveness of this model is extensively evaluated for long-term monthly solar radiation forecasting using meteorological data collected over a 20-year period (from Jan 2001 to Dec 2020) from the National Aeronautics and Space Administration (NASA). The proposed SE-BiLSTM model is compared with well-established forecasting models including Naïve, Autoregressive Moving Average (ARMA), Multi-layer Perceptron (MLP), LSTM, and Bidirectional LSTM. Through rigorous simulation tests, our model demonstrates superior performance, achieving the lowest mean absolute percentage error (MAPE) of 4.52% and mean absolute error (MAE) of 7.89 kW/m2. This advancement holds significant promise for enhancing solar energy forecasting accuracy and its practical application in renewable energy systems.

References

BELMAHDI, B., LOUZAZNI, M., EL BOUARDI, A. One month-ahead forecasting of mean daily global solar radiation using time series models. Optik, v. 219, 165207, 2020. doi: https://doi.org/10.1016/j.ijleo.2020.165207

FISCHER, T., KRAUSS, C. Deep learning with long short-term memory networks for financial market predictions. European journal of operational research, v. 270, n. 2, p. 654-669, 2018. doi: https://doi.org/10.1016/j.ejor.2017.11.054

FLORES, J. J., GRAFF, M., RODRIGUEZ, H. Evolutive design of ARMA and ANN models for time series forecasting. Renewable Energy, v. 44, p. 225-230, 2012. doi: https://doi.org/10.1016/j.renene.2012.01.084

GHIMIRE, S., DEO, R. C., CASILLAS-PÉREZ, D., SALCEDO-SANZ, S., SHARMA, E., ALI, M. Deep learning CNN-LSTM-MLP hybrid fusion model for feature optimizations and daily solar radiation prediction. Measurement, v. 202, p. 111759, 2022. doi: https://doi.org/10.1016/j.measurement.2022.111759

HUANG, X., LI, Q., TAI, Y., CHEN, Z., ZHANG, J., SHI, J. et al. Hybrid deep neural model for hourly solar irradiance forecasting. Renewable Energy, 171, p.1041-1060, 2021. doi: https://doi.org/10.1016/j.renene.2021.02.161

KHELIFI, R., GUERMOUI, M., RABEHI, A., TAALLAH, A., ZOUKEL, A., GHONEIM, S. S. et al. Short-term PV power forecasting using a hybrid TVF-EMD-ELM strategy. International Transactions on Electrical Energy Systems, v. 2023, p. 1-14, 2023. doi: https://doi.org/10.1155/2023/6413716

MERRA-2 Project. (n.d.). Retrieved November 10, 2022, from http://www.sodapro.

com/webservices/meteodata

MOHAMAD RADZI, P. N. L., AKHTER, M. N., MEKHILEF, S., MOHAMED SHAH, N. Review on the application of photovoltaic forecasting using machine learning for very short-to long-term forecasting. Sustainability, v. 15, n. 4, p. 2942, 2023. doi: https://doi.org/10.3390/su15042942

PENG, T., ZHANG, C., ZHOU, J., NAZIR, M. S. An integrated framework of Bi-directional long-short term memory (BiLSTM) based on sine cosine algorithm for hourly solar radiation forecasting. Energy, v. 221, p. 119887, 2021. doi: https://doi.org/10.1016/j.energy.2021.119887

RAHIMI, N., PARK, S., CHOI, W., OH, B., KIM, S., CHO, Y. H., et al. A comprehensive review on ensemble solar power forecasting algorithms. Journal of Electrical Engineering & Technology, v. 18, n. 2, p. 719-733, 2023. doi: https://doi.org/10.1007/s42835-023-01378-2

RODRÍGUEZ, F., FLEETWOOD, A., GALARZA, A., FONTÁN, L. Predicting solar energy generation through artificial neural networks using weather forecasts for microgrid control. Renewable energy, v. 126, p. 855-864, 2018. doi: https://doi.org/10.1016/j.renene.2018.03.070

SHARADGA, H., HAJIMIRZA, S., BALOG, R. S. (2020). Time series forecasting of solar power generation for large-scale photovoltaic plants. Renewable Energy, 150, 797-807. doi: https://doi.org/10.1016/j.renene.2019.12.131

SOBRI, S., KOOHI-KAMALI, S., RAHIM, N. A. Solar photovoltaic generation forecasting methods: A review. Energy conversion and management, v. 156, 459-497, 2018. doi: https://doi.org/10.1016/j.enconman.2017.11.019

TAI, B., YU, L., HUANG, Y., WANG, J., WANG, Y., ZHU, Y., et al. Power prediction of photovoltaic power generation based on LSTM model with additive Attention mechanism. In: 2023 7th International Conference on Smart Grid and Smart Cities (ICSGSC). IEEE, Sep 2023. p. 474-480. doi: https://doi.org/10.1109/ICSG

SC59580.2023.10319231

VAN DER MEER, D. W., WIDÉN, J., MUNKHAMMAR, J. Review on probabilistic forecasting of photovoltaic power production and electricity consumption. Renewable and Sustainable Energy Reviews, v. 81, p. 1484-1512, 2018. doi: https://doi.org/10.1016/j.rser.2017.05.212

WANG, Y., WANG, D., TANG, Y. (2020). Clustered hybrid wind power prediction model based on ARMA, PSO-SVM, and clustering methods. IEEE access, 8, 17071-17079. doi: https://doi.org/10.1109/ACCESS.2020.2968390

WU, X., SU, Y., SUN, Y., YANG, H., ZHEN, Z., WANG, F. A minutely solar irradiance forecasting method based on multidimensional feature extraction using all-sky images. In: (2023) IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference (I&CPS) IEEE, May 2023. p. 1-7. doi: https://doi.org/10.1109/ICPS57144.2023.10142089

YAMAK, P. T., YUJIAN, L., GADOSEY, P. K. A comparison between arima, lstm, and gru for time series forecasting. In: Proceedings of the 2019 2nd international conference on algorithms, computing and artificial intelligence Dec 2019. p. 49-55. doi: https://doi.org/10.1145/3377713.3377722

YILDIRIM, A., BILGILI, M., OZBEK, A. One-hour-ahead solar radiation forecasting by MLP, LSTM, and ANFIS approaches. Meteorology and Atmospheric Physics, v. 135, n. 1, p. 10, 2023. doi: https://doi.org/10.1007/s007

-022-00946-x

Downloads

Published

2024-04-15

How to Cite

Teta, A., Medkour, M., Rabehi, A., Korich, B., & Bakria, D. (2024). Long-term solar radiation forecasting based on LSTM and attention mechanism: a case study in Algeria. STUDIES IN ENGINEERING AND EXACT SCIENCES, 5(1), 1117–1134. https://doi.org/10.54021/seesv5n1-058