10.1007/s40095-022-00530-4

Predicting photovoltaic power generation using double-layer bidirectional long short-term memory-convolutional network

  • Mohammed Sabri*1,
  • Mohammed El Hassouni2,
  1. LRIT, Mohammed V University in Rabat, Rabat, 1014, MA
  2. FLSH, Mohammed V University in Rabat, Rabat, 1014, MA

Published in Issue 2022-09-28

How to Cite

Sabri, M., & El Hassouni, M. (2022). Predicting photovoltaic power generation using double-layer bidirectional long short-term memory-convolutional network. International Journal of Energy and Environmental Engineering, 14(3 (September 2023). https://doi.org/10.1007/s40095-022-00530-4
Crossref
Scopus
Google Scholar
Europe PMC

Abstract

Abstract Accurate photovoltaic (PV) power prediction is critical for PV power plant safety and stability. The main restrictions influencing the accuracy of the PV power forecast are the variability and intermittency of solar energy. Therefore, this study proposes a hybrid deep learning model for PV power forecast that is successfully developed using the combination of the bidirectional long short-term memory (BLSTM) and convolutional neural network (CNN) and is applied to the actual dataset collected in the DKASC PV system in Alice Springs, Australia. The proposed architecture is a structure of two major branches. BLSTM is used first to extract the bidirectional temporal characteristics of PV power. Next, CNN was used to capture the spatial characteristics. The prediction results of the hybrid model are compared with those of the single model LSTM, BLSTM, CNN, gated recurrent unit, recurrent neural network (RNN), and the hybrid network (LSTM–CNN, CNN–LSTM) in order to demonstrate the higher performance of the proposed hybrid prediction model. By comparing statistical performance indicators such as root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), and coefficient of determination ( R 2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^2$$\end{document} ) values with other existing deep learning models, the performance of the proposed BLSTM–CNN model has been demonstrated. The results indicate that the BLSTM–CNN model has the highest precision with the lowest MSE of 0.0089, MAE of 0.0531, RMSE of 0.0944, and highest R 2 of 0.9993. BLSTM–CNN can enhance forecasting accuracy while also accurately capturing the various temporal–spatial characteristics of PV power.

Keywords

  • Photovoltaic power forecasting,
  • Deep learning,
  • Bidirectional long short-term memory,
  • Convolutional neural network

References

  1. Abdel-Basset et al. (2021) Pv-net: an innovative deep learning approach for efficient forecasting of short-term photovoltaic energy production 303(127)
  2. Agoua et al. (2017) Short-term spatio-temporal forecasting of photovoltaic power production 9(2) (pp. 538-546) https://doi.org/10.1109/TSTE.2017.2747765
  3. Behera et al. (2018) Solar photovoltaic power forecasting using optimized modified extreme learning machine technique 21(3) (pp. 428-438)
  4. Chen et al. (2020) Very-short-term power prediction for PV power plants using a simple and effective RCC-LSTM model based on short term multivariate historical datasets 9(2) https://doi.org/10.3390/electronics9020289
  5. Cheng et al. (2019) A hybrid electricity price forecasting model with Bayesian optimization for German energy exchange (pp. 653-666) https://doi.org/10.1016/j.ijepes.2019.03.056
  6. Chu et al. (2015) Short-term reforecasting of power output from a 48 MWe solar PV plant (pp. 68-77) https://doi.org/10.1016/j.solener.2014.11.017
  7. Das et al. (2018) Forecasting of photovoltaic power generation and model optimization: a review (pp. 912-928) https://doi.org/10.1016/j.rser.2017.08.017
  8. De Giorgi et al. (2014) Photovoltaic power forecasting using statistical methods: impact of weather data 8(3) (pp. 90-97) https://doi.org/10.1049/iet-smt.2013.0135
  9. Díaz-Vico et al. (2017) Deep neural networks for wind and solar energy prediction 46(3) (pp. 829-844) https://doi.org/10.1007/s11063-017-9613-7
  10. DKASC Alice Springs (2021) 1B: Trina.
  11. http://dkasolarcentre.com.au/locations/alice-springs?source=1B
  12. Dolara et al. (2015) Comparison of different physical models for PV power output prediction (pp. 83-99) https://doi.org/10.1016/j.solener.2015.06.017
  13. Du et al. (2018) Multi-step ahead forecasting in electrical power system using a hybrid forecasting system (pp. 533-550) https://doi.org/10.1016/j.renene.2018.01.113
  14. Gao et al. (2019) Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM 187(115)
  15. He et al. (2022) Novel double-layer bidirectional LSTM network with improved attention mechanism for predicting energy consumption (pp. 350-360) https://doi.org/10.1016/j.isatra.2021.08.030
  16. Hinton and Salakhutdinov (2006) Reducing the dimensionality of data with neural networks 313(5786) (pp. 504-507) https://doi.org/10.1126/science.1127647
  17. Hochreiter and Schmidhuber (1997) Long short-term memory 9(8) (pp. 1735-1780) https://doi.org/10.1162/neco.1997.9.8.1735
  18. Hopfield (1982) Neural networks and physical systems with emergent collective computational abilities 79(8) (pp. 2554-2558) https://doi.org/10.1073/pnas.79.8.2554
  19. Hossain et al. (2017) Application of extreme learning machine for short term output power forecasting of three grid-connected PV systems (pp. 395-405) https://doi.org/10.1016/j.jclepro.2017.08.081
  20. Hu et al. (2018) A seasonal model using optimized multi-layer neural networks to forecast power output of PV plants 11(2) https://doi.org/10.3390/en11020326
  21. Jaihuni et al. (2022) A novel recurrent neural network approach in forecasting short term solar irradiance (pp. 63-74) https://doi.org/10.1016/j.isatra.2021.03.043
  22. Jammeli et al. (2021) Sequential artificial intelligence models to forecast urban solid waste in the city of Sousse, Tunisia https://doi.org/10.1109/TEM.2021.3081609
  23. Joseph, L.L., Goel, P., Jain, A., et al.: A novel hybrid deep learning algorithm for smart city traffic congestion predictions. In: 2021 6th International Conference on Signal Processing, pp. 561–565. Computing and Control (ISPCC), IEEE (2021)
  24. Kim and Cho (2019) Predicting residential energy consumption using CNN-LSTM neural networks (pp. 72-81) https://doi.org/10.1016/j.energy.2019.05.230
  25. Kulshrestha et al. (2020) Bayesian BILSTM approach for tourism demand forecasting 83(102)
  26. Lan et al. (2011) ARMA model of the solar power station based on output prediction 48(2) (pp. 31-35)
  27. Lawal et al. (2021) Wind speed prediction using hybrid 1d CNN and BLSTM network (pp. 156-679) https://doi.org/10.1109/ACCESS.2021.3129883
  28. Lee and Kim (2021) PV power prediction in a peak zone using recurrent neural networks in the absence of future meteorological information (pp. 1098-1110) https://doi.org/10.1016/j.renene.2020.12.021
  29. Li et al. (2020) The short-term interval prediction of wind power using the deep learning model with gradient descend optimization (pp. 197-211) https://doi.org/10.1016/j.renene.2020.03.098
  30. Li et al. (2020) A hybrid deep learning model for short-term PV power forecasting 259(114)
  31. Liu (2019) China’s renewable energy law and policy: a critical review (pp. 212-219) https://doi.org/10.1016/j.rser.2018.10.007
  32. Malvoni et al. (2016) Data on support vector machines (SVM) model to forecast photovoltaic power (pp. 13-16) https://doi.org/10.1016/j.dib.2016.08.024
  33. Mellit et al. (2020) Advanced methods for photovoltaic output power forecasting: a review 10(2) https://doi.org/10.3390/app10020487
  34. Miao et al. (2018) Markov chain model for solar farm generation and its application to generation performance evaluation (pp. 905-917) https://doi.org/10.1016/j.jclepro.2018.03.173
  35. Nguyen et al. (2021) A new method for forecasting energy output of a large-scale solar power plant based on long short-term memory networks a case study in Vietnam 199(107)
  36. Nguyen Dinh, T., Phan Hoang, N.: Air pollution forecasting using regression models and lstm deep learning models for Vietnam. In: International Conference on Future Data and Security Engineering, Springer, 264–275 (2021)
  37. Ogliari et al. (2017) Physical and hybrid methods comparison for the day ahead PV output power forecast (pp. 11-21) https://doi.org/10.1016/j.renene.2017.05.063
  38. Pan et al. (2020) Photovoltaic power forecasting based on a support vector machine with improved ant colony optimization 277(123)
  39. Peng et al. (2021) An integrated framework of Bi-directional long-short term memory (BiLSTM) based on sine cosine algorithm for hourly solar radiation forecasting 221(119)
  40. Sabri and El Hassouni (2022) A comparative study of LSTM and RNN for photovoltaic power forecasting (pp. 265-274) Springer https://doi.org/10.1007/978-3-030-94188-8_25
  41. Sabri, M., El Hassouni, M.: A novel deep learning approach for short term photovoltaic power forecasting based on GRU-CNN model. In: E3S Web of Conferences, EDP Sciences, 00064 (2022)
  42. Sabri and El Hassouni (2022) Accurate photovoltaic power prediction models based on deep convolutional neural networks and gated recurrent units 44(3) (pp. 6303-6320)
  43. Sanjari and Gooi (2016) Probabilistic forecast of PV power generation based on higher order Markov chain 32(4) (pp. 2942-2952) https://doi.org/10.1109/TPWRS.2016.2616902
  44. Shi et al. (2020) Expected output calculation based on inverse distance weighting and its application in anomaly detection of distributed photovoltaic power stations https://doi.org/10.1016/j.jclepro.2020.119965
  45. Srivastava et al. (2014) Dropout: a simple way to prevent neural networks from overfitting 15(1) (pp. 1929-1958)
  46. Tovar et al. (2020) PV power prediction, using CNN-LSTM hybrid neural network model Case of study: Temixco-Morelos, Mexico 13(24) https://doi.org/10.3390/en13246512
  47. Ünal et al. (2021) A novel load forecasting approach based on smart meter data using advance preprocessing and hybrid deep learning 11(6) https://doi.org/10.3390/app11062742
  48. Voyant et al. (2017) Machine learning methods for solar radiation forecasting: a review (pp. 569-582) https://doi.org/10.1016/j.renene.2016.12.095
  49. Wang et al. (2017) Deterministic and probabilistic forecasting of photovoltaic power based on deep convolutional neural network (pp. 409-422) https://doi.org/10.1016/j.enconman.2017.10.008
  50. Wang et al. (2019) A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network 251(113)
  51. Wang et al. (2019) Photovoltaic power forecasting based LSTM-convolutional network 189(116)
  52. Wang, S., Wang, Y., Cheng, Y., et al.: An improved model for power prediction of PV system based on Elman neural networks. In: 2020 Asia Energy and Electrical Engineering Symposium (AEEES), IEEE, 902–907 (2020)
  53. Wang (2010) The analysis of the impacts of energy consumption on environment and public health in China 35(11) (pp. 4473-4479) https://doi.org/10.1016/j.energy.2009.04.014
  54. Wojtkiewicz et al. (2019) Hour-ahead solar irradiance forecasting using multivariate gated recurrent units 12(21) https://doi.org/10.3390/en12214055
  55. Wu et al. (2021) Ultra-short-term multi-step wind power forecasting based on CNN-LSTM 15(5) (pp. 1019-1029) https://doi.org/10.1049/rpg2.12085
  56. Yamada et al. (2014) Prediction of next day solar power generation by gray theory and neural networks 134(6) (pp. 494-500)
  57. Yan and Hy (2022) A sea clutter detection method based on LSTM error frequency domain conversion 61(1) (pp. 883-891) https://doi.org/10.1016/j.aej.2021.04.084
  58. Zhen et al. (2020) A hybrid deep learning model and comparison for wind power forecasting considering temporal-spatial feature extraction 12(22) https://doi.org/10.3390/su12229490
  59. Zhen et al. (2021) Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information https://doi.org/10.1016/j.energy.2021.120908
  60. Zhou et al. (2020) Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine https://doi.org/10.1016/j.energy.2020.117894