This paper proposes a model called X-LSTM-EO, which integrates explainable artificial intelligence (XAI), long short-term memory (LSTM), and equilibrium optimizer (EO) to reliably forecast solar power generation. The LSTM component forecasts power generation rates based on environmental conditions, while the EO component optimizes the LSTM model's hyper-parameters through training. The XAI-based Local Interpretable and Model-independent Explanation (LIME) is adapted to identify the critical factors that influence the accuracy of the power generation forecasts model in smart solar systems. The effectiveness of the proposed X-LSTM-EO model is evaluated through the use of five metrics; R-squared (R2), root mean square error (RMSE), coefficient of variation (COV), mean absolute error (MAE), and efficiency coefficient (EC). The proposed model gains values 0.99, 0.46, 0.35, 0.229, and 0.95, for R2, RMSE, COV, MAE, and EC respectively. The results of this paper improve the performance of the original model's conventional LSTM, where the improvement rate is; 148%, 21%, 27%, 20%, 134% for R2, RMSE, COV, MAE, and EC respectively. The performance of LSTM is compared with other machine learning algorithm such as Decision tree (DT), Linear regression (LR) and Gradient Boosting. It was shown that the LSTM model worked better than DT and LR when the results were compared. Additionally, the PSO optimizer was employed instead of the EO optimizer to validate the outcomes, which further demonstrated the efficacy of the EO optimizer. The experimental results and simulations demonstrate that the proposed model can accurately estimate PV power generation in response to abrupt changes in power generation patterns. Moreover, the proposed model might assist in optimizing the operations of photovoltaic power units. The proposed model is implemented utilizing TensorFlow and Keras within the Google Collab environment.

College of Business Administration Kuwait University Kuwait Kuwait

Department of Basic Engineering Science Faculty of Engineering Menoufia University Shebin El Kom Egypt

Faculty of Computers and AI Cairo University Giza Egypt

Faculty of Electrical Engineering and Computer Science VSB Technical University of Ostrava Ostrava Czech Republic

Faculty of Science Helwan University Helwan Egypt

Misr Higher Institute for Commerce and Computers Mansoura Egypt

Scientific Research School of Egypt Cairo Egypt

Zobrazit více v PubMed

Antonanzas J., Osorio N., Escobar R., Urraca R., Martinez-de-Pison F., & Antonanzas-Torres F. (2016, October). Review of photovoltaic power forecasting. Solar Energy, 136, 78–111. doi: 10.1016/j.solener.2016.06.069 DOI

Khan Z. A., Hussain T., & Baik S. W. (2023, May). Dual stream network with attention mechanism for photovoltaic power forecasting. Applied Energy, 338, 120916. doi: 10.1016/j.apenergy.2023.120916 DOI

Almasad A., Pavlak G., Alquthami T., & Kumara S. (2023). Site suitability analysis for implementing solar PV power plants using GIS and fuzzy MCDM based approach. Solar Energy, 249, 642–650.

Qing X.; Niu Y. Hourly Day-Ahead Solar Irradiance Prediction Using Weather Forecasts by LSTM. Energy 2018, 148, 461–468.

Sobri S.; Koohi-Kamali S.; Rahim N.A. Solar Photovoltaic Generation Forecasting Methods: A review. Energy Convers. Manag. 2018, 156, 459–497.

Alshammari A. (2023). Generation forecasting employing Deep Recurrent Neural Network with metaheruistic feature selection methodology for Renewable energy power plants. Sustainable Energy Technologies and Assessments, 55, 102968.

Yin R., & He J. (2023). Design of a photovoltaic electric bike battery-sharing system in public transit stations. Applied Energy, 332, 120505.

Zulfiqar M., Kamran M., Rasheed M. B., Alquthami T., & Milyani A. H. (2023). A hybrid framework for short term load forecasting with a navel feature engineering and adaptive grasshopper optimization in smart grid. Applied Energy, 338, 120829.

Osali, N. (2023, February). Optimal Scheduling of Active Distribution Networks Considering Dynamic Transformer Rating Under High Penetration of Renewable Energies. In 2023 8th International Conference on Technology and Energy Management (ICTEM) (pp. 1–7). IEEE.

Ahmed R., Sreeram V., Mishra Y., and Arif M. D., “A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization,” Renew. Sustain. Energy Rev., vol. 124, 2020, Art. no. 109792.

Khan M. H. R., & Righetti R. (2022). Ultrasound estimation of strain time constant and vascular permeability in tumors using a CEEMDAN and linear regression-based method. Computers in Biology and Medicine, 148, 105707. doi: 10.1016/j.compbiomed.2022.105707 PubMed DOI

Kim E., Akhtar M. S., & Yang O. B. (2023). Designing solar power generation output forecasting methods using time series algorithms. Electric Power Systems Research, 216, 109073.

Cervantes J., Garcia-Lamont F., Rodríguez-Mazahua L., & Lopez A. (2020). A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing, 408, 189–215.

Ali I. M. S., & Hariprasad D. (2023). Hyper-heuristic salp swarm optimization of multi-kernel support vector machines for big data classification. International Journal of Information Technology, 15(2), 651–663.

Zhu X., Li M., Liu X., & Zhang Y. (2024). A backpropagation neural network-based hybrid energy recognition and management system. Energy, 131264.

Song J., Krishnamurthy V., Kwasinski A., & Sharma R. (2013, April). Development of a Markov-Chain-Based Energy Storage Model for Power Supply Availability Assessment of Photovoltaic Generation Plants. IEEE Transactions on Sustainable Energy, 4(2), 491–500. 10.1109/tste.2012.2207135 DOI

Long H., Zhang Z., & Su Y. (2014, August). Analysis of daily solar power prediction with data-driven approaches. Applied Energy, 126, 29–37. 10.1016/j.apenergy.2014.03.084 DOI

Phan Q. T., Wu Y. K., Phan Q. D., & Lo H. Y. (2022, May 2). A Novel Forecasting Model for Solar Power Generation by a Deep Learning Framework with Data Preprocessing and Postprocessing. 2022 IEEE/IAS 58th Industrial and Commercial Power Systems Technical Conference (I&CPS). 10.1109/icps54075.2022.9773862 DOI

Mat Daut M. A., Hassan M. Y., Abdullah H., Rahman H. A., Abdullah M. P., & Hussin F. (2017, April). Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: A review. Renewable and Sustainable Energy Reviews, 70, 1108–1118. 10.1016/j.rser.2016.12.015 DOI

Ugurlu U., Oksuz I., & Tas O. (2018, May 14). Electricity Price Forecasting Using Recurrent Neural Networks. Energies, 11(5), 1255. 10.3390/en11051255 PubMed DOI PMC

Qing X., & Niu Y. (2018, April). Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy, 148, 461–468. 10.1016/j.energy.2018.01.177. DOI

Abdel-Nasser M., & Mahmoud K. (2017, October 14). Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural Computing and Applications, 31(7), 2727–2740. 10.1007/s00521-017-3225-z DOI

He Y., Gao Q., Jin Y., & Liu F. (2022). Short-term photovoltaic power forecasting method based on convolutional neural network. Energy Reports, 8, 54–62.

Singla P., Duhan M., & Saroha S. (2022). A hybrid solar irradiance forecasting using full wavelet packet decomposition and bi-directional long short-term memory (BiLSTM). Arabian Journal for Science and Engineering, 47(11), 14185–14211.

Singla P., Duhan M., & Saroha S. (2023). A point and interval forecasting of solar irradiance using different decomposition based hybrid models. Earth Science Informatics, 16(3), 2223–2240.

Singla P., Duhan M., & Saroha S. (2023). An integrated framework of robust local mean decomposition and bidirectional long short-term memory to forecast solar irradiance. International Journal of Green Energy, 20(10), 1073–1085.

Phan Q. T., Wu Y. K., Phan Q. D., & Lo H. Y. (2022). A novel forecasting model for solar power generation by a deep learning framework with data preprocessing and postprocessing. IEEE Transactions on Industry Applications, 59(1), 220–231.

Sabir D., Hafeez K., Batool S., Akbar G., Khan L., Hafeez G., et al.. (2024). Prediction of Solar PV power using Deep Learning with Correlation-based Signal Synthesis. IEEE Access.

Wang Z., Zhang Y., Li G., Zhang J., Zhou H., & Wu J. (2024). A novel solar irradiance forecasting method based on multi-physical process of atmosphere optics and LSTM-BP model. Renewable Energy, 120367.

Ibrahim M. S., Gharghory S. M., & Kamal H. A. (2024). A hybrid model of CNN and LSTM autoencoder-based short-term PV power generation forecasting. Electrical Engineering, 1–17.

Ehteram M., Nia M. A., Panahi F., & Farrokhi A. (2024). Read-First LSTM model: A new variant of long short term memory neural network for predicting solar radiation data. Energy Conversion and Management, 305, 118267.

Hong Y. Y., & Martinez J. J. F. (2024). Forecasting solar irradiation using convolutional long short-term memory and feature selection of data from neighboring locations. Sustainable Energy, Grids and Networks, 38, 101271.

Liu W., & Mao Z. (2024). Short-term photovoltaic power forecasting with feature extraction and attention mechanisms. Renewable Energy, 120437.

Bukhari SM, Moosavi SK, Zafar MH, Mansoor M, Mohyuddin H, Ullah SS, et al.. Federated transfer learning with orchard-optimized Conv-SGRU: A novel approach to secure and accurate photovoltaic power forecasting. Renewable Energy Focus. 2024. Mar 1;48:100520.

Abou Houran M, Bukhari SM, Zafar MH, Mansoor M, Chen W. COA-CNN-LSTM: Coati optimization algorithm-based hybrid deep learning model for PV/wind power forecasting in smart grid applications. Applied Energy. 2023. Nov 1;349:121638.

Khan UA, Khan NM, Zafar MH. Resource efficient PV power forecasting: Transductive transfer learning based hybrid deep learning model for smart grid in Industry 5.0. Energy Conversion and Management: X. 2023. Oct 1;20:100486.

Faramarzi A., Heidarinejad M., Stephens B., &Mirjalili S. (2020). Equilibrium optimizer: A novel optimization algorithm. Knowledge-Based Systems, 191, 105190.

Kawakura S., Hirafuji M., Ninomiya S., & Shibasaki R. (2022). Analyses of Diverse Agricultural Worker Data with Explainable Artificial Intelligence: XAI based on SHAP, LIME, and LightGBM. European Journal of Agriculture and Food Sciences, 4(6), 11–19. 10.24018/ejfood.2022.4.6.348. DOI

https://www.kaggle.com/datasets/anikannal/solar-power-generation-data?select=Plant_1_Generation_Data.csv.

Urbanowicz R. J., Meeker M., La Cava W., Olson R. S., & Moore J. H. (2018, September). Relief-based feature selection: Introduction and review. Journal of Biomedical Informatics, 85, 189–203. doi: 10.1016/j.jbi.2018.07.014 PubMed DOI PMC

Ziegel E., Press W., Flannery B., Teukolsky S., & Vetterling W. (1987, November). Numerical Recipes: The Art of Scientific Computing. Technometrics, 29(4), 501. 10.2307/1269484. DOI

Kumar S., & Chong I. (2018, December 19). Correlation Analysis to Identify the Effective Data in Machine Learning: Prediction of Depressive Disorder and Emotion States. International Journal of Environmental Research and Public Health, 15(12), 2907. doi: 10.3390/ijerph15122907 PubMed DOI PMC

https://center4ee.org/how-solar-energy-works/

Joseph V. R. (2022, April 4). Optimal ratio for data splitting. Statistical Analysis and Data Mining: The ASA Data Science Journal, 15(4), 531–538. 10.1002/sam.11583 DOI

Zayed M. E., Zhao J., Li W., Elsheikh A. H., & Elaziz M. A. (2021, November). A hybrid adaptive neuro-fuzzy inference system integrated with equilibrium optimizer algorithm for predicting the energetic performance of solar dish collector. Energy, 235, 121289. 10.1016/j.energy.2021.121289 DOI

Code Adam Optimization Algorithm From Scratch by Jason Brownlee on January 13, 2021 in Optimization. https://machinelearningmastery.com/adam-optimization-from-scratch/

Freitas D., Lopes L. G., & Morgado-Dias F. (2020, March 21). Particle Swarm Optimisation: A Historical Review Up to the Current Developments. Entropy, 22(3), 362. doi: 10.3390/e22030362 PubMed DOI PMC

Zheng J., Zhang H., Dai Y., Wang B., Zheng T., Liao Q., et al.. (2020, January). Time series prediction for output of multi-region solar power plants. Applied Energy, 257, 114001. 10.1016/j.apenergy.2019.114001 DOI

Wang K., Qi X., & Liu H. (2019, December). Photovoltaic power forecasting based LSTM-Convolutional Network. Energy, 189, 116225. 10.1016/j.energy.2019.116225 DOI

Wang K., Qi X., & Liu H. (2019, October). A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network. Applied Energy, 251, 113315. 10.1016/j.apenergy.2019.113315 DOI

Saxena N., Kumar R., Rao Y. K. S. S., Mondloe D. S., Dhapekar N. K., Sharma A., et al.. (2024, January). Hybrid KNN-SVM machine learning approach for solar power forecasting. Environmental Challenges, 14, 100838. 10.1016/j.envc.2024.100838. DOI

Salau A. O., & Alitasb G. K. (2024, March). MPPT efficiency enhancement of a grid connected solar PV system using Finite Control set model predictive controller. Heliyon, 10(6), e27663. doi: 10.1016/j.heliyon.2024.e27663 PubMed DOI PMC

Krishna V. M., Duvvuri S. S., Sobhan P. V., Yadlapati K., Sandeep V., & Narendra B. (2024, March). Experimental study on excitation phenomena of renewable energy source driven induction generator for isolated rural community loads. Results in Engineering, 21, 101761. 10.1016/j.rineng.2024.101761 DOI