Enhance Solar Power Generation Using Advanced Computational Techniques for Improved Forecast Accuracy and Efficiency

Huiting Wei, Yongguang Chen, Qi Wang

Abstract


Solar energy forecasting using machine learning (ML) involves creating computational models to predict photovoltaic (PV) system output based on real-time and historical environmental data. This study applies ML regression techniques—Random Forest Regression (RFR), Support Vector Regression (SVR), and Light Gradient Boosting Machine Regression (LGBR)—to model solar energy generation using key input features such as solar irradiance, temperature, humidity, and panel specifications. Feature engineering processes, including missing value imputation, random permutation, and normalization, are employed to enhance input quality. To improve model performance, these regression models are hybridized with Fire Hawk Optimization (FHO), which fine-tunes hyperparameters to boost predictive accuracy. Performance is assessed using metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), R², Normalized Mean Square Error (NMSE), and Average Index of Optimization (AIO) across training, validation, and testing phases. In the training phase, the best results are achieved by LGFH (RMSE = 121), RFFH (RMSE = 140), and SVFH (RMSE = 152), showing that FHO integration significantly enhances prediction accuracy. The hybrid models display lower RMSE and improved robustness compared to standalone methods. Despite challenges posed by data variability and model complexity, the proposed methodology demonstrates reliable forecasting capabilities, contributing to improved energy management, grid stability, and better integration of solar power into renewable energy systems. Future work may involve extending the framework to broader datasets and refining optimization for enhanced generalization in diverse environments.


Keywords


Solar Generation, photovoltaic systems, Machine Learning, Metaheuristic Algorithm

Full Text:

PDF

References


M. D. A. Munnaf and T. Islam, “Enhancing Solar Energy Prospects: Predicting Direct Normal Irradiance in Qinghai Province Using ALO-RF Modeling,” Advances in Engineering and Intelligence Systems, vol. 003, no. 01, pp. 85–98, 2024, doi: 10.22034/aeis.2024.444686.1172.

A. Al Kassem, M. Al Ahmadi, and A. Draou, “Modeling and Simulation Analysis of a Hybrid PV-Wind Renewable Energy Sources for a Micro-Grid Application,” in 2021 9th International Conference on Smart Grid (icSmartGrid), 2021, pp. 103–106. doi: 10.1109/icSmartGrid52357.2021.9551215.

N. H. Alombah, J. N. Mungwe, A. Harrison, W. F. Mbasso, and H. B. Fotsin, “Advanced IoT-Based Monitoring System for Real-Time Photovoltaic Performance Evaluation: Conception, Development and Experimental Validation,” Sci Afr, p. e02763, 2025.

D. Y. Liu, J. Wang, X. Q. Feng, S. Guo, and C. Xu, “Investigation and analysis on the combined operation of solar thermal power and conventional thermal power,” in 2009 International Conference on Sustainable Power Generation and Supply, 2009, pp. 1–6. doi: 10.1109/SUPERGEN.2009.5348131.

N. H. Alombah, A. Harrison, W. F. Mbasso, H. Belghiti, H. B. Fotsin, P. Jangir, S. F. Al-Gahtani, and Z. M. S. Elbarbary., “Multiple-to-single maximum power point tracking for empowering conventional MPPT algorithms under partial shading conditions,” Sci Rep, vol. 15, no. 1, p. 14540, 2025.

Y. Iwasaki, K. Yukita, T. Hosoe, and K. Ikeda, “Basic study for the construction of a microgrid using small wind turbines as the main power source [PDF Not Yet Available In IEEE Xplore],” in 2021 9th International Conference on Smart Grid (icSmartGrid), 2021, p. 1. doi: 10.1109/icSmartGrid52357.2021.9551236.

H. A. Kazem, A. H. A. Al-Waeli, M. T. Chaichan, K. Sopian, A. S. Al Busaidi, and A. Gholami, “Photovoltaic-thermal systems applications as dryer for agriculture sector: A review,” Case Studies in Thermal Engineering, vol. 47, p. 103047, 2023.

V. Kamble, A. Bansode, T. Waghmare, and K. Bamane, “Development of Hybrid Compensators for Enhancing Power Quality in Electrical Distribution Systems Using Innovative Optimization Techniques,” 2025.

X. Wei, A. Harrison, A. T. Naser, W. F. Mbasso, I. Dagal, N. H. Alombah, P. Jangir, M. Sharaf, and M. El-Meligy, “A new intelligent control and advanced global optimization methodology for peak solar energy system performance under challenging shading conditions,” Appl Energy, vol. 390, p. 125808, 2025.

L. Navinkumar Rao, R. Somalwar, K. Joshi, and P. Sarathi Subudhi, “An Improved MPPT algorithm for Performance Improvement of 50 kW Grid Connected PV System,” 2025.

J. Wang, Z. Han, and Z. Guan, “Hybrid solar-assisted combined cooling, heating, and power systems: A review,” Renewable and Sustainable Energy Reviews, vol. 133, p. 110256, 2020.

A. Kasaeian, G. Nouri, P. Ranjbaran, and D. Wen, “Solar collectors and photovoltaics as combined heat and power systems: A critical review,” Energy Convers Manag, vol. 156, pp. 688–705, 2018.

A. Badiei, Y. G. Akhlaghi, X. Zhao, S. Shittu, X. Xiao, J. Li, Y. Fan, and G. Li, “A chronological review of advances in solar assisted heat pump technology in 21st century,” Renewable and Sustainable Energy Reviews, vol. 132, p. 110132, 2020.

M. M. Hasan, S. Hossain, M. Mofijur, Z. Kabir, I. A. Badruddin, T. M. Yunus Khan, and E. Jassim, “Harnessing solar power: a review of photovoltaic innovations, solar thermal systems, and the dawn of energy storage solutions,” Energies (Basel), vol. 16, no. 18, p. 6456, 2023.

B. Anand, R. Shankar, S. Murugavelh, W. Rivera, K. M. Prasad, and R. Nagarajan, “A review on solar photovoltaic thermal integrated desalination technologies,” Renewable and Sustainable Energy Reviews, vol. 141, p. 110787, 2021.

J. Chen, A. Harrison, N. H. Alombah, W. F. Mbasso, R. J. J. Molu, A. M. Alharbi, and P. Jangir, “Irradiance sensorless PSO-based Integral Backstepping and Immersion & invariance algorithm for robust MPPT control with real-climatic microcontroller-in-the-loop experimental validation,” Computers and Electrical Engineering, vol. 123, p. 110279, 2025.

Z. Rahimi-Ahar, M. S. Hatamipour, and L. R. Ahar, “Air humidification-dehumidification process for desalination: A review,” Prog Energy Combust Sci, vol. 80, p. 100850, 2020.

A. Omar, A. Nashed, Q. Li, G. Leslie, and R. A. Taylor, “Pathways for integrated concentrated solar power-Desalination: A critical review,” Renewable and Sustainable Energy Reviews, vol. 119, p. 109609, 2020.

A. Bamasag, E. Almatrafi, T. Alqahtani, P. Phelan, M. Ullah, M. Mustakeem, M. Obaid, and N. Ghaffour, “Recent advances and future prospects in direct solar desalination systems using membrane distillation technology,” J Clean Prod, vol. 385, p. 135737, 2023.

H. S. Son, M. W. Shahzad, N. Ghaffour, and K. C. Ng, “Pilot studies on synergetic impacts of energy utilization in hybrid desalination system: multi-effect distillation and adsorption cycle (MED-AD),” Desalination, vol. 477, p. 114266, 2020.

S. H. Son HyukSoo, M. W. Shahzad, N. G. Noreddine Ghaffour, and N. K. Ng KimChoon, “Pilot studies on synergetic impacts of energy utilization in hybrid desalination system: multi-effect distillation and adsorption cycle (MED-AD).,” 2020.

A. Modi, F. Bühler, J. G. Andreasen, and F. Haglind, “A review of solar energy based heat and power generation systems,” Renewable and Sustainable Energy Reviews, vol. 67, pp. 1047–1064, 2017.

L. Peng, S. Liu, R. Liu, and L. Wang, “Effective long short-term memory with differential evolution algorithm for electricity price prediction,” Energy, vol. 162, pp. 1301–1314, 2018.

A. Almalaq and J. J. Zhang, “Evolutionary deep learning-based energy consumption prediction for buildings,” ieee access, vol. 7, pp. 1520–1531, 2018.

K. Wang, X. Qi, and H. Liu, “Photovoltaic power forecasting based LSTM-Convolutional Network,” Energy, vol. 189, p. 116225, 2019.

S. Harbola and V. Coors, “One dimensional convolutional neural network architectures for wind prediction,” Energy Convers Manag, vol. 195, pp. 70–75, 2019.

H. Aprillia, H.-T. Yang, and C.-M. Huang, “Short-term photovoltaic power forecasting using a convolutional neural network–salp swarm algorithm,” Energies (Basel), vol. 13, no. 8, p. 1879, 2020.

D. Yu, W. Choi, M. Kim, and L. Liu, “Forecasting day-ahead hourly photovoltaic power generation using convolutional self-attention based long short-term memory,” Energies (Basel), vol. 13, no. 15, p. 4017, 2020.

S. Van Buuren and S. Van Buuren, Flexible imputation of missing data, vol. 10. CRC press Boca Raton, FL, 2012.

P. F. Smith, S. Ganesh, and P. Liu, “A comparison of random forest regression and multiple linear regression for prediction in neuroscience,” J Neurosci Methods, vol. 220, no. 1, pp. 85–91, 2013.

Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” J Comput Syst Sci, vol. 55, no. 1, pp. 119–139, 1997.

V. N. Vapnik, “The nature of statistical learning,” Theory, 1995.

V. Vapnik, “Statistical Learning Theory. New York: John Willey & Sons,” Inc, 1998.

J. Fan, X. Ma, L. Wu, F. Zhang, X. Yu, and W. Zeng, “Light Gradient Boosting Machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data,” Agric Water Manag, vol. 225, p. 105758, 2019.

X. Sun, M. Liu, and Z. Sima, “A novel cryptocurrency price trend forecasting model based on LightGBM,” Financ Res Lett, vol. 32, p. 101084, 2020.

M. A. Elaziz, A. Dahou, D. A. Orabi, S. Alshathri, E. M. Soliman, and A. A. Ewees, “A Hybrid Multitask Learning Framework with a Fire Hawk Optimizer for Arabic Fake News Detection,” Mathematics, vol. 11, no. 2, pp. 1–15, 2023.




DOI (PDF): https://doi.org/10.20508/ijrer.v15i2.16494.g9065

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is indexed in EI Compendex, SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics)and CrossRef.

IJRER has been indexed in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2025; 

h=35,

Average citation per item=6.59

Last three Years Impact Factor=(1947+1753+1586)/(146+201+78)=5286/425=12.43

Category Quartile:Q4