Machine Learning and Deep Learning Approaches for Optimal Solar Panel Tilt Angle Prediction Using Meteorological Data from Kano, Nigeria

Oreoluwa Michael Adenuga; Tosin Emmanuel Ariyo; Prof Peter Olabisi Oluseyi

doi:10.56201/wjimt.v10.no7.2026.pg1.26

📄 Download Paper

Machine Learning and Deep Learning Approaches for Optimal Solar Panel Tilt Angle Prediction Using Meteorological Data from Kano, Nigeria

Oreoluwa Michael Adenuga, Tosin Emmanuel Ariyo, Prof Peter Olabisi Oluseyi

Abstract

The energy yield of photovoltaic installations depends critically on panel orientation, yet most installations in developing regions rely on fixed tilt angles chosen by rule of thumb. This study develops and compares classical machine learning and deep learning models for predicting the optimal hourly tilt angle of solar panels using multi-year meteorological measurements from the Kano region of Nigeria. A timestamped dataset of global horizontal irradiance, direct normal irradiance, diffuse horizontal irradiance, module temperature, wind speed, and relative humidity was cleaned, deduplicated, and enriched through feature engineering, including derivation of the clearness index from extraterrestrial irradiance, a fixed surface albedo of 0.23, solar zenith angle computation from site geometry, and specific humidity estimation from the Tetens relation. The target tilt angle was defined from the solar zenith angle. Four regression models were trained with cross-validation: linear regression, decision tree, random forest, and XGBoost. Hyperparameter tuning with randomized search showed XGBoost (RMSE 1.94) and random forest (RMSE 3.06) far outperforming linear regression (RMSE 564.25). A stacked long short-term memory network with 128 and 64 units, trained on 120-hour input windows with early stopping, achieved the best performance with an RMSE of 0.24, and test-set residuals largely fell within plus or minus 5 degrees. Predicted tilt profiles reproduced physically expected behaviour: diurnal peaks near solar noon, a seasonal cycle peaking at about 3.1 degrees in June and July and falling to about

Keywords

solar tilt angle; machine learning; LSTM; XGBoost; random forest; solar tracking; clearness index; Nigeria

References

[1] J. A. Duffie and W. A. Beckman, Solar Engineering of Thermal Processes, 4th ed. Hoboken, NJ, USA: Wiley, 2013. [2] R. Eke and A. Senturk, 'Performance comparison of a double-axis sun tracking versus fixed PV system,' Solar Energy, vol. 86, no. 9, pp. 2665-2672, 2012, doi: 10.1016/j.solener.2012.06.006. [3] F. E. Tahiri, K. Chikh, and M. Khafallah, 'Optimal management energy system and control strategies for isolated hybrid solar-wind-battery-diesel power system,' Emerging Science Journal, vol. 5, no. 2, pp. 111-124, 2021, doi: 10.28991/esj-2021-01262. [4] B. Y. H. Liu and R. C. Jordan, 'The interrelationship and characteristic distribution of direct, diffuse and total solar radiation,' Solar Energy, vol. 4, no. 3, pp. 1-19, 1960. [5] M. Z. Jacobson and V. Jadhav, 'World estimates of PV optimal tilt angles and ratios of sunlight incident upon tilted and tracked PV panels relative to horizontal panels,' Solar Energy, vol. 169, pp. 55-66, 2018. [6] A. Basem, S. Opakhai, Z. M. S. Elbarbary, F. Atamurotov, and N. E. Benti, 'A comprehensive analysis of advanced solar panel productivity and efficiency through numerical models and emotional neural networks,' Scientific Reports, vol. 15, no. 1, pp. 1-17, 2025, doi: 10.1038/s41598-024-70682-2. [7] C. Voyant et al., 'Machine learning methods for solar radiation forecasting: A review,' Renewable Energy, vol. 105, pp. 569-582, 2017. [8] S. E. Aifuwa, T. O. Oshoba, E. Ogbuefi, P. N. Ike, S. B. Nnabueze, and J. Olatunde-Thorpe, 'Predictive analytics models enhancing supply chain demand forecasting accuracy and reducing inventory management inefficiencies,' International Journal of Multidisciplinary Research and Growth Evaluation, vol. 1, no. 3, pp. 171-181, 2020, doi: 10.54660/. IJMRGE.2020.1.3.171-181. [9] M. I. Atakpa, T. O. Abolaji, and N. F. Abetoh, 'Statistical time-series models for long-range public health trend forecasting: A review and conceptual framework,' International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 10, no. 6, pp. 2748-2780, 2024, doi: 10.32628/CSEIT2410792. [10] K. A. Kuterbekov, A. M. Kabyshev, K. Z. Bekmyrza, M. M. Kubenova, and A. T. Ayalew, 'How can solar panels collectors enhance energy efficiency? Utilization of the novel optimization techniques,' International Journal of Low-Carbon Technologies, vol. 19, pp. 1049-1059, 2024, doi: 10.1093/ijlct/ctae048. [11] J. R. B. del Rosario and E. P. Dadios, 'Design and optimization of photovoltaic solar energy in a small domesticated establishment (an integrative review),' Journal of Advanced Management Science, vol. 1, no. 1, pp. 160-164, 2013, doi: 10.12720/joams.1.1.160-164. [12] J. Robert and B. Rosario, 'Development of a fuzzy logic-based PV solar tracking system simulated using QT fuzzy engine,' 2015. [13] T. Esram and P. L. Chapman, 'Comparison of photovoltaic array maximum power point tracking techniques,' IEEE Transactions on Energy Conversion, vol. 22, no. 2, pp. 439-449, 2007. [14] V. H. U. Eze et al., 'Development of maximum power point tracking algorithm based on Improved Optimized Adaptive Differential Conductance Technique for renewable energy generation,' Heliyon, vol. 11, no. 1, p. e41344, 2025, doi: 10.1016/j.heliyon. 2024.e41344. [15] I. Reda and A. Andreas, 'Solar position algorithm for solar radiation applications,' Solar Energy, vol. 76, no. 5, pp. 577-589, 2004. [16] E. Skoplaki and J. A. Palyvos, 'On the temperature dependence of photovoltaic module electrical performance: A review of efficiency/power correlations,' Solar Energy, vol. 83, no. 5, pp. 614-624, 2009. [17] T. Huld et al., 'A power-rating model for crystalline silicon PV modules,' Solar Energy Materials and Solar Cells, vol. 95, no. 12, pp. 3359-3369, 2011, doi: 10.1016/j.solmat.2011.07.026. [18] S. A. Kalogirou, 'Artificial neural networks in renewable energy systems applications: A review,' Renewable and Sustainable Energy Reviews, vol. 5, no. 4, pp. 373-401, 2001. [19] A. Mellit and S. A. Kalogirou, 'Artificial intelligence techniques for photovoltaic applications: A review,' Progress in Energy and Combustion Science, vol. 34, no. 5, pp. 574- 632, 2008. [20] A. Mellit and A. M. Pavan, 'A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy,' Solar Energy, vol. 84, no. 5, pp. 807-821, 2010. [21] H. T. C. Pedro and C. F. M. Coimbra, 'Assessment of forecasting techniques for solar power production with no exogenous inputs,' Solar Energy, vol. 86, no. 7, pp. 2017-2028, 2012. [22] M. Q. Raza, M. Nadarajah, and C. Ekanayake, 'On recent advances in PV output power forecast,' Solar Energy, vol. 136, pp. 125-144, 2016. [23] D. Yang, J. Kleissl, C. A. Gueymard, H. T. C. Pedro, and C. F. M. Coimbra, 'History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining,' Solar Energy, vol. 168, pp. 60-101, 2018. [24] G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ, USA: Wiley, 2015. [25] M. I. Atakpa and A. N. Fobellah, 'Anomaly detection in financial time-series data: A conceptual model for healthcare and banking applications,' International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 9, no. 2, pp. 967-997, 2023, doi: 10.32628/CSEIT2342441. [26] J. O. Sanni, 'Artificial intelligence driven demand forecasting models addressing volatility in complex service organizations,' Computer Science & IT Research Journal, vol. 7, no. 1, pp. 1- 26, 2026, doi: 10.51594/csitrj.v7i1.2170. [27] L. Wedraogo and J. O. Sanni, 'Machine learning models addressing uncertainty in cross- channel campaign performance forecasting accuracy,' International Journal of Advanced Multidisciplinary Research and Studies, vol. 4, no. 6, pp. 2875-2890, 2024, doi: 10.62225/2583049X.2024.4.6.5648. [28] E. Oghenemaiga, A. Basnet, and U. N. Anene, 'Predictive analytics applications for forecasting traffic patterns across owned and operated media platforms,' International Journal of Advanced Multidisciplinary Research and Studies, vol. 4, no. 6, 2024, doi: 10.62225/2583049X.2024.4.6.5668. [29] O. N. Michael and O. E. Ogunsola, 'Development of predictive data models for enhancing crop resilience and climate adaptation in agrarian economies,' International Journal of Advanced Multidisciplinary Research and Studies, vol. 3, no. 1, pp. 1510-1527, 2023, doi: 10.62225/2583049X.2023.3.1.5143. [30] S. Xie, X. Wang, C. Qu, X. Wang, and J. Guo, 'Impacts of different wind speed simulation methods on conditional reliability indices,' International Transactions on Electrical Energy Systems, vol. 20, pp. 1-6, 2013, doi: 10.1002/etep. [31] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009. [32] L. Breiman, 'Random forests,' Machine Learning, vol. 45, no. 1, pp. 5-32, 2001. [33] T. Chen and C. Guestrin, 'XGBoost: A scalable tree boosting system,' in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785-794. [34] J. Bergstra and Y. Bengio, 'Random search for hyper-parameter optimization,' Journal of Machine Learning Research, vol. 13, pp. 281-305, 2012. [35] S. Hochreiter and J. Schmidhuber, 'Long short-term memory,' Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997. [36] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016. [37] D. P. Kingma and J. Ba, 'Adam: A method for stochastic optimization,' in Proceedings of the 3rd International Conference on Learning Representations , San Diego, CA, USA, 2015. [38] O. O. Ladapo, A. A. Dosunmu, D. Jooda, and T. O. Abolaji, 'Human-in-the-loop machine learning: A state of the art,' Journal of Frontiers in Multidisciplinary Research, vol. 3, no. 1, pp. 656-669, 2022, doi: 10.54660/. JFMR.2022.3.1.656-669. [39] D. Dagodzo, M. C. Ahiaeke Patrick, and C. Aliliele, 'AI and deep learning for vegetation classification in power corridor management: A review,' International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 8, no. 1, pp. 668-698, 2022, doi: 10.32628/CSEIT2281227. [40] D. Dagodzo and M. C. Ahiaeke Patrick, 'An integrated framework for UAV, LiDAR, and GIS in infrastructure corridor management,' International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 7, no. 5, pp. 497-524, 2021, doi: 10.32628/CSEIT217566. [41] E. A. Sunday and G. O. Omoegun, 'Smart fault detection in HVAC systems using sensor- based monitoring,' International Journal of Scientific Research in Science, Engineering and Technology, vol. 7, no. 4, pp. 380-403, 2022. [42] E. A. Sunday, G. O. Omoegun, M. A. Essien, and O. A. Oluokun, 'Transitioning from reactive to predictive maintenance in mechanical systems,' International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 6, no. 6, pp. 425-447, 2020. [43] B. K. Yeboah, O. F. Enow, P. N. Ike, and S. B. Nnabueze, 'Program design for advanced preventive maintenance in renewable energy systems,' Shodhshauryam, International Scientific Refereed Research Journal, vol. 7, no. 2, pp. 138-156, 2024, doi: 10.32628/SHISRRJ2472156. [44] F. R. Albogamy et al., 'An optimal adaptive control strategy for energy balancing in smart microgrid using dynamic pricing,' IEEE Access, vol. 10, pp. 37396-37411, 2022, doi: 10.1109/ACCESS.2022.3164809. [45] L. Peng, A. Zabihi, M. Azimian, H. Shirvani, and F. Shahnia, 'Developing a robust expansion planning approach for transmission networks and privately-owned renewable sources,' IEEE Access, vol. 11, pp. 76046-76058, 2023, doi: 10.1109/ACCESS.2022.3226695. [46] D. D. Milosavljevic, T. S. Kevkic, and S. J. Jovanovic, 'Review and validation of photovoltaic solar simulation tools/software based on case study,' Open Physics, vol. 20, no. 1, pp. 431- 451, 2022, doi: 10.1515/phys-2022-0042. [47] N. Shirzadi, F. Nasiri, and U. Eicker, 'Optimal configuration and sizing of an integrated renewable energy system,' Energies, vol. 13, no. 3527, pp. 1-18, 2020. [48] W. McKinney, 'Data structures for statistical computing in Python,' in Proceedings of the 9th Python in Science Conference, Austin, TX, USA, 2010, pp. 51-56. [49] C. R. Harris et al., 'Array programming with NumPy,' Nature, vol. 585, pp. 357-362, 2020. [50] W. F. Holmgren, C. W. Hansen, and M. A. Mikofski, 'pvlib python: A python package for modeling solar energy systems,' Journal of Open-Source Software, vol. 3, no. 29, p. 884, 2018. [51] F. Pedregosa et al., 'Scikit-learn: Machine learning in Python,' Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011. [52] M. Abadi et al., 'TensorFlow: A system for large-scale machine learning,' in Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation , Savannah, GA, USA, 2016, pp. 265-283. [53] J. D. Hunter, 'Matplotlib: A 2D graphics environment,' Computing in Science and Engineering, vol. 9, no. 3, pp. 90-95, 2007. [54] A. Tonoyan, O. Dada, and S. S. Ayivi-Donkor, 'Advances in demand forecasting: Machine learning algorithms for revenue projection and financial planning accuracy,' Gyanshauryam, International Scientific Refereed Research Journal, vol. 4, no. 1, pp. 282-317, 2021. [55] W. Asiedu and R. Quainoo, 'How far can energy harvesting take us? A systematic review of radio frequency strategies for energy autonomous sensing,' Shodhshauryam, International Scientific Refereed Research Journal, vol. 6, no. 1, pp. 448-466, 2023. [56] W. Asiedu, R. Quainoo, and A. Asiedu, 'Predictive power management for intermittent IoT devices using lightweight machine learning under uncertain energy harvest,' Gulf Journal of Engineering and Technology, vol. 2, no. 4, pp. 108-118, 2026. [57] A. Tonoyan, O. Dada, and S. S. Ayivi-Donkor, 'Real-time KPI tracking systems: A review of automated performance monitoring and data-driven decision making,' World Journal of Innovation and Modern Technology, vol. 8, no. 6, pp. 247-281, 2024, doi: 10.56201/wjimt.v8.no6. 2024.pg247.281. [58] N. M. Komi, 'Hybrid deep learning for wind power forecasting: From grid stability to market equity for small generators,' International Journal of Multidisciplinary Research and Growth Evaluation, vol. 2, no. 6, pp. 989-1014, 2021, doi: 10.54660/. IJMRGE.2021.2.6.989-1014. [59] N. M. Komi, 'When accurate forecasts are not fair forecasts: Deep learning load prediction and equity across districts,' Shodhshauryam, International Scientific Refereed Research Journal, vol. 6, no. 6, pp. 476-546, 2023, doi: 10.32628/SHISRRJ247102. [60] N. M. Komi and O. S. Ganiu, 'Edge intelligence for resilient microgrid control: Advances, energy sovereignty, and open challenges,' Gyanshauryam, International Scientific Refereed Research Journal, vol. 6, no. 3, pp. 525-586, 2023, doi: 10.32628/GISRRJ236339. [61] N. M. Komi and A. Adamolekun, 'Interpretable machine learning for early failure prediction in distributed renewable energy assets,' International Journal of Multidisciplinary Research and Growth Evaluation, vol. 2, no. 6, pp. 1015-1038, 2021, doi: 10.54660/. IJMRGE.2021.2.6.1015-1038. [62] O. Kumuyi, E. Uzoka, B. Akeju, and D. E. Ozowara, 'Architecture for machine learning- enabled predictive energy management using IoT sensor networks,' International Journal of Advanced Multidisciplinary Research and Studies, vol. 4, no. 6, pp. 3138-3149, 2024, doi: 10.62225/2583049X.2024.4.6.6004. [63] O. O. Ladapo, D. Jooda, A. A. Dosunmu, and T. O. Abolaji, 'Keeping humans in the loop: Human-centered automated annotation with generative AI,' International Journal of Multidisciplinary Futuristic Development, vol. 5, no. 1, pp. 81-95, 2024. [64] O. O. Ladapo, D. Jooda, A. A. Dosunmu, and T. O. Abolaji, 'On the disagreement problem in human-in-the-loop federated machine learning,' International Journal of Multidisciplinary Research and Growth Evaluation, vol. 7, no. 3, pp. 178-192, 2026. [65] D. Dagodzo and M. C. Ahiaeke Patrick, 'A framework for national-scale UAV deployment in power infrastructure: Lessons from developing economies,' International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 11, no. 4, pp. 779-824, 2025, doi: 10.32628/CSEIT251116286.

Machine Learning and Deep Learning Approaches for Optimal Solar Panel Tilt Angle Prediction Using Meteorological Data from Kano, Nigeria

Abstract

Keywords

References

More Articles from WORLD JOURNAL OF INNOVATION AND MODERN TECHNOLOGY