Optimization of Solar PV Performance Using Predictive Power Modeling and Real-Time Data Analysis: A Case Study of Kano State, Nigeria
DOI:
https://doi.org/10.33003/fjs-2026-10(ANB-K)-5292Keywords:
Photovoltaic System Performance, Energy Forecasting, Optimization, Predictive Monitoring, ModelingAbstract
The world demand of power combined with the performance degradation of solar energy by the environmental factors necessitate new optimization solutions. Solar PV systems experience intensive performance issues that can be attributed to heat by temperature variation and humidity change that leads to unreliable production of energy. The study addresses the best solar PV performance optimization using predictive power model and live data analysis with Kano State Nigeria being the prime study region. The study adopts a two-fold methodology that relates predictor analytics using machine learning to real-time data tracking functions to enhance the functionality of the PV systems. The 10-year average that was 12 months revealed that May had the highest temperature of 35.0 C and January had lowest temperature of 22.5 C and August had the highest humidity of 82 and March the least humidity of 15 . It has been demonstrated that the efficiency of power generation is maximum in temperatures of 25 C - 30 C but high humidity has harmful consequences to PV efficiency. Predictive analytics has demonstrated improvement in accuracy of forecasting and system reliability as per the comparison with previous studies. The barriers to implementation along with the computational complexity became some of the impediments in the course of the study. Integration based on predictive models results in efficient PV operation since they reduce the system inefficiencies and maximize the amount of power generated.
References
Adurodija, J. O., Okonkwo, U. C., & Agbo, S. N. (1998). The role of renewable energy in sustainable development: A Nigerian perspective. Energy Policy, 26(7), 531–537.
Akinboro, F. G., Adediran, A. A., & Oladipo, O. T. (2012). Alternative energy sources for Nigeria: Solar energy. Renewable Energy Review, 18(3), 45–55.
Alghassi, H., Mohammed, A., & Ibrahim, Y. (2020). Predictive analytics in solar energy forecasting. Journal of Energy Science, 12(4), 98–112.
Ali, M. (2021). Challenges in solar energy data acquisition and analysis in sub-Saharan Africa. African Journal of Renewable Energy, 15(1), 45–60.
Amankwah-Amoah, J. (2015). Solar energy adoption in developing countries: Lessons from Sub-Saharan Africa. Technological Forecasting and Social Change, 92, 234–242.
Badewole, A. O., & Oyebode, O. O. (2016). The impact of high installation costs on the adoption of solar PV systems in Nigeria. In Proceedings of the African Renewable Energy Conference (pp. 43–57). Lagos, Nigeria.
Bello, J. T., Adewumi, R., & Lawal, M. (2022). Deep learning-based solar power generation forecasting in California. Renewable Energy Technology Journal, 20(5), 315–329.
Donev, J. M. C. K. (2018). The fundamentals of photovoltaic technology: Understanding solar PV systems. Renewable Energy & Sustainability, 23(2), 112–127.
George, L., & Albert, M. L. (2022). Machine learning for solar energy forecasting: A review. Artificial Intelligence in Renewable Energy, 14(3), 201–218.
Hanley, J. A., & McNeil, B. J. (1982). The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143(1), 29–36.
International Energy Agency Photovoltaic Power Systems Programme. (2014). Global trends in photovoltaic power generation: Annual report. IEA Publications.
Kanwal, F., Ahmad, S., & Youssef, A. (2022). Machine learning applications in solar energy: Current trends and future research directions. Journal of Energy Systems, 29(2), 156–178.
Michael, P., & Venkatesh, P. (2020). Hydrogen production via electrolysis: A pathway to achieving carbon neutrality. Journal of Sustainable Energy, 16(4), 301–318.
Mohamed, A., Khan, R., & Patel, H. (2014). Applications of solar energy: A review. International Journal of Energy Research, 22(1), 78–92.
Okpala, P. J., & Torres, A. (2023). Data quality issues in solar energy forecasting: A case study of Nigeria. Journal of Energy Analytics, 21(1), 89–104.
Olson, D. L., & Delen, D. (2008). Advanced data mining techniques for predictive analytics. In Proceedings of the International Conference on Data Science and Applications (pp. 78–92).
Pearsall, N. (2016). The performance of photovoltaic systems: Modelling, measurement, and assessment. Elsevier.
Ravi, K. (2024). Predictive modeling for renewable energy applications. Renewable Energy Research Journal, 30(3), 210–225.
Robert, B. J., & Stephen, O. (2014). The energy crisis in Nigeria: Challenges and solutions. Journal of Energy Policy & Management, 19(3), 89–105.
Rochell, M. S. (2010). The future of solar energy: Policies and perspectives. International Journal of Renewable Energy Studies, 8(2), 134–150.
Rouse, M., & Kanwal, F. (2019). Big data and predictive analytics in energy sector applications. Energy Analytics Journal, 26(5), 321–336.
Salunkhe, P., & Desavale, K. (2021). Machine learning techniques for solar energy forecasting: A comparative study. Energy Informatics Review, 17(4), 77–92.
SunPower. (2023). Monitoring and optimizing solar panel efficiency using data analytics. https://www.sunpower.com/research2023
Sanni, D. M., Joseph, E., & Adamu, M. A. (2020). The importance of film thickness on the Photovoltaic performance of Perovskite solar cells. Fudma Journal of Sciences, 4(1), 600-606.
Venkatesh, P., & Murugan, K. (2022). Optimizing solar PV system performance using artificial intelligence. Smart Grid & Renewable Energy, 28(2), 156–172.
Xia, J., & Cioroaica, A. (2020). Digital twin applications in predictive monitoring of solar PV systems. Renewable Energy and AI, 19(3), 189–205.
Yusuf, A. (2021). The impact of desert climate on solar PV efficiency in Sokoto, Nigeria. https://www.renewableenergyafrica.com/yusuf2021
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Ibrahim Jibril, Musa Garba Abdullahi, Shuaibu Uba, Maimuna Aliyu Abubakar, Nasir Adam Abubakar, Sakinat L. Usman, Nasir Yusuf Muhammad
This work is licensed under a Creative Commons Attribution 4.0 International License.
