Evaluating the Performance of Artificial Neural Network Models for Solar PV Output Forecasting in Nigeria’s Grid-Connected Systems

Dalyop Stephen Choji; Anibaba Olawale Oluwatosin; Adegboye Luqman Adetola; Wasiu Olalekan Idowu; Bakare Akeem Adegoke

doi:10.56201/ijemt.vol.11.no5.2025.pg38.50

📄 Download Paper

Evaluating the Performance of Artificial Neural Network Models for Solar PV Output Forecasting in Nigeria’s Grid-Connected Systems

Dalyop Stephen Choji, Anibaba Olawale Oluwatosin, Adegboye Luqman Adetola, Wasiu Olalekan Idowu, Bakare Akeem Adegoke

Abstract

The growing reliance on solar photovoltaic (PV) energy as a cleaner alternative to fossil fuels has amplified the need for accurate forecasting mechanisms, especially in developing countries like Nigeria where grid instability and load mismatches are common. This study evaluates the performance of Artificial Neural Network (ANN) models for forecasting solar PV output in grid- connected systems within the Nigerian energy context. Using historical meteorological and load demand data from 2020 to 2025, an ANN model was developed, trained, and simulated using MATLAB R2022a. The model incorporated key variables such as solar irradiance, ambient temperature, and time stamps to predict solar power generation. Simulation results were compared with actual output to assess accuracy using metrics such as Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the coefficient of determination (R²). The ANN model achieved a MAPE of 6.83%, an RMSE of 12.47 kW, and an R² value of 0.95—demonstrating high predictive accuracy and adaptability to nonlinear solar data variations. The study further presents graphical analyses, including predicted vs actual output curves, error distribution histograms, and regression scatter plots, which confirm the model’s robustness. These results validate the application of ANN for solar PV forecasting and emphasize its potential to enhance energy planning, grid stability, and real-time energy dispatch in Nigeria. Furthermore, the findings advocate for the integration of AI-based forecasting tools into Nigeria’s energy management systems to optimize renewable energy use. This paper contributes to the body of knowledge on intelligent forecasting for smart grid applications and provides a replicable model for similar developing regions.

Keywords

Artificial Neural Network (ANN); Solar Photovoltaic (PV); Forecasting; Grid Integration; Renewable Energy; Nigeria; Smart Grid; Solar Irradiance; MATLAB Simulation; Forecast Accuracy.

References

Alobaidi, M. H., & Zobaa, A. F. (2019). Artificial intelligence-based approaches for renewable energy forecasting: A review. Renewable and Sustainable Energy Reviews, 104, 418–442. Babaei, M., Ardehali, M. M., & Kasaeian, A. (2021). Optimal hybrid renewable energy design using ANFIS and ANN. Applied Energy, 302, 117474. Barbieri, J., & Spalvieri, A. (2018). Forecasting methods for renewable energy applications: A comparative review. Renewable Energy, 126, 915–926. Barbato, A., Bianchini, G., Fornari, F., & Vaccaro, A. (2022). Deep learning methods for short- term solar forecasting: A comprehensive review. Energies, 15(3), 685. Chen, C., Duan, S., Cai, T., & Liu, B. (2011). Online 24-h solar power forecasting based on weather type classification using artificial neural network. Solar Energy, 85(11), 2856– Chakraborty, S., & Saha, H. (2021). Machine learning models for solar energy forecasting: Comparative analysis. Energy Reports, 7, 1607–1615. Gope, A., & Sinha, A. K. (2022). Power forecasting models using ANN for microgrid applications in Africa. Sustainable Energy Technologies and Assessments, 53, 102614. Hossain, M. J., Mahmud, M. A., & Pota, H. R. (2019). Artificial intelligence-based control and monitoring for smart grid: A review. IEEE Access, 7, 105379–105389. Kabalci, E. (2020). Intelligent demand-side management using ANN for smart grid applications. International Journal of Electrical Power & Energy Systems, 115, 105478. Kapsali, M., & Kaldellis, J. K. (2010). Combining photovoltaics and pumped-storage units to effectively support remote islands’ electricity needs. Renewable Energy, 35(6), 1376– Kaytherm. (2022, September 19). What is a solar home energy storage system? https://www.kaytherm.com Kirschen, D. S., & Strbac, G. (2004). Fundamentals of Power System Economics. Wiley. Korpás, M., Tande, J. O., & Toftevaag, T. (2016). A wind-hydrogen system for remote islands. Wind Engineering, 40(1), 21–33. Li, X., & Shi, J. (2018). Photovoltaic power forecasting using a hybrid deep learning model. Applied Energy, 231, 131–141. Liu, C., Yu, D., & Zhang, Q. (2020). Short-term solar power forecasting using hybrid deep learning model. Energy, 192, 116682. Mahmud, K., Ravishankar, J., & Town, G. (2021). Grid stability improvement using solar forecasting and inverter control. Electric Power Systems Research, 194, 107024. Ma, T., Yang, H., & Lu, L. (2014). A feasibility study of a stand-alone hybrid solar–wind–battery system for a remote island. Applied Energy, 121, 149–158. Mohamed, F. A., & Koivo, H. N. (2010). Online management genetic algorithms of microgrid for residential application. Energy Conversion and Management, 51(3), 534–546. Mukund, R. P. (2009). Wind and Solar Power Systems: Design, Analysis, and Operation. CRC Press. Mujeeb, A., et al. (2018). Hybrid PV-wind system optimization for healthcare buildings. Sustainable Cities and Society, 38, 135–143. Nwachukwu, I. M., et al. (2022). Forecasting power generation in Nigeria using machine learning. Heliyon, 8(5), e09389. Obiora, U., & Nnaji, C. (2021). AI-based forecasting for renewable integration into Nigeria’s power grid. Energy Reports, 7, 489–501. Palomás, J., Olivella, P., & Escrig, C. (2018). Voltage control strategies in smart distribution grids: A review. Renewable and Sustainable Energy Reviews, 81, 771–781. Parida, B., Iniyan, S., & Goic, R. (2011). A review of solar photovoltaic technologies. Renewable and Sustainable Energy Reviews, 15(3), 1625–1636. Pradeep, K., et al. (2021). Power flow control techniques in hybrid power systems. International Journal of Electrical Power & Energy Systems, 130, 106955. Reddy, P. J., & Veershetty, G. (2016). Optimization of a hybrid renewable energy system for rural electrification. Renewable and Sustainable Energy Reviews, 58, 453–466. Shafiullah, G. M., Urmee, T., & Yusof, A. M. (2013). Solar energy adoption in developing countries. Renewable and Sustainable Energy Reviews, 28, 356–364. Singh, S., & Singh, M. (2020). A review of forecasting techniques in renewable energy systems. Journal of Cleaner Production, 255, 120295. Yadav, R. K., et al. (2017). A comparative analysis of artificial neural network models for solar forecasting. Procedia Computer Science, 122, 370–377. Zhou, Y., & Zhang, H. (2020). Machine learning models for renewable energy forecasting. Renewable Energy, 147, 2630–2645. Zhou, Y., & Zhang, H. (2021). Performance evaluation of deep learning for PV power prediction. IEEE Access, 9, 87678–87689. Zhou, Y., & Zhang, H. (2022). Hybrid models for solar irradiance forecasting: An overview. Renewable and Sustainable Energy Reviews, 154, 111780. Akuru, U. B., Onukwube, H. N., Okoro, O. I., & Obe, E. S. (2013). Towards 100% renewable energy in Nigeria. Renewable and Sustainable Energy Reviews, 27, 257–272. Ahmed, A., & Salim, N. (2020). Grid infrastructure and solar integration challenges in Sub- Saharan Africa. Energy Reports, 6, 1438–1446. Aneke, M., & Wang, M. (2016). Energy storage technologies and real-life applications. Applied Energy, 179, 350–377. Eltamaly, A. M., Al-Saud, M. A., & Mohamed, M. (2016). Renewable energy technologies for sustainable development in Saudi Arabia. Renewable and Sustainable Energy Reviews, 58, 144–163. Fathima, A. H., & Palanisamy, K. (2015). Forecasting of solar energy using hybrid neural networks. Procedia Computer Science, 48, 535–540. Alam, M. M., & Rashid, M. M. (2018). Simulation of grid-connected PV using MATLAB/Simulink. Renewable Energy Focus, 27, 80–87. Mehigan, L., Deane, J. P., Gallachóir, B. Ó., & Bertsch, V. (2018). Renewable energy policy review for Nigeria. Energy Policy, 123, 747–759. Zhou, Y., & Zhang, H. (2023). AI-Driven forecasting for off-grid PV applications in West Africa. Sustainable Energy Technologies and Assessments, 55, 102897. Iloeje, O. C. (2020). Challenges of integrating PV systems in Nigerian grid. Nigerian Journal of Electrical Engineering, 19(1), 45–56. Abdi, H., & Taghipour, M. (2019). Enabling technologies for renewables: A global review. Renewable and Sustainable Energy Reviews, 100, 120–131. Machlev, R., Pellitero, A., & Moser, A. (2020). IoT-enabled demand response in solar-based smart grids. Energy Reports, 6, 1955–1965. Anvari-Moghaddam, A., Monsef, H., & Rahimi-Kian, A. (2015). Optimal demand response in smart grids. Applied Energy, 139, 607–617. Albadi, M. H., & El-Saadany, E. F. (2008). A summary of demand response in electricity markets. Electric Power Systems Research, 78(11), 1989–1996. Zhou, Y., & Zhang, H. (2024). Enhancing solar forecasting with hybrid ML algorithms. IEEE Transactions on Sustainable Energy, 15(2), 1784–1792. Zhou, Y., & Zhang, H. (2025). Forecasting uncertainties in renewable energy systems. Applied Energy, 348, 121497. Zhou, Y., & Zhang, H. (2025). Long-term PV forecasting using hybrid AI models. Energy AI, 9

Evaluating the Performance of Artificial Neural Network Models for Solar PV Output Forecasting in Nigeria’s Grid-Connected Systems

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY