Proceedings of International Conference on Applied Innovation in IT  ·  2024/11/30  ·  Vol. 12  ·  Issue 2  ·  pp. 173–183
Comparative Analysis of LSTM-Based PV Power Forecasting Models with Climate-Adaptive Feature Selection in Abuja, Nigeria
David Akpuluma, Wolf-Gerrit Früh, Neda Firoz, James Abam, Mohammed Umar Bello, Comfort Williams and Ambrose Onne Okpu
📄 Download PDF DOI: 10.25673/118131
Abstract
In this research, we analyse how Long Short-Term Memory (LSTM) models can predict photovoltaic (PV) power output, in Abuja, Nigeria by selecting specific climate features and model configurations. The rising energy needs due to population growth and urbanisation emphasise the importance of sustainable energy sources. This study aims to improve the accuracy of PV power forecasts for integrating power into the current electrical grid and enhancing energy management strategies. By analysing data from the ERA5 dataset that includes various climatic features, we rigorously trained and assessed the LSTM models. Our results indicate that specific window sizes and combinations of features notably enhance forecasting accuracy with a window size of 6 and a mix of meteorological and solar radiation features showing the performance metrics (MAE, RMSE, R²). The study also underscores the significance of autocorrelation and cross-correlation analyses in optimizing model setups. Our findings suggest that LSTM models can accurately predict PV power output offering insights for maximizing energy usage in urban areas with similar climates. This research contributes to efforts aimed at reducing reliance on fossil fuels and promoting sustainable energy solutions. Future endeavours will explore integrating real-time data and incorporating additional climatic features to further refine forecasting models.
Keywords
PV Power Forecasting LSTM Models Climatic Feature Selection Renewable Energy Solar Energy Prediction Abuja Autocorrelation Analysis Cross-Correlation Analysis Sustainable Energy Solutions
References
  1. C. Etukudor, B. Couraud, V. Robu, W. Fruh, D. Flynn, and C. Okereke, “Automated negotiation for peer-to-peer electricity trading in local energy markets,” Energies, vol. 13, no. 4, 2020. [Online]. Available: https://doi.org/10.3390/en13040920.
  2. S. M. Kadiri, A. O. Bagre, M. B. Camara, B. Dakyo, and Y. Coulibaly, “Electrical power distribution status in west assessment and perspective overview,” in Proc. IEEE Int. Conf. Renewable Energy Res. Appl. (ICRERA), 2019. [Online]. Available: https://doi.org/10.1109/ICRERA47325.2019.8997112.
  3. W. Tsai, C. Tu, C. Hong, and W. Lin, “A review of state-of-the-art and short-term forecasting models for solar PV power generation,” Energies, vol. 16, no. 14, 2023. [Online]. Available: https://doi.org/10.3390/en16145436.
  4. K. Tu, H. Xiong, and F. Chen, “Comprehensive prediction of generation power in photovoltaic microgrid,” in Proc. IEEE Joint Int. Inf. Technol. Artif. Intell. Conf., 2019. [Online]. Available: https://doi.org/10.1109/ITAIC.2019.8785746.
  5. O. T. Ibitoye, O. S. Agunbiade, T. W. Ilemobola, A. B. Oluwadare, P. C. Ofodu, K. O. Lawal, and J. O. Dada, “Nigeria electricity grid and the potentials of renewable energy integration: A concise review,” in Proc. IEEE 7th Int. Energy Conf. (ENERGYCON), 2022, pp. 1-4. [Online]. Available: https://doi.org/10.1109/ENERGYCON53164.2022.9830349.
  6. Y. N. Chanchangi, F. Adu, A. Ghosh, S. Sundaram, and T. K. Mallick, “Nigeria’s energy review: Focusing on solar energy potential and penetration,” Environ. Dev. Sustain., vol. 25, no. 7, pp. 5755-5796, 2023. [Online]. Available: https://doi.org/10.1007/s10668-022-02308-4.
  7. C. K. Rao, S. Sahoo, and F. F. Yanine, “Forecasting electric power generation in a photovoltaic power system for smart energy management,” in Proc. Int. Conf. Intell. Controller Comput. Smart Power (ICICCSP), 2022. [Online]. Available: https://doi.org/10.1109/ICICCSP53532.2022.9862396.
  8. M. N. Akhter et al., “An hour-ahead PV power forecasting method based on an RNN-LSTM model for three different PV plants,” Energies, vol. 15, p. 2243, 2022. [Online]. Available: https://doi.org/10.3390/EN15062243.
  9. Y. Wang, Y. Shen, S. Mao, X. Chen, and H. Zou, “LASSO and LSTM integrated temporal model for short-term solar intensity forecasting,” IEEE Internet Things J., vol. 6, pp. 2933-2944, 2019. [Online]. Available: https://doi.org/10.1109/JIOT.2018.2877510.
  10. F. Jin, “Photovoltaic power generation prediction based on k-means clustering analysis and GRO-CNN-LSTM attention,” Math. Model. Algorithm Appl., vol. 2, no. 1, pp. 61-68, 2024. [Online]. Available: https://doi.org/10.54097/qdcrpc46.
  11. R. Kabir, A. Elmouatamid, H. Elkhoukhi, and P. W. Pong, “Photovoltaic power forecasting using neural networks for short and medium-term dependencies,” in Proc. IEEE Texas Power Energy Conf. (TPEC), 2024, pp. 1-6. [Online]. Available: https://doi.org/10.1109/TPEC60005.2024.10472207.
  12. T. Magesh et al., “Prediction of solar power irradiance using machine learning and deep learning for smart grid integration,” in Proc. Int. Conf. Recent Adv. Electr. Electron. Ubiquitous Commun. Comput. Intell. (RAEEUCCI), 2024, pp. 1-6. [Online]. Available: https://doi.org/10.1109/RAEEUCCI61380.2024.10547750.
  13. C. K. Rodriguez-Leguizamon et al., “PV power generation forecasting based on XGBoost and LSTM models,” in Proc. IEEE Workshop Power Electron. Power Qual. Appl. (PEPQA), 2023, pp. 1-6. [Online]. Available: https://doi.org/10.1109/PEPQA59611.2023.10325757.
  14. H. He, R. Hu, Y. Zhang, Y. Zhang, and R. Jiao, “A power forecasting approach for PV plant based on irradiance index and LSTM,” in Proc. 37th Chin. Control Conf. (CCC), 2018, pp. 9404-9409. [Online]. Available: https://doi.org/10.23919/ChiCC.2018.8483960.
  15. T. Limouni et al., “Univariate and multivariate LSTM models for one step and multistep PV power forecasting,” Int. J. Renew. Energy Dev., vol. 11, no. 3, pp. 815-824, 2022. [Online]. Available: https://doi.org/10.14710/ijred.2022.43953.
  16. R. Ahmed et al., “Computationally expedient photovoltaic power forecasting: A LSTM ensemble method augmented with adaptive weighting and data segmentation technique,” Energy Convers. Manage., vol. 258, p. 115563, 2022. [Online]. Available: https://doi.org/10.1016/j.enconman.2022.115563.
  17. H. Hersbach et al., “ERA5 hourly data on single levels from 1940 to present,” Copernicus Climate Change Service (C3S) Climate Data Store (CDS), 2023. [Online]. Available: https://doi.org/10.24381/cds.adbb2d47.
  18. M. AlKandari and I. Ahmad, “Solar power generation forecasting using ensemble approach based on deep learning and statistical methods,” Appl. Comput. Informat., vol. 20, no. 3/4, pp. 231-250, 2024. [Online]. Available: https://doi.org/10.1016/j.aci.2019.11.002.
  19. A. M. Hayajneh, F. Alasali, A. Salama, and W. Holderbaum, “Intelligent solar forecasts: Modern machine learning models and TinyML role for improved solar energy yield predictions,” IEEE Access, vol. 12, pp. 10846-10864, 2024. [Online]. Available: https://doi.org/10.1109/ACCESS.2024.3354703.

Proceedings of the International Conference on Applied Innovations in IT by Anhalt University of Applied Sciences is licensed under CC BY-SA 4.0  ·  This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License

ICAIIT 2026
International Conference on Applied Innovation in IT
Navigation
Publisher
ISSN2199-8876
Publisher Edition Hochschule Anhalt
Location Anhalt University of Applied Sciences
Email leiterin.hsb@hs-anhalt.de
Phone +49 (0) 3496 67 5611
Address Building 01, Room 425
Bernburger Str. 55
D-06366 Köthen, Germany
Open Access License
CC BY-SA 4.0

All works are licensed under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0), unless otherwise noted.

Published by ICAIIT in cooperation with Anhalt University of Applied Sciences.

© 2026 ICAIIT — International Conference on Applied Innovations in IT. Anhalt University of Applied Sciences, Köthen, Germany.
Visitors: site traffic counter