VG-BiLSTM: Modeling Feature Variability for Robust PV Power Prediction
Received: 15 December 2025 | Revised: 1 January 2026, 19 January 2026, and 4 February 2026 | Accepted: 7 February 2026 | Online: 13 March 2026
Corresponding author: K. Dhana Sree Devi
Abstract
Photovoltaic (PV) power generation oscillates across multiple timescales due to changing weather and environmental conditions. These fluctuations have a huge impact on the stability and operational costs of the grid and reduce its effective use. Motivated by the need for reliable grid integration, this study emphasizes the importance of explicitly modeling variability in PV features to improve the robustness of solar power prediction models. Conventional approaches often neglect short-term fluctuations in key meteorological features, which can lead to degraded model performance and accuracy. This study presents the Variability Gated Bidirectional Long Short-Term Memory (VG-BiLSTM) framework, which explicitly models both features and variability using descriptors to predict short-term PV power output. The proposed method computes feature descriptors, the rolling standard deviation, ramp rate, and coefficient of variation for each feature, and employs a variability attention module to dynamically weight them. A gating network combines raw and variability representations into a single latent embedding, which is then input into a Bidirectional LSTM for temporal modeling. Experimental results show that VG-BiLSTM outperforms baseline RNN, GRU, LSTM, and their bidirectional versions, achieving much lower RMSE and nRMSE in different sky types. The model also achieved the best error levels across regions, with RMSE and NRMSE reduced to 21.6 W and 20.4%, respectively, outperforming other models.
Keywords:
PV power, envirnomental features, variability descriptors, BiLSTM, variability attentionDownloads
References
A. O. M. Maka and J. M. Alabid, "Solar energy technology and its roles in sustainable development," Clean Energy, vol. 6, no. 3, pp. 476–483, June 2022.
K. Hasan, S. B. Yousuf, M. S. H. K. Tushar, B. K. Das, P. Das, and Md. S. Islam, "Effects of different environmental and operational factors on the PV performance: A comprehensive review," Energy Science & Engineering, vol. 10, no. 2, pp. 656–675, Feb. 2022.
Y. Guo, Q. Han, T. Li, H. Fu, M. Liang, and S. Zhang, "Robust Photovoltaic Power Forecasting Model Under Complex Meteorological Conditions," Mathematics, vol. 13, no. 11, May 2025, Art. no. 1783.
H. B. Wolff, "Support Vector Regression for Solar Power Prediction," Ph.D. dissertation, University of Oldenburg, 2017.
G. P. Zhang, "Time series forecasting using a hybrid ARIMA and neural network model," Neurocomputing, vol. 50, pp. 159–175, Jan. 2003.
T. A. Nguyen et al., "A Study on Novel Solar Power Forecasting using an XGB-LiGBM-RF Hybrid Model and the L-BFGS-B Optimization Algorithm," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 24516–24522, Aug. 2025.
J. Yu et al., "Deep Learning Models for PV Power Forecasting: Review," Energies, vol. 17, no. 16, Aug. 2024, Art. no. 3973.
M. Saffari and M. Khodayar, "Spatiotemporal Deep Learning for Power System Applications: A Survey," IEEE Access, vol. 12, pp. 93623–93657, 2024.
J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling." arXiv, Dec. 11, 2014.
Y. Li, F. Ye, Z. Liu, Z. Wang, and Y. Mao, "A Short-Term Photovoltaic Power Generation Forecast Method Based on LSTM," Mathematical Problems in Engineering, vol. 2021, pp. 1–11, Jan. 2021.
A. Zameer, F. Jaffar, F. Shahid, M. Muneeb, R. Khan, and R. Nasir, "Short-term solar energy forecasting: Integrated computational intelligence of LSTMs and GRU," PLOS ONE, vol. 18, no. 10, Oct. 2023, Art. no. e0285410.
X. Lei, "A Photovoltaic Prediction Model with Integrated Attention Mechanism," Mathematics, vol. 12, no. 13, July 2024.
K. Yang, Y. Cai, and J. Cheng, "A deep learning model based on multi-attention mechanism and gated recurrent unit network for photovoltaic power forecasting," Computers and Electrical Engineering, vol. 123, Apr. 2025, Art. no. 110250.
A. Alcañiz, D. Grzebyk, H. Ziar, and O. Isabella, "Trends and gaps in photovoltaic power forecasting with machine learning," Energy Reports, vol. 9, pp. 447–471, Dec. 2023.
M. Subramaniam, D. Hanafi, and A. Joret, "Neural Network Based Prediction of Solar Power Generation," Evolution in Electrical and Electronic Engineering, vol. 6, no. 2, pp. 356–365, Oct. 2025.
T. E. Hoff and R. Perez, "Quantifying PV power Output Variability," Solar Energy, vol. 84, no. 10, pp. 1782–1793, Oct. 2010.
B. Nouri et al., "Ramp Rate Metric Suitable for Solar Forecasting," Solar RRL, vol. 8, no. 24, Dec. 2024, Art. no. 2400468.
J. Yan, T. Qu, S. Han, Y. Liu, X. Lei, and H. Wang, "Reviews on characteristic of renewables: Evaluating the variability and complementarity," International Transactions on Electrical Energy Systems, vol. 30, no. 7, July 2020.
T. Kealy, "The missing parameter in renewable energy power quality analysis, i.e., the coefficient of variation: Case study of a 3-MW on-site wind turbine project in Ireland," Journal of Cleaner Production, vol. 280, Jan. 2021, Art. no. 124699.
C. Wu, X. P. Zhang, and M. Sterling, "Solar power generation intermittency and aggregation," Scientific Reports, vol. 12, no. 1, Jan. 2022, Art. no. 1363.
"Solar energy power generation dataset." Kaggle, [Online]. Available: https://www.kaggle.com/datasets/stucom/solar-energy-power-generation-dataset.
D. K. D. S. Devi, "dhanasreek/Solar-Energy-Datasets." July 04, 2025, [Online]. Available: https://github.com/dhanasreek/Solar-Energy-Datasets.
Downloads
How to Cite
License
Copyright (c) 2026 Are Sambasiva Rao, K. Dhana Sree Devi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
