Citation :

Siva Prakash Sunkara, Kalyani Sunkara, "SSLR-AE Net: Tasmanian Devil Optimized Deep Learning Architecture for Ultra-Short-Term Solar Irradiance Forecasting," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 10, pp. 138-156, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I10P111

Abstract

Stable grid operation and the effective integration of renewable energy supplies depend heavily on accurate short-term solar irradiance predictions. However, accurate prediction is difficult due to the extremely nonlinear behavior of solar irradiance and the inherent unpredictability of climatic variables. This research proposes a more efficient regression-based forecasting approach by employing the integration of Tasmanian Devil Optimization (TDO) for adaptive hyperparameter tuning as well as a State-Space Latent Retention Autoencoder (SSLR-AE) network to address the aforementioned issues. The enhanced framework has been developed to perform better than the baseline SSLR-AE model as well as conventional Deep Neural Networks (DNN) in terms of a range of performance metrics, including R2, MSE, RMSE, MAE, and MAPE, respectively. The results demonstrate a substantial reduction in error rates as well as improved convergence stability. Overall, it can be observed that the proposed approach provides a reliable and accurate solution for short-term solar irradiance forecasting, and it can be used in sophisticated smart energy management.

Keywords

Solar irradiance forecasting, Deep Neural Network (DNN), Metaheuristic optimization, Renewable energy, Regression analysis, Solar irradiance.

References

1. Yakov Malinkovich et al., “A Combined Persistence and Physical Approach for Ultra-Short-Term Photovoltaic Power Forecasting using Distributed Sensors,” Sensors, vol. 24, no. 9, pp. 1-19, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Chenlei Xie et al., “Sky-Image-based Ultra-Short-Term PV Power Forecasting for Campus Microgrids,” Journal of Renewable and Sustainable Energy, vol. 17, no. 5, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Grzegorz Dudek, Paweł Piotrowski, and Dariusz Baczyński, “Forecasting in Modern Power Systems: Challenges, Techniques, and Emerging Trends,” Energies, vol. 18, no. 14, pp. 1-11, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Ewa Chodakowska et al., “ARIMA Models in Solar Radiation Forecasting in Different Geographic Locations,” Energies, vol. 16, no. 13, pp. 1-24, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Domingos S. de O. Santos et al., “Solar Irradiance Forecasting using Dynamic Ensemble Selection,” Applied Sciences, vol. 12, no. 7, pp. 1-19, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Brahim BELMAHDI, and Abdelmajid EL BOUARDI, “Short-Term Solar Radiation Forecasting using Machine Learning Models Under Different Sky Conditions: Evaluations and Comparisons,” Environmental Science and Pollution Research, vol. 31, no. 1, pp. 966-981, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Ameera M. Almarzooqi et al., “A Hybrid Machine-Learning Model for Solar Irradiance Forecasting,” Clean Energy, vol. 8, no. 1, pp. 100-110, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Mantosh Kumar et al., “Solar Irradiance Prediction using an Optimized data Driven Machine Learning Models,” Journal of Grid Computing, vol. 21, no. 2, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Zhongyuan Su et al., “Improving Ultra-Short-Term Photovoltaic Power Forecasting using Advanced Deep-Learning Approach,” Measurement, vol. 239, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Congzhi Huang, and Mengyuan Yang, “Memory Long and Short Term Time Series Network for Ultra-Short-Term Photovoltaic Power Forecasting,” Energy, vol. 279, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Mohammed Alghassab, “Advancing Photovoltaic Power Forecast Accuracy: A Hybrid Particle Filter and Recurrent Neural Network Model for Data-Scarce Scenarios toward Thermal Adaptation,” Case Studies in Thermal Engineering, vol. 75, pp.1-19, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Hao Xiao et al., “Ultra-short-term Photovoltaic Power Prediction based on Improved Temporal Convolutional Network and Feature Modeling,” CSEE Journal of Power and Energy Systems, vol. 11, no. 5, pp. 2024-2035, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Yongning Zhang et al., “A Deep Learning-based Dual-Scale Hybrid Model for Ultra-Short-Term Photovoltaic Power Forecasting,” Sustainability, vol. 16, no. 17, pp. 1-22, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Neelam Mughees et al., “Bi-LSTM-based Deep Stacked Sequence-to-Sequence Autoencoder for Forecasting Solar Irradiation and Wind Speed,” Computers, Materials, and Continua, vol. 75, no. 3, pp. 6375-6393, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Madderla Chiranjeevi et al., “Solar Irradiation Prediction Hybrid Framework using Regularized Convolutional BiLSTM-based Autoencoder Approach,” IEEE Access, vol. 11, pp. 131362-131375, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Mouaad Bougoffa et al., “Stacked AutoEncoder based Diagnosis Applied on a Solar Photovoltaic System,” IFAC-PapersOnLine, vol. 58, no. 4, pp. 384-389, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Rachida Elmousaid, “Ultra-Short-Term Global Horizontal Irradiance Forecasting based on a Novel and Hybrid GRU-TCN Model,” Results in Engineering, vol. 23, pp.1-14, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Jingxuan Liu et al., “Harvesting Spatiotemporal Correlation from Sky Image Sequence to Improve Ultra-Short-Term Solar Irradiance Forecasting,” Renewable Energy, vol. 209, pp. 619-631, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Min Wang et al., “Ultra-Short-Term Solar Irradiance Forecasting based on Cloud-Type Guidance and Multimodal Fusion,” Solar Energy, vol. 305, 2026.
    [CrossRef] [Google Scholar] [Publisher Link] 
20. Mengyu Li, Yong Li, and Yongfa Diao, “A Precise and Efficient K-means-ELM Model to Improve Ultra-Short-Term Solar Irradiance Forecasting,” Renewable Energy Focus, vol. 51, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Lijie Wang, “Ultra-Short-Term Solar Irradiance Prediction Using an Integrated Framework with Novel Textural Convolution Kernel for Feature Extraction of Clouds,” Sustainability, vol. 17, no. 6, pp. 1-23, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Yifeng Ma et al., “Research on Ultra-Short-Term Photovoltaic Power Forecasting using Multimodal Data and Ensemble Learning,” Energy, vol .330, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Xiaoqiao Huang et al., “A 3D ConvLSTM-CNN Network based on Multi-Channel Color Extraction for Ultra-Short-Term Solar Irradiance Forecasting,” Energy, vol. 272, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Abdulaziz Alorf, and Muhammad Usman Ghani Khan, “Solar Irradiance Forecasting using Temporal Fusion Transformers,” International Journal of Energy Research, vol. 2025, no. 1, pp. 1-19, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Yuan Gao et al., “Spatio-Temporal Interpretable Neural Network for Solar Irradiation Prediction using Transformer,” Energy and Buildings, vol. 297, pp. 1-42, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Hanjin Zhang et al., “A Novel Hybrid Transformer-based Framework for Solar Irradiance Forecasting Under Incomplete Data Scenarios,” IEEE Transactions on Industrial Informatics, vol. 20, no. 6, pp. 8605-8615, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Muhammad Sabir Naveed et al., “Leveraging Advanced AI Algorithms with Transformer-Infused Recurrent Neural Networks to Optimize Solar Irradiance Forecasting,” Frontiers in Energy Research, vol. 12, pp. 1-18, 2024. 
    [CrossRef] [Google Scholar] [Publisher Link]