volume | PIER Journals

Abstract

Accurate photovoltaic (PV) power forecasting requires both meteorological information and a representation of inverter operating states. This study develops a physics-informed DT-LSTM framework in which a reduced-order thermoelectric digital twin converts measured PV power, ambient temperature, wind speed, and irradiance into estimated loss power, thermal load, equivalent temperature, and temperature rise. Field power and weather records from January to June 2024 are aligned causally and divided chronologically into training (January 1-April 15), validation (April 16-30), main testing (May), and external testing (June) periods. At a 5 min resolution over the extended 07:00-22:00 window, DT-LSTM achieves MAE/RMSE values of 65.90/132.12 kW in the main test and 67.07/124.52 kW in the external test, compared with 72.57/137.77 kW and 73.10/130.12 kW for LSTM. The estimated thermal states are model-derived variables rather than measured device temperatures; accordingly, the results demonstrate forecasting utility and physical consistency, not direct temperature-field validation. The study provides a physics-informed virtual-sensing forecasting framework and identifies controlled multi-seed ablation and measured thermal validation as future work.

1. Marques Lameirinhas, Ricardo A., João Paulo N. Torres, and João P. de Melo Cunha, "A photovoltaic technology review: History, fundamentals and applications," Energies, Vol. 15, No. 5, 1823, March 2022.
doi:10.3390/en15051823 Google Scholar

2. Vo, Thi Thu Em, Hyeyoung Ko, Junho Huh, and Namje Park, "Overview of possibilities of solar floating photovoltaic systems in the offshore industry," Energies, Vol. 14, No. 21, 6988, October 2021.
doi:10.3390/en14216988 Google Scholar

3. Gaboitaolelwe, Jwaone, Adamu Murtala Zungeru, Abid Yahya, Caspar K. Lebekwe, Dasari Naga Vinod, and Ayodeji Olalekan Salau, "Machine learning based solar photovoltaic power forecasting: A review and comparison," IEEE Access, Vol. 11, 40820-40845, 2023.
doi:10.1109/access.2023.3270041 Google Scholar

4. Soomar, Arsalan Muhammad, Abdul Hakeem, Mustapha Messaoudi, Piotr Musznicki, Amjad Iqbal, and Stanislaw Czapp, "Solar photovoltaic energy optimization and challenges," Frontiers in Energy Research, Vol. 10, 879985, May 2022.
doi:10.3389/fenrg.2022.879985 Google Scholar

5. Høiaas, Ingeborg, Katarina Grujic, Anne Gerd Imenes, Ingunn Burud, Espen Olsen, and Nabil Belbachir, "Inspection and condition monitoring of large-scale photovoltaic power plants: a review of imaging technologies," Renewable and Sustainable Energy Reviews, Vol. 161, 112353, June 2022.
doi:10.1016/j.rser.2022.112353 Google Scholar

6. Hazim, Hazim Imad, Kyairul Azmi Baharin, Chin Kim Gan, Ahmad H. Sabry, and Amjad J. Humaidi, "Review on optimization techniques of PV/inverter ratio for grid-Tie PV systems," Applied Sciences, Vol. 13, No. 5, 3155, March 2023.
doi:10.3390/app13053155 Google Scholar

7. Boscaino, Valeria, Vito Ditta, Giuseppe Marsala, Nicola Panzavecchia, Giovanni Tinè, Valentina Cosentino, Antonio Cataliotti, and Dario Di Cara, "Grid-connected photovoltaic inverters: Grid codes, topologies and control techniques," Renewable and Sustainable Energy Reviews, Vol. 189, 113903, January 2024.
doi:10.1016/j.rser.2023.113903 Google Scholar

8. Hazim, Hazim Imad, Kyairul Azmi Baharin, Chin Kim Gan, and Ahmad H. Sabry, "Techno-economic optimization of photovoltaic (PV)-inverter power sizing ratio for grid-connected PV systems," Results in Engineering, Vol. 23, 102580, September 2024.
doi:10.1016/j.rineng.2024.102580 Google Scholar

9. Zhang, Bo and Yuan Gao, "Igbt reliability analysis of photovoltaic inverter with reactive power output capability," Microelectronics Reliability, Vol. 147, 115073, August 2023.
doi:10.1016/j.microrel.2023.115073 Google Scholar

10. Zhao, Ensheng, Yang Han, Xiangyang Lin, Enping Liu, Ping Yang, and Amr S. Zalhaf, "Harmonic characteristics and control strategies of grid-connected photovoltaic inverters under weak grid conditions," International Journal of Electrical Power & Energy Systems, Vol. 142, 108280, November 2022.
doi:10.1016/j.ijepes.2022.108280 Google Scholar

11. Malik, Azra, Ahteshamul Haque, V. S. Bharath Kurukuru, Mohammed Ali Khan, and Frede Blaabjerg, "Overview of fault detection approaches for grid connected photovoltaic inverters," e-Prime --- Advances in Electrical Engineering, Electronics and Energy, Vol. 2, 100035, 2022.
doi:10.1016/j.prime.2022.100035 Google Scholar

12. Tao, Fei, Bin Xiao, Qinglin Qi, Jiangfeng Cheng, and Ping Ji, "Digital twin modeling," Journal of Manufacturing Systems, Vol. 64, 372-389, July 2022.
doi:10.1016/j.jmsy.2022.06.015 Google Scholar

13. Liu, Xin, Du Jiang, Bo Tao, Feng Xiang, Guozhang Jiang, Ying Sun, Jianyi Kong, and Gongfa Li, "A systematic review of digital twin about physical entities, virtual models, twin data, and applications," Advanced Engineering Informatics, Vol. 55, 101876, January 2023.
doi:10.1016/j.aei.2023.101876 Google Scholar

14. Wang, Yonggui, Yong Qi, Jian Li, Le Huan, Yusen Li, Bitao Xie, and Yongshan Wang, "The wind and photovoltaic power forecasting method based on digital twins," Applied Sciences, Vol. 13, No. 14, 8374, July 2023.
doi:10.3390/app13148374 Google Scholar

15. Natgunanathan, Iynkaran, Vicky Mak-Hau, Sutharshan Rajasegarar, and Adnan Anwar, "Deakin microgrid digital twin and analysis of AI models for power generation prediction," Energy Conversion and Management: X, Vol. 18, 100370, April 2023.
doi:10.1016/j.ecmx.2023.100370 Google Scholar

16. Zazoum, Bouchaib, "Solar photovoltaic power prediction using different machine learning methods," Energy Reports, Vol. 8, 19-25, April 2022.
doi:10.1016/j.egyr.2021.11.183 Google Scholar

17. Markovics, Dávid and Martin János Mayer, "Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction," Renewable and Sustainable Energy Reviews, Vol. 161, 112364, June 2022.
doi:10.1016/j.rser.2022.112364 Google Scholar

18. Zhang, Xiaoyu, Yushuai Li, Tianyi Li, Yonghao Gui, Qiuye Sun, and David Wenzhong Gao, "Digital twin empowered PV power prediction," Journal of Modern Power Systems and Clean Energy, Vol. 12, No. 5, 1472-1483, September 2024.
doi:10.35833/mpce.2023.000351 Google Scholar

19. Alghamdi, Hisham, et al. "RETRACTED: A prediction model for the performance of solar photovoltaic-thermoelectric systems utilizing various semiconductors via optimal surrogate machine learning methods," Engineering Science and Technology, an International Journal, Vol. 40, 101363, April 2023.
doi:10.1016/j.jestch.2023.101363 Google Scholar

20. Zayed, Mohamed E., Moustafa M. Aboelmaaref, and Mohamed Chazy, "Design of solar air conditioning system integrated with photovoltaic panels and thermoelectric coolers: Experimental analysis and machine learning modeling by random vector functional link coupled with white whale optimization," Thermal Science and Engineering Progress, Vol. 44, 102051, September 2023.
doi:10.1016/j.tsep.2023.102051 Google Scholar

21. Al-Selwi, Safwan Mahmood, Mohd Fadzil Hassan, Said Jadid Abdulkadir, Amgad Muneer, Ebrahim Hamid Sumiea, Alawi Alqushaibi, and Mohammed Gamal Ragab, "RNN-LSTM: From applications to modeling techniques and beyond --- Systematic review," Journal of King Saud University Computer and Information Sciences, Vol. 36, No. 5, 102068, June 2024.
doi:10.1016/j.jksuci.2024.102068 Google Scholar

22. Jebli, Imane, Fatima-Zahra Belouadha, Mohammed Issam Kabbaj, and Amine Tilioua, "Prediction of solar energy guided by pearson correlation using machine learning," Energy, Vol. 224, 120109, June 2021.
doi:10.1016/j.energy.2021.120109 Google Scholar

23. Negro, Massimo and Roberto Galdi, "Advanced 3D electromagnetic transient-thermal steady coupled FEM simulation of a LV busbar of a rectifier transformer," International Journal of Applied Electromagnetics and Mechanics, Vol. 76, No. 1-2, 257-269, September 2024.
doi:10.3233/jae-230410 Google Scholar

24. Konstantinou, Maria, Stefani Peratikou, and Alexandros G. Charalambides, "Solar photovoltaic forecasting of power output using LSTM networks," Atmosphere, Vol. 12, No. 1, 124, January 2021.
doi:10.3390/atmos12010124 Google Scholar

25. Akhter, Muhammad Naveed, Saad Mekhilef, Hazlie Mokhlis, Raza Ali, Muhammad Usama, Munir Azam Muhammad, and Anis Salwa Mohd Khairuddin, "A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems," Applied Energy, Vol. 307, 118185, February 2022.
doi:10.1016/j.apenergy.2021.118185 Google Scholar

26. Haddad, Sofiane, Ammar Boulaiche, Ammar Soukkou, Mohamed Benghanem, Abdelhamid Rabhi, and Belqees Hassan, "Enhancing photovoltaic panel diagnosis using a fine-tuned convolutional neural network model," Computers and Electrical Engineering, Vol. 129, 110824, January 2026.
doi:10.1016/j.compeleceng.2025.110824 Google Scholar

Dr. Juanjuan Zhang

Dr. Xiaoyan Jiang