Pemodelan Daya Photovoltaic Berdasarkan Distribusi Termal Menggunakan Algoritma Support Vector Regression

Isyatur Raziah, Andri Novandri, Cut Mutia, Yuwaldi Away

Abstract


Kinerja photovoltaic (PV) sangat dipengaruhi oleh karakteristik termal, terutama temperatur yang berdampak langsung terhadap daya keluaran. Pada kondisi nyata, distribusi temperatur pada permukaan panel tidak selalu seragam, sehingga pemodelan berbasis temperatur rata-rata sering kali kurang akurat. Penelitian ini bertujuan untuk memodelkan daya keluaran PV berdasarkan distribusi temperatur menggunakan algoritma Support Vector Regression (SVR). Variabel input yang digunakan meliputi temperatur atas dan bawah panel, irradiance matahari serta kelembapan udara, sementara daya keluaran PV dijadikan sebagai variabel target. Model SVR diterapkan dengan fungsi kernel Radial Basis Function (RBF) untuk menangkap hubungan nonlinier antara variabel input dan output. Hasil pengujian menunjukkan bahwa akurasi model meningkat seiring dengan bertambahnya jumlah dan variasi dataset, dengan performa terbaik diperoleh pada dataset 10 hari yang menghasilkan nilai error rendah serta nilai  dan   yang tinggi. Temuan ini menunjukkan bahwa SVR efektif dan andal dalam memprediksi daya keluaran PV berbasis distribusi temperatur panel.

Full Text:

PDF

References


P. K. Dash and N. C. Gupta, “Effect of Temperature on Power Output from Different Commercially Available Photovoltaic Modules,” J. Eng. Res. Appl. www.ijera.com, vol. 5, no. 1, pp. 1–4, 2015.

O. Dupré, R. Vaillon, and M. A. Green, Thermal Behavior of Photovoltaic Devices. Cham: Springer International Publishing, 2017.

I. Raziah, A. Novandri, and Y. Away, “Real-Time Monitoring of Photovoltaic Panel Using Node-RED,” sinkron, vol. 8, no. 3, pp. 2049–2060, Aug. 2024, doi: 10.33395/sinkron.v8i3.13929.

T. J. Silverman et al., “Reducing Operating Temperature in Photovoltaic Modules,” in IEEE Journal of Photovoltaics, Mar. 2018, vol. 8, no. 2, pp. 532–540, doi: 10.1109/JPHOTOV.2017.2779842.

Asri, Y. Away, Nasaruddin, I. Devi Sara, and A. Novandri, “Enhancement of Photovoltaic Performance With Coolant Calcium Chloride: Experimental and Predictive Modeling,” IEEE Access, vol. 12, no. July, pp. 112839–112851, 2024, doi: 10.1109/ACCESS.2024.3443695.

H. G. Teo, P. S. Lee, and M. N. A. Hawlader, “An Active Cooling System for Photovoltaic Modules,” Appl. Energy, vol. 90, no. 1, pp. 309–315, 2012, doi: 10.1016/j.apenergy.2011.01.017.

G. Todorov, H. Vasilev, K. Kamberov, T. Ivanov, and Y. Sofronov, “Concept and Virtual Prototyping of Cooling Module for Photovoltaic System,” in 6th International Symposium on Environment-Friendly Energies and Applications (EFEA), 2021, pp. 3–6, doi: 10.1109/EFEA49713.2021.9406247.

M. Seapan, Y. Hishikawa, M. Yoshita, and K. Okajima, “Temperature and Irradiance Dependences of the Current and Voltage at Maximum Power of Crystalline Silicon PV Devices,” Sol. Energy, vol. 204, no. 5, pp. 459–465, 2020, doi: 10.1016/j.solener.2020.05.019.

S. Kalaiselvan, V. Karthikeyan, G. Rajesh, A. Sethu Kumaran, B. Ramkiran, and P. Neelamegam, “Solar PV Active and Passive Cooling Technologies - A Review,” in International Conference on Computation of Power, Energy, Information and Communication (ICCPEIC), Mar. 2018, pp. 166–169, doi: 10.1109/ICCPEIC.2018.8525185.

Y. Hishikawa et al., “Voltage-Dependent Temperature Coefficient of the I-V Curves of Crystalline Silicon Photovoltaic Modules,” IEEE J. Photovoltaics, vol. 8, no. 1, pp. 48–53, 2018, doi: 10.1109/JPHOTOV.2017.2766529.

T. Ozden, D. Tolgay, and B. G. Akinoglu, “Daily and Monthly Module Temperature Variation for 9 Different Modules,” in International Conference on Photovoltaic Science and Technologies (PVCon), Jul. 2018, pp. 4849–4854, doi: 10.1109/PVCon.2018.8523878.

S. Dubey, J. N. Sarvaiya, and B. Seshadri, “Temperature Dependent Photovoltaic (PV) Efficiency and Its Effect on PV Production in the World - A Review,” Energy Procedia, vol. 33, pp. 311–321, 2013, doi: 10.1016/j.egypro.2013.05.072.

L. Fan, Y. Ji, and G. Wu, “Research on Temperature Prediction Model in Greenhouse Based on Improved SVR,” J. Phys. Conf. Ser., vol. 1802, no. 4, p. 042001, Mar. 2021, doi: 10.1088/1742-6596/1802/4/042001.

Y. Tao, H. Yan, H. Gao, Y. Sun, and G. Li, “Application of SVR Optimized by Modified Simulated Annealing (MSA-SVR) Air Conditioning Load Prediction Model,” J. Ind. Inf. Integr., vol. 15, pp. 247–251, Sep. 2019, doi: 10.1016/j.jii.2018.04.003.

E. S. Nasution, Y. Away, Syahrial, I. D. Sara, and A. Novandri, “SVR-Optimized ANN Model for Predicting Earthquake Risk in Electrical Substations Based on Disaster Datasets in the Aceh Region, Indonesia,” IEEE Access, vol. 13, pp. 105027–105043, 2025, doi: 10.1109/ACCESS.2025.3579797.

Y. Xiang, L. Gou, L. He, S. Xia, and W. Wang, “A SVR–ANN Combined Model Based on Ensemble EMD for Rainfall Prediction,” Appl. Soft Comput., vol. 73, pp. 874–883, Dec. 2018, doi: 10.1016/j.asoc.2018.09.018.

A. Mirarabi, H. R. Nassery, M. Nakhaei, J. Adamowski, A. H. Akbarzadeh, and F. Alijani, “Evaluation of Data-Driven Models (SVR and ANN) for Groundwater-Level Prediction in Confined and Unconfined Systems,” Environ. Earth Sci., vol. 78, no. 15, p. 489, Aug. 2019, doi: 10.1007/s12665-019-8474-y.

Z. Xuan et al., “Multi-variable time series forecasting for thermal load of air-conditioning system on SVR,” in 2015 34th Chinese Control Conference (CCC), Jul. 2015, vol. 2015-Septe, no. 1, pp. 8276–8280, doi: 10.1109/ChiCC.2015.7260952.




DOI: https://doi.org/10.35308/jti.v5i1.14747

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 



Jurnal Teknologi Informasi
e-ISSN: 2829-8934  I  DOI: 10.35308
Jl. Alue Peunyareng, Ujong Tanoh Darat, Meureubo, Kabupaten Aceh Barat, Aceh 23681, Indonesia
(0655) 7110535
License Creative Commons is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License