Fotovoltaik Verilerin Tahminlemesinde Hiper Parametre Etkisinin İncelenmesi

Yıl 2025, Cilt: 15 Sayı: 1, 27 - 40, 25.01.2025

Fikriye Ataman

Öz

Günümüzde yenilebilir enerji kaynaklarına olan ihtiyaç her gün biraz daha artmaktadır. Bu çalışmanın amacı yenilebilir enerji kaynağı olan fotovoltaik enerji üretiminde, kullanılan tahminleme modelleri için uygun hiper parametre seçiminin tespit edilmesidir. Çalışma kapsamında gerçek bir fotovoltaik veri seti üzerinde tahminleme yapılmaktadır. Tahminleme için kullanılan dört model seçilmiş ve bu modellerin başarımına etki eden hiper parametrelerin bulunarak modellerin fotovoltaik veriler için alan adaptasyonu araştırılmıştır. Seçilen modeller Gause Süreç Regresyonu(GSR), Ridge Çekirdek Regresyonu(RÇR), Destek Vektör Regresyonu (DVR), Çok Katmanlı Algılayıcı (ÇKA)’dır. Yapılan çalışma sonucunda fotovoltaik verilerde kullanılan tahmin modellerinde hiper parametre optimizasyonunun model başarısına önemli bir etkisi olduğu bulgusuna ulaşılmıştır. GSR modeli %99.9, RÇR modeli %99.9, SVR modeli %99.4 ve ÇKA modeli %89.3 başarı göstermiştir. Bu çalışma ile, modellerde kullanılan hiper parametre seçiminin, model tahmin başarısını doğrudan etkilediği ve fotovoltaik verilerin tahminlemesinde kullanılması gereken hiper parametreler ortaya konulmuştur. Bu çalışma, fotovoltaik veri tahmini üzerinde çalışan diğer çalışmalara önemli bir katkı sağlayacaktır

Anahtar Kelimeler

: Fotovoltaik Enerji, Tahminleme, Yapay Zeka, Hiper Parametre

Kaynakça

• [1] V. P. Wright, ‘World Energy Outlook.’, 2023. [Online]. Available: https://iea.blob.core.windows.net/assets/26ca51d0-4a42-4649-a7c0-552d75ddf9b2/WorldEnergyOutlook2023.pdf
• [2] M. Ş. Kalay, ‘Fotovoltaik Enerji Santrallerinde Panellere Ait Verilerin Uzaktan Erişim İle İzlenmesi Ve Kayıt Altına Alınması’, Marmamara Üniversitesi, 2023.
• [3] M. J. Alshareef, ‘A Comprehensive Review of the Soiling Effects on PV Module Performance’, IEEE Access, vol. 11, no. December, pp. 134623–134651, 2023, doi: 10.1109/ACCESS.2023.3337204.
• [4] C. R. Sarin, G. Mani, A. A. Stonier, G. Peter, P. Kumaresan, and V. Ganji, ‘An extensive critique on expert system control in solar photovoltaic dominated microgrids’, IET Renewable Power Generation, no. July, pp. 1–16, 2023, doi: 10.1049/rpg2.12875.
• [5] J. Gaboitaolelwe, A. M. Zungeru, A. Yahya, C. K. Lebekwe, D. N. Vinod, and A. O. Salau, ‘Machine Learning Based Solar Photovoltaic Power Forecasting: A Review and Comparison’, IEEE Access, vol. 11, no. April, pp. 40820–40845, 2023, doi: 10.1109/ACCESS.2023.3270041.
• [6] I. Shafi et al., ‘An Artificial Neural Network-Based Approach for Real-Time Hybrid Wind–Solar Resource Assessment and Power Estimation’, Energies, vol. 16, no. 10, pp. 1–18, 2023, doi: 10.3390/en16104171.
• [7] R. Tobishima and S. Urano, ‘Solar radiation estimation for photovoltaic power generation using Geostationary and Low-Earth Orbit Satellite Data’, 2023 IEEE Belgrade PowerTech, PowerTech 2023, pp. 1–6, 2023, doi: 10.1109/PowerTech55446.2023.10202850.
• [8] L. Visser, T. AlSkaif, J. Hu, A. Louwen, and W. van Sark, ‘On the value of expert knowledge in estimation and forecasting of solar photovoltaic power generation’, Solar Energy, vol. 251, no. September 2022, pp. 86–105, 2023, doi: 10.1016/j.solener.2023.01.019.
• [9] D. Akal, ‘Destek Vektör Regresyon ( SVR ) Yöntemi Kullan ı larak Haftal ı k Dönemde Fotovoltaik Panel Enerji Tahmini’, no. January 2024, 2023.
• [10] M. Phiri, M. Mulenga, A. Zimba, and C. I. Eke, ‘Deep learning techniques for solar tracking systems: A systematic literature review, research challenges, and open research directions’, Solar Energy, vol. 262, no. April, p. 111803, 2023, doi: 10.1016/j.solener.2023.111803.
• [11] O. Gandhi et al., ‘The value of solar forecasts and the cost of their errors: A review’, Renewable and Sustainable Energy Reviews, vol. 189, no. October 2023, 2024, doi: 10.1016/j.rser.2023.113915.
• [12] J. Tian, R. Ooka, and D. Lee, ‘Multi-scale solar radiation and photovoltaic power forecasting with machine learning algorithms in urban environment: A state-of-the-art review’, Journal of Cleaner Production, vol. 426, no. September, p. 139040, 2023, doi: 10.1016/j.jclepro.2023.139040.
• [13] J. F. L. de Oliveira et al., ‘Forecasting Methods for Photovoltaic Energy in the Scenario of Battery Energy Storage Systems: A Comprehensive Review’, Energies, vol. 16, no. 18, pp. 1–20, 2023, doi: 10.3390/en16186638.
• [14] A. M. Assaf, H. Haron, H. N. Abdull Hamed, F. A. Ghaleb, S. N. Qasem, and A. M. Albarrak, ‘A Review on Neural Network Based Models for Short Term Solar Irradiance Forecasting’, Applied Sciences (Switzerland), vol. 13, no. 14, 2023, doi: 10.3390/app13148332.
• [15] I. Gallardo, D. Amor, and Á. Gutiérrez, ‘Recent Trends in Real-Time Photovoltaic Prediction Systems’, Energies, vol. 16, no. 15, pp. 1–17, 2023, doi: 10.3390/en16155693.
• [16] N. Rahimi et al., ‘A Comprehensive Review on Ensemble Solar Power Forecasting Algorithms’, Journal of Electrical Engineering and Technology, vol. 18, no. 2, pp. 719–733, 2023, doi: 10.1007/s42835-023-01378-2.
• [17] B. E. Demir, ‘A New Low-Cost Internet of Things-Based Monitoring System Design for Stand-Alone Solar Photovoltaic Plant and Power Estimation’, Applied Sciences, vol. 13, no. 24, p. 13072, 2023, doi: 10.3390/app132413072.
• [18] L. Visser, T. AlSkaif, J. Hu, A. Louwen, and W. van Sark, ‘On the value of expert knowledge in estimation and forecasting of solar photovoltaic power generation’, Solar Energy, vol. 251, no. December 2022, pp. 86–105, 2023, doi: 10.1016/j.solener.2023.01.019.
• [19] H. Wen, Y. Du, X. Chen, E. G. Lim, H. Wen, and K. Yan, ‘A regional solar forecasting approach using generative adversarial networks with solar irradiance maps’, Renewable Energy, vol. 216, no. October 2022, p. 119043, 2023, doi: 10.1016/j.renene.2023.119043.
• [20] D. Venkateswaran and Y. Cho, ‘Efficient solar power generation forecasting for greenhouses: A hybrid deep learning approach’, Alexandria Engineering Journal, vol. 91, no. February, pp. 222–236, 2024, doi: 10.1016/j.aej.2024.02.004.
• [21] C. Maduabuchi et al., ‘Renewable Energy Potential Estimation Using Climatic-Weather-Forecasting Machine Learning Algorithms’, Energies, vol. 16, no. 4, 2023, doi: 10.3390/en16041603.
• [22] S. Islam and N. K. Roy, ‘Renewables integration into power systems through intelligent techniques: Implementation procedures, key features, and performance evaluation’, Energy Reports, vol. 9, pp. 6063–6087, 2023, doi: 10.1016/j.egyr.2023.05.063.
• [23] F. Z. Ennaji, A. El Fazziki, H. El Alaouiel Abdallaoui, A. Sadiq, M. Sadgal, and D. Benslimane, ‘Multi-agent framework for social CRM: Extracting and analyzing opinions’, in Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA, IEEE Computer Society, Jul. 2016. doi: 10.1109/AICCSA.2016.7945700.
• [24] J. Wang, ‘An Intuitive Tutorial to Gaussian Process Regression’, Computing in Science and Engineering, vol. 25, no. 4, pp. 4–11, 2023, doi: 10.1109/MCSE.2023.3342149.
• [25] P. S. Palar, L. Parussini, L. Bregant, K. Shimoyama, and L. R. Zuhal, ‘On kernel functions for bi-fidelity Gaussian process regressions’, Structural and Multidisciplinary Optimization, vol. 66, no. 2, pp. 1–22, 2023, doi: 10.1007/s00158-023-03487-y.
• [26] S. Barthelmé, P. O. Amblard, N. Tremblay, and K. Usevich, ‘Gaussian Process Regression in the Flat Limit’, Annals of Statistics, vol. 51, no. 6, pp. 2471–2505, 2023, doi: 10.1214/23-AOS2336.
• [27] J. Dearmon and T. E. Smith, ‘A Local Gaussian Process Regression Approach, to Mass Appraisal of Residential Properties’, Journal of Real Estate Finance and Economics, no. 0123456789, 2024, doi: 10.1007/s11146-024-09980-5.
• [28] Y. Xie, D. Wu, and Z. Qiang, ‘A unifying view for the mixture model of sparse Gaussian processes’, Information Sciences, vol. 660, no. May 2023, 2024, doi: 10.1016/j.ins.2024.120124.
• [29] B. Jin and X. Xu, ‘Forecasting wholesale prices of yellow corn through the Gaussian process regression’, Neural Computing and Applications, vol. 36, no. 15, pp. 8693–8710, 2024, doi: 10.1007/s00521-024-09531-2.
• [30] S. Manzhos and M. Ihara, ‘Degeneration of kernel regression with Matern kernels into low-order polynomial regression in high dimension’, Journal of Chemical Physics, vol. 160, no. 2, 2024, doi: 10.1063/5.0187867.
• [31] J. Li, Y. Liu, and W. Wang, ‘Optimal Rates for Agnostic Distributed Learning’, IEEE Transactions on Information Theory, vol. 70, no. 4, pp. 2759–2778, 2024, doi: 10.1109/TIT.2023.3344656.
• [32] L. Tang and Z. H. Zhang, ‘Nuclear charge radius predictions by kernel ridge regression with odd–even effects’, Nuclear Science and Techniques, vol. 35, no. 2, pp. 1–9, 2024, doi: 10.1007/s41365-024-01379-4.
• [33] A. M. Almarzooqi, M. Maalouf, T. H. M. El-Fouly, V. E. Katzourakis, M. S. El Moursi, and C. V. Chrysikopoulos, ‘A hybrid machine-learning model for solar irradiance forecasting’, Clean Energy, vol. 8, no. 1, pp. 100–110, 2024, doi: 10.1093/ce/zkad075.
• [34] L. Ran, Z. Wang, B. Yang, A. Amiri-Margavi, and N. Alshahrani, ‘Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures’, Case Studies in Thermal Engineering, vol. 54, no. January, p. 104076, 2024, doi: 10.1016/j.csite.2024.104076.
• [35] W. Wan and M. Xu, ‘The implementation of a multi-layer perceptron model using meta-heuristic algorithms for predicting undrained shear strength’, Multiscale and Multidisciplinary Modeling, Experiments and Design, 2024, doi: 10.1007/s41939-024-00435-1.
• [36] C. Liu et al., ‘End-to-end methane gas detection algorithm based on transformer and multi-layer perceptron’, Optics Express, vol. 32, no. 1, p. 987, 2024, doi: 10.1364/oe.511813.
• [37] X. Feng, Y. H. Xiu, H. X. Long, Z. T. Wang, A. Bilal, and L. M. Yang, ‘Advancing single-cell RNA-seq data analysis through the fusion of multi-layer perceptron and graph neural network’, Briefings in Bioinformatics, vol. 25, no. 1, pp. 1–13, 2024, doi: 10.1093/bib/bbad481.
• [38] J. Bak, M. Tai, D. Park, and S. Jeong, ‘Subsonic Wind Tunnel Wall Interference Correction Method Using Data Mining and Multi-Layer Perceptron’, International Journal of Aeronautical and Space Sciences, 2024, doi: 10.1007/s42405-023-00704-2.
• [39] X. Wu, G. Yan, W. Zhang, and Y. Bao, ‘Prediction Of Compressive Strength Of High-performance Concrete Using Multi-layer Perceptron’, Journal of Applied Science and Engineering (Taiwan), vol. 27, no. 7, pp. 2719–2733, 2024, doi: 10.6180/jase.202407_27(7).0004.
• [40] S. Das, S. Moon, R. Kaur, G. Sharma, P. Kumar, and U. Lavrenčič Štangar, ‘Artificial neural network modeling of photocatalytic degradation of pollutants: a review of photocatalyst, optimum parameters and model topology’, Catalysis Reviews - Science and Engineering, vol. 00, no. 00, pp. 1–35, 2024, doi: 10.1080/01614940.2024.2338131.
• [41] S. Mobile, E. Computing, U. Hybrid, and L. Method, ‘Learning Method’, pp. 1–19, 2024.
• [42] C. S. Jiang, X. Chen, B. Y. Jiang, and G. Q. Liang, ‘Hybrid genetic algorithm and support vector regression for predicting the shear capacity of recycled aggregate concrete beam’, Soft Computing, vol. 28, no. 2, pp. 1023–1039, 2024, doi: 10.1007/s00500-023-09380-6.
• [43] Y. Lin, L. Li, S. Yang, X. Chen, X. Li, and Z. Zhu, ‘Performance prediction and optimization of hydrogenation feed pump based on particle swarm optimization–least squares support vector regression surrogate model’, Engineering Applications of Computational Fluid Mechanics, vol. 18, no. 1, 2024, doi: 10.1080/19942060.2024.2315985.
• [44] Y. Huang, Z. Zhou, M. Li, and X. Luo, ‘Prediction of Ground Vibration Induced by Rock Blasting Based on Optimized Support Vector Regression Models’, Computer Modeling in Engineering & Sciences, vol. 139, no. 3, pp. 3147–3165, 2024, doi: 10.32604/cmes.2024.045947.
• [45] Y. Zhuo and T. Morimoto, ‘A Hybrid Model for Forecasting Realized Volatility Based on Heterogeneous Autoregressive Model and Support Vector Regression’, Risks, vol. 12, no. 1, 2024, doi: 10.3390/risks12010012.
• [46] M. Açikkar, ‘Fast grid search: A grid search-inspired algorithm for optimizing hyperparameters of support vector regression’, Turkish Journal of Electrical Engineering and Computer Sciences, vol. 32, no. 1, pp. 68–92, 2024, doi: 10.55730/1300-0632.4056.
• [47] K. K. Yaswanth, V. Sathish Kumar, J. Revathy, G. Murali, and C. Pavithra, ‘Compressive strength prediction of ternary blended geopolymer concrete using artificial neural networks and support vector regression’, Innovative Infrastructure Solutions, vol. 9, no. 2, pp. 1–24, 2024, doi: 10.1007/s41062-023-01343-y.
• [48] L. Sun and T. Li, ‘Using Novel Optimization Algorithms with Support Vector Regression to Estimate Pile Settlement Rates’, Indian Geotechnical Journal, 2024, doi: 10.1007/s40098-024-00901-0.
• [49] B. Sharma and N. K. Goel, ‘Streamflow prediction using support vector regression machine learning model for Tehri Dam’, Applied Water Science, vol. 14, no. 5, 2024, doi: 10.1007/s13201-024-02135-0.
• [50] M. Abroun, A. Jahangiri, A. G. Shamim, and H. Heidari, ‘Predicting long-term electricity prices using modified support vector regression method’, Electrical Engineering, 2024, doi: 10.1007/s00202-023-02174-x.
• [51] J. Gao and Y. Liu, ‘Prediction and the influencing factor study of colorectal cancer hospitalization costs in China based on machine learning-random forest and support vector regression: a retrospective study’, Frontiers in Public Health, vol. 12, no. February, pp. 1–11, 2024, doi: 10.3389/fpubh.2024.1211220.
• [52] J. Yao, Y. Zhang, X. Liang, and T. Ding, ‘Investigating the estimation of optimum moisture content through support vector regression in individual and hybrid approaches’, Multiscale and Multidisciplinary Modeling, Experiments and Design, 2024, doi: 10.1007/s41939-024-00397-4.
• [53] M. Achite, S. Emami, M. Jehanzaib, O. M. Katipoğlu, and H. Emami, ‘An election algorithm combined with support vector regression for estimating hydrological drought’, Modeling Earth Systems and Environment, vol. 10, no. 1, pp. 1395–1405, 2024, doi: 10.1007/s40808-023-01850-y.