YSA Tabanlı MPPT'ye Genel Bir Bakış ve Bir Örnek

Abstract

Bu çalışma, kavram kanıtı olarak YSA denetleyicisi kullanan PV sistemleri için MPPT'ye genel bir bakış ve bir simülasyon sunmaktadır. Dünya yenilenebilir enerji kaynaklarına yönelirken güneş enerjisi yüksek verimlilikle toplanmalıdır. Alışılagelmiş P&O ve InC yöntemi, MPP etrafında salınarak güç kaybeder ve ani hava değişikliklerine yavaş tepki verir. Bu nedenle çalışma, YSA'yı daha iyi bir seçenek olarak test etmektedir. Yazarlar, birçok ağ türünü, eğitim şemasını ve karma stratejileri kapsayan daha önceki YSA tabanlı MPPT çalışmalarını incelemektedir. Daha sonra aynı PV dizisi üzerinde bir YSA kontrolörü ve bir P&O kontrolörü çalıştıran bir MATLAB Simulink modeli oluşturmuşturlardır. YSA, İstanbul 2020 hava durumu verileriyle eğitilmiştir. Sonuçlar, YSA'nın 252 W ve yüzde 87.9 verimliliğe ulaştığını, P&O'nun 241 W ve yüzde 84.26 verimliliğe ulaştığını ve InC'nin 245 W ve yüzde 78.1 verimliliğe ulaştığını göstermiştir. YSA ayrıca MPP'yi daha hızlı ve ışınım değiştiğinde daha istikrarlı bir davranışla takip etmektedir. Bu sonuçlar, YSA tabanlı MPPT'nin PV sistemlerinin enerji çıkışını artırabileceğini doğrulamaktadır.

Keywords

• Yapay Sinir Ağları (YSA)
• En Yüksek Güç Noktası Takibi (EYGNT)(MPPT)
• Fotovoltaik
• Yenilenebilir enerji

An Overview of ANN based MPPT and an Example

Abstract

The study presents an overview and a simulation of maximum power point tracking (MPPT) for Photovoltaic (PV) systems that uses an artificial neural network (ANN) controller as proof of concept. Solar energy must be harvested with high efficien-cy as the world turns to renewables. The usual Perturb and Observe (P&O) and Incremental (InC) method loses power by oscil-lating around the Maximum Power Point (MPP) and reacts slowly to sudden weather changes. The work therefore tests an ANN as a better choice. The authors survey earlier ANN MPPT studies that cover many network types, training schemes and mixed strategies. They then build a MATLAB/Simulink model that runs an ANN controller and a P&O controller on the same PV array. The ANN learns from Istanbul 2020 weather data. The results show the ANN reaches 252 W and 87.9% of efficiency while P&O reaches 241 W and 84.26% of efficiency, and InC reaches 245 W and 78.1% of efficiency. The ANN also tracks the MPP faster and with steadier behaviour when irradiance varies. These outcomes confirm that ANN MPPT can raise the energy output of PV systems.

Keywords

• Artificial Neural Network (ANN)
• Maximum Power Point Tracking (MPPT)
• Photovoltaics
• Renewable energy

References

1. [1] M. Hussain, A. Sarwar, M. Tariq, S. Urooj, A. BaQais, & M. Hossain, "An evaluation of ann algorithm perfor-mance for mppt energy harvesting in solar pv systems", Sustainability, vol. 15, no. 14, p. 11144, 2023.
2. [2] Ž. Zečević and M. Rolevski, "Neural network approach to mppt control and irradiance estimation", Applied Sci-ences, vol. 10, no. 15, p. 5051, 2020.
3. [3] S. Al-Majidi, M. Abbod, & H. Al‐Raweshidy, "Design of an intelligent mppt based on ann using a real photovol-taic system data”, p. 1-6, 2019.
4. [4] L. Elobaid, A. Abdelsalam, & E. Zakzouk, "Artificial neural network‐based photovoltaic maximum power point tracking techniques: a survey", Iet Renewable Power Generation, vol. 9, no. 8, p. 1043-1063, 2015.
5. [5] O. Veligorskyi, R. Chakirov, & Y. Vagapov, "Artificial neural network-based maximum power point tracker for the photovoltaic application”, 2015.
6. [6] J. Lima, J. Corleta, A. Medeiros, V. Canalli, F. Antunes, F. Libanoet al., "A pic controller for grid connected pv system using a fpga based inverter”, vol. 1, p. 169-173.
7. [7] S. Messalti, A. Harrag, & A. Loukriz, "A new neural net-works mppt controller for pv systems”, p. 1-6, 2015.
8. [8] M. Tsai, C. Tseng, K. Hung, & S. Lin, "A novel dsp-based mppt control design for photovoltaic systems using neural network compensator", Energies, vol. 14, no. 11, p. 3260, 2021.

9. [9] M. Yılmaz, R. Çelikel, & A. Gündoğdu, "Enhanced pho-tovoltaic systems performance: anti-windup pi control-ler in ANN arv mppt method", IEEE Access, vol. 11, p. 90498-90509, 2023.
10. [10] J. Morgoš, P. Klčo, & K. Hrudkay, "Artificial neural network based mppt algorithm for modern household with electric vehicle", Communications - Scientific Let-ters of the University of Zilina, vol. 24, no. 1, p. C18-C26, 2022.
11. [11] U. Younas, A. Kulaksız, & Z. Ali, "Deep learning stack lstm based mppt control of dual stage 100 kwp grid-tied solar pv system", IEEE Access, vol. 12, p. 77555-77574, 2024.
12. [12] M. Makhloufi, Y. Abdessemed, & M. Khireddine, "A feed forward neural network mppt control strategy ap-plied to a modified Cúk converter", International Jour-nal of Electrical and Computer Engineering (IJECE), vol. 6, no. 4, p. 1421, 2016. https://doi.org/10.11591/ijece.v6i4.9704
13. [13] J. Khanam and S. Foo, "Modeling of a photovoltaic array in matlab simulink and maximum power point tracking using neural network", Electrical & Electronic Technology Open Access Journal, vol. 2, no. 2, p. 40-46, 2018.
14. [14] Rauschenbach, H. S. "Solar cell array design handbook-The principles and technology of photovoltaic energy conversion." NASA STI/Recon Technical Report A 80 (1980): 34847.
15. [15] A. Orioli and A. Gangi, "A criterion for rating the usabil-ity and accuracy of the one-diode models for photovol-taic modules", Energies, vol. 9, no. 6, p. 427, 2016.
16. [16] S. Adak, H. Cangi, A. Yilmaz, & U. Arifoğlu, "Develop-ment software program for extraction of photovoltaic cell equivalent circuit model parameters based on the newton–raphson method", Journal of Computational Electronics, 2022.
17. [17] S. Pindado, J. Cubas, E. Roibás-Millán, F. Bugallo-Siegel, & F. Sorribes-Palmer, "Assessment of explicit models for different photovoltaic technologies", Ener-gies, vol. 11, no. 6, p. 1353, 2018. https://doi.org/10.3390/en11061353
18. [18] D. V. Sudarsan Reddy and T. S. Thangavel, “Review on power electronic boost converters,” Australian Journal of Electrical & Electronics Engineering, vol. 18, no. 3, pp. 127-137, 2021, doi: 10.1080/1448837X.2021.1935091.
19. [19] N. Thulasiraman, L. Viswanathan, and P. Sriramalaksh-mi, “Review of DC-DC boost converter derived topolo-gies for renewable energy applications,” International Journal of Power Electronics and Drive Systems, vol. 15, no. 2, pp. 947-957, 2024, doi: 10.11591/ijpeds. v15.i2. pp947-957.
20. [20] B. Poorali and E. Adib, “Right-half-plane zero elimina-tion of boost converter using magnetic coupling with forward energy transfer,” IEEE Transactions on Indus-trial Electronics, vol. 66, no. 11, pp. 8454-8462, 2019, doi: 10.1109/TIE.2019.2891408.
21. [21] J. Sun, D. M. Mitchell, M. F. Greuel, P. T. Krein, and R. M. Bass, “Averaged modeling of PWM converters oper-ating in discontinuous conduction mode,” IEEE Trans-actions on Power Electronics, vol. 16, no. 4, pp. 482-492, 2001, doi: 10.1109/63.931052.
22. [22] W. Tang, F. C. Lee, and R. B. Ridley, “Small-signal modeling of average current-mode control,” IEEE Transactions on Power Electronics, vol. 8, no. 2, pp. 112-119, 1993, doi: 10.1109/63.223961.
23. [23] Y. Gu, D. Zhang, and Z. Zhao, “Input/output current ripple cancellation and RHP zero elimination in a boost converter using an integrated magnetic technique,” IEEE Transactions on Power Electronics, vol. 30, no. 2, pp. 747-756, 2015, doi: 10.1109/TPEL.2014.2327059.
24. [24] I. Bashir, A. H. Bhat, and S. Ahmad, “A review on soft-switched PFC boost converter for efficient lowering of switching losses”, Electric Power Systems Research, vol. 242, Art. no. 111430, 2025, doi: 10.1016/j.epsr.2025.111430.
25. [25] N. Boubekri, D. Saifia, S. Doudou, and M. Chadli, “SOS-Based Robust Control Design Subject to Actuator Satu-ration for Maximum Power Point Tracking of Photovol-taic System,” in Advances in Robust Control and Ap-plications, N. Derbel et al., Eds. Singapore: Springer, 2023, pp. 53–85. doi: 10.1007/978-981-99-3463-8_3
26. [26] A. Ali et al., “Review of Online and Soft-Computing Maximum Power Point Tracking Techniques under Non-Uniform Solar Irradiation Conditions,” Energies, vol. 13, no. 12, p. 3256, 2020. doi: 10.3390/en13123256
27. [27] C. A. Berard Jr., “A Second-Generation (High-Speed) Maximum Power Tracker for Space Applications,” Space Congress Proc., pp. 752–758, 1968.
28. [28] D. Mlakić, L. Majdandžić, and S. Nikolovski, “ANFIS Used as a Maximum Power Point Tracking Algorithm for a Photovoltaic System,” Int. J. Electr. & Comput. Eng., vol. 8, no. 2, pp. 867–879, 2018. doi: 10.11591/ijece. v8i2.pp867-879
29. [29] T. Sutikno et al., “A Review of Recent Advances in Metaheuristic Maximum Power Point Tracking Algo-rithms for Solar Photovoltaic Systems under Partial-Shading Conditions,” Indon. J. Sci. Technol., vol. 7, no. 1, pp. 131–158, 2021. doi: 10.17509/ijost. v7i1.45612
30. [30] P. Bharadwaj and V. John, “Optimised Global Maximum Power Point Tracking of Photovoltaic Systems Based on Rectangular Power Comparison,” IEEE Access, vol. 9, pp. 53602–53616, 2021. doi: 10.1109/ACCESS.2021.3071136
31. [31] I. Sajid et al., “An MPPT Method Using Phasor Particle Swarm Optimisation for PV-Based Generation under Varying Irradiance,” IET Renew. Power Gener., vol. 18, no. 16, pp. 4197–4209, 2024. doi: 10.1049/rpg2.13158
32. [32] I. Naidu et al., “A Novel Mine Blast Optimisation Algo-rithm-Based MPPT Controlling for Grid-PV Systems,” AIMS Electr. & Electr. Eng., vol. 7, no. 2, pp. 135–155, 2023. doi: 10.3934/electreng.2023008
33. [33] L. Qi and Z. Shangguan, “Reliability analysis of waste tires semi-submersible breakwater,” Applied Mechanics and Materials, vol. 864, pp. 363–368, 2017.
34. [34] J. Günther, E. Reichensdörfer, P. Pilarski, and K. Di-epold, “Interpretable PID parameter tuning for control engineering using general dynamic neural networks: an extensive comparison,” PLOS ONE, vol. 15, no. 12, e0243320, 2020.
35. [35] I. Farkhoutdinov, “The use of artificial neural networks to solve the ‘make or buy’ problem,” Helix, vol. 9, no. 4, pp. 5243–5247, 2019. https://doi.org/10.29042/2019-5243-5247
36. [36] T. Knez, O. Machidon, and V. Pejović, “Self-adaptive approximate mobile deep learning,” Electronics, vol. 10, no. 23, 2958, 2021. https://doi.org/10.3390/electronics10232958
37. [37] I. Tsoulos, A. Tzallas, and E. Karvounis, “Constructing the bounds for neural network training using grammati-cal evolution,” Computers, vol. 12, no. 11, 226, 2023.
38. [38] N. Nedjah and L. Mourelle, “Reconfigurable hardware for neural networks: binary versus stochastic,” Neural Computing and Applications, vol. 16, no. 3, pp. 249–255, 2007.
39. [39] A. Łuksza and W. Sieńko, “Traveling salesman problem solutions by using passive neural networks,” in Proc. 11th Int. Conf. Informatics in Control, Automation and Robotics, 2014.
40. [40] R. Tuntaş, “The modeling and hardware implementation of semiconductor circuit elements by using ANN and FPGA,” Acta Physica Polonica A, vol. 128, no. 2B, pp. B-78–B-82, 2015. https://doi.org/10.12693/aphyspola.128.B-78
41. [41] J. Behler, “Neural-network potential-energy surfaces in chemistry: a tool for large-scale simulations,” Physical Chemistry Chemical Physics, vol. 13, no. 40, pp. 17930–17955, 2011. https://doi.org/10.1039/C1CP21668F
42. [42] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, Oct. 1986.
43. [43] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradi-ent-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998. https://doi.org/10.1109/5.726791
44. [44] I. U. Haq et al., “Neural network-based adaptive global sliding mode MPPT controller design for stand-alone photovoltaic systems,” PLOS ONE, vol. 17, no. 1, p. e0260480, 2022.
45. [45] M. Yılmaz and M. F. Çorapsız, “A novel fast MPPT strategy with high efficiency for fast changing irradi-ance in PV systems,” Renewable Energy, vol. 239, p. 111144, 2025.
46. [46] M. Yılmaz and M. F. Çorapsız, “Artificial neural net-work based MPPT algorithm with boost converter to-pology for stand-alone PV system,” DergiPark, 2022.
47. [47] L. Al-Hmoud and F. Al-Shdefat, “Improving photovolta-ic water pumping system performance with PSO-based MPPT and PSO-based direct torque control using real time simulation,” Sustainability, vol. 16, 2024.
48. [48] M. Yılmaz and M. F. Çorapsız, “A robust MPPT method based on optimizable Gaussian process regression and high-order sliding mode control for solar systems under partial shading conditions,” Renewable Energy, vol. 239, p. 111144, 2025.
49. [49] A. El-Bayoumi and A. A. El-Fergany, “A review of tradi-tional and advanced MPPT approaches for PV systems under uniformly insolation and partially shaded condi-tions,” Energies, vol. 15, no. 3, p. 1031, 2024.
50. [50] J. Morgoš, M. Frivaldsky and M. Balog, “Artificial neu-ral network based MPPT algorithm for modern house-hold with electric vehicle,” Communications, vol. 24, no. 1, 2021.
51. [51] A. G. López-Martínez, A. R. Barrera-Figueroa and G. Chávez-Romero, “Artificial neural networks in MPPT algorithms for optimization of photovoltaic power sys-tems: A review,” Energies, vol. 12, no. 10, p. 1260, 2021.
52. [52] S. Abdulkareem, “An evaluation of ANN algorithm per-formance for MPPT energy harvesting in solar PV sys-tems,” ResearchGate Preprint, 2023.
53. [53] D. S. Pillai and N. Rajasekar, “An MPPT based sensor-less line-line and line-ground fault detection technique for PV systems,” IEEE Trans. Power Electron., vol. PP, no. 99, pp. 1–1, 2018.
54. [54] I. U. Haq et al., “Neural network-based adaptive global sliding mode MPPT controller design for stand-alone photovoltaic systems,” PLOS ONE, vol. 17, no. 1, p. e0260480, 2022.
55. [55] H. N. Hamed and R. J. Al-Rubaye, “ANN based MPPT controller to an interleaved soft switching boost con-verter for a PV system,” International Journal Corner, 2022.
56. [56] A. El-Bayoumi and A. A. El-Fergany, “A review of tradi-tional and advanced MPPT approaches for PV systems under uniformly insolation and partially shaded condi-tions,” Energies, vol. 15, no. 3, p. 1031, 2024.
57. [57] K. Jabri et al., “FPGA implementation of synergetic controller-based MPPT algorithm for a standalone PV system,” Energies, vol. 13, no. 3, p. 64, 2025.
58. [58] S. Z. Islam et al., “Sustainable smart irrigation system using solar PV with rain-water harvesting for indoor plants,” PLOS ONE, 2024.
59. [59] N. Ghouali and S. Boudghène, “Reinforcement neural network-based grid-integrated PV control and battery management system,” Energies, vol. 18, no. 3, p. 637, 2025.
60. [60] R. Benyoucef and F. Benyoucef, “Application of artifi-cial intelligence in wind power systems,” Energies, vol. 15, no. 5, p. 2443, 2025. https://doi.org/10.3390/en15052443
61. [61] T. Guillod et al., “Artificial neural network based fast and accurate inductor modeling and design,” IEEE Open J. Power Electron., vol. 1, pp. 1–1, 2020.
62. [62] M. A. Sayed et al., “Dynamic controller design for max-imum power point tracking control for solar energy sys-tems,” Energies, vol. 13, no. 2, p. 71, 2024.
63. [63] Y. Bengio, “Practical recommendations for gradient-based training of deep architectures,” in Neural Net-works: Tricks of the Trade, 2nd ed., G. Montavon, G. Orr, and K. R. Müller, Eds. Berlin, Germany: Springer, 2012, pp. 437–478.
64. [64] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” Proc. 3rd Int. Conf. Learning Represen-tations (ICLR), San Diego, CA, USA, May 2015.
65. [65] L. Bottou, “Stochastic gradient descent tricks,” in Neu-ral Networks: Tricks of the Trade, 2nd ed., G. Monta-von, G. B. Orr and K.-R. Müller, Eds. Berlin, Germany: Springer, 2012, pp. 421–436. https://doi.org/10.1007/978-3-642-35289-8_25
66. [66] A. C. Wilson, R. Roelofs, M. Stern, N. Srebro and B. Recht, “The marginal value of adaptive gradient meth-ods in machine learning,” in Advances in Neural Infor-mation Processing Systems 30 (NeurIPS), Long Beach, CA, USA, Dec 2017, pp. 4148–4158.
67. [67] M. T. Hagan and M. B. Menhaj, “Training feedforward networks with the Marquardt algorithm,” IEEE Trans. Neural Netw., vol. 5, no. 6, pp. 989–993, Nov 1994.
68. [68] C. Zhang, S. Bengio, M. Hardt, B. Recht and O. Vinyals, “Understanding deep learning requires rethinking gen-eralization,” Proc. 5th Int. Conf. Learning Representa-tions (ICLR), Toulon, France, Apr 2017.
69. [69] N. Mungoli, “Exploring the frontier of deep neural net-works: progress, challenges, and future directions,” J. Electr. Electron. Eng., vol. 2, no. 3, 2023.
70. [70] S. Sengupta et al., “A review of deep learning with spe-cial emphasis on architectures, applications and recent trends,” Knowl.-Based Syst., vol. 194, p. 105596, Mar. 2020.
71. [71] H. Ninomiya, “A novel quasi-Newton-based optimisa-tion for neural network training incorporating Nesterov’s accelerated gradient,” Nonlinear Theory Appl. IEICE, vol. 8, no. 4, pp. 289–301, Oct. 2017.
72. [72] G. Pereyra, G. Tucker, J. Chorowski, Ł. Kaiser, and G. Hinton, “Regularising neural networks by penalising confident output distributions,” arXiv:1701.06548, Jan. 2017.
73. [73] J. Panerati, M. Schnellmann, C. Patience, G. Beltrame, and G. Patience, “Experimental methods in chemical engineering: artificial neural networks – ANNs,” Can. J. Chem. Eng., vol. 97, no. 9, pp. 2372–2382, 2019.