Comparison of deep learning and regression-based MPPT algorithms in PV systems

KARABINAOGLU, MURAT SALIM; GÜNEROGLU, AZİZ; ÇAKIR, BEKIR; kazdaloglu, abdulvehhab; BASOGLU, Mustafa Engin

doi:10.55730/1300-0632.3941

Comparison of deep learning and regression-based MPPT algorithms in PV systems

MURAT SALIM KARABINAOGLU, (TÜBİTAK Ulusal Metroloji Enstitüsü (TÜBİTAK UME), Kocaeli, Türkiye)

Bekir ÇAKIR, (Kocaeli Üniversitesi, Mühendislik Fakültesi, Elektrik Mühendisliği Bölümü, Kocaeli, Türkiye)

Mustafa Engin BAŞOĞLU, (Gümüşhane Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü, Gümüşhane, Türkiye)

abdulvehhab kazdaloglu, (Kocaeli Üniversitesi, Mühendislik Fakültesi, Elektrik Mühendisliği Bölümü, Kocaeli, Türkiye)

AZİZ GÜNEROGLU

Turkish Journal of Electrical Engineering and Computer Sciences

14 0

Yıl: 2022 Cilt: 30 Sayı: 6 Sayfa Aralığı: 2319 - 2338 Metin Dili: İngilizce DOI: 10.55730/1300-0632.3941 İndeks Tarihi: 09-12-2022

Comparison of deep learning and regression-based MPPT algorithms in PV systems

Öz:

Solar energy systems (SES) and photovoltaic (PV) modules should be operated at the maximum power point (MPP) to achieve the highest eﬀiciency in the energy generation processes. Maximum power point tracking (MPPT) applications using conventional methods may not be able to follow the global MPP (GMPP) of the PV system under changing atmospheric conditions and they could oscillate around the local MPP. In this study, a machine learning and deep learning (DL) based long short-term memory (LSTM) model is proposed as an innovative solution for MPPT. Contrary to the traditional MPPT applications using current and voltage sensors, the output resistance of the PV module estimation was made by using environmental parameters (such as temperature and radiation) and artificial intelligence algorithms in this study.The LSTM model was compared with artificial neural networks (ANN) and regression methods regarding mean square error (MSE), root mean square error(RMSE) and mean absolute error (MAE) parameters. It has been determined that the LSTM model has a better performance and could more successfully follow MPP compared to the other methods. Finally, after the comparison with the ANN method, it is proved that LSTM gives 37%, 21%, and 31% more successful MSE, RMSE, and MAE results, respectively.

Anahtar Kelime: Maximum power point tracking deep learning long-short term memory regression artificial neural network

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] Karami N, Moubayed N, Outbib R. General review and classification of different MPPT Techniques. Renewable and Sustainable Energy Reviews 2017; 68: 1-8. doi: 10.1016/j.rser.2016.09.132
[2] Esram T, Chapman PL. Comparison of photovoltaic array maximum power point tracking techniques. IEEE Transactions on Energy Conversion 2007; 22 (2): 439-449. doi: 10.1109/TEC.2006.874230
[3] De Brito MA, Galotto L, Sampaio LP, e Melo GD, Canesin CA. Evaluation of the main MPPT tech- niques for photovoltaic applications. IEEE Transactions on Industrial Electronics 2012; 60 (3): 1156-1167. doi: 10.1109/TIE.2012.2198036
[4] Reisi AR, Moradi MH, Jamasb S. Classification and comparison of maximum power point tracking tech- niques for photovoltaic system: A review. Renewable and Sustainable Energy Reviews 2013; 19: 433-443. doi: 10.1016/j.rser.2012.11.052
[5] Ram JP, Babu TS, Rajasekar N. A comprehensive review on solar PV maximum power point tracking techniques. Renewable and Sustainable Energy Reviews 2017; 67: 826-847. doi: 10.1016/j.rser.2016.09.076
[6] Keyrouz F. Enhanced Bayesian based MPPT controller for PV systems. IEEE Power and Energy Technology Systems Journal 2018; 5 (1): 11-17. doi: 10.1109/JPETS.2018.2811708
[7] Batarseh MG, Za’ter ME. Hybrid maximum power point tracking techniques: A comparative survey, suggested classification and uninvestigated combinations. Solar Energy 2018; 169: 535-555. doi: 10.1016/j.solener.2018.04.045
[8] Bingöl O, Özkaya B. A comprehensive overview of soft computing based MPPT techniques for partial shading conditions in PV systems. Mühendislik Bilimleri ve Tasarım Dergisi 2019; 7 (4): 926-939. doi: 10.21923/jesd.570887
[9] Yang B, Zhong L, Zhang X, Shu H, Yu T et al. Novel bio-inspired memetic salp swarm algorithm and application to MPPT for PV systems considering partial shading condition. Journal of Cleaner Production 2019; 215: 1203-1222. doi: 10.1016/j.jclepro.2019.01.150
[10] Yap KY, Sarimuthu CR, Lim JM. Artificial intelligence based MPPT techniques for solar power system: A review. Journal of Modern Power Systems and Clean Energy 2020; 8 (6): 1043-1059. doi: 10.35833/MPCE.2020.000159
[11] Femia N, Petrone G, Spagnuolo G, Vitelli M. Optimization of perturb and observe maximum power point tracking method. IEEE Transactions on Power Electronics 2005; 20 (4): 963-973. doi: 10.1109/TPEL.2005.850975
[12] Likhith K, Tejas TN, Charan KY, Hosamane V, Bharati SK. Design and Development of an Eﬀicient Photovoltaic System with Maximum Power Point Tracking Technique. International Journal of Engineering Research & Tech- nology (IJERT) NCESC 2018; 6 (13).
[13] Amrouche B, Belhamel M, Guessoum A. Artificial intelligence based P&O MPPT method for photovoltaic systems. Revue des Energies Renouvelables ICRESD-07 Tlemcen 2007: 11-6.
[14] Rizzo SA, Scelba G. ANN based MPPT method for rapidly variable shading conditions. Applied Energy 2015; 145: 124-132. doi: 10.1016/j.apenergy.2015.01.077
[15] Sindhura LS, Chaudary K. Artificial neural network implementation for maximum power point tracking of optimized solar panel. International Journal of Computer Applications 2013; 78 (10).
[16] Khanaki R, Radzi MA, Marhaban MH. Comparison of ANN and P&O MPPT methods for PV applications under changing solar irradiation. In: 2013 IEEE Conference on Clean Energy and Technology (CEAT); Lankgkawi, Malaysia; 2013. pp. 287-292.
[17] Bouselham L, Hajji M, Hajji B, Bouali H. A new MPPT-based ANN for photovoltaic system under partial shading conditions. Energy Procedia 2017; 111: 924-933. doi: 10.1016/j.egypro.2017.03.255
[18] Chtouki I, Wira P, Zazi M. Comparison of several neural network perturb and observe MPPT methods for photovoltaic applications. In: 2018 IEEE International Conference on Industrial Technology (ICIT); Lyon, France; 2018. pp. 909-914.
[19] Çelikel R, Gündoğdu A. ANN-Based MPPT Algorithm for Photovoltaic Systems. Turkish Journal of Science and Technology. 2020; 15 (2): 101-110.
[20] Saravanan S, Babu NR. Maximum power point tracking algorithms for photovoltaic system–A review. Renewable and Sustainable Energy Reviews 2016; 57: 192-204. doi: 10.1016/j.rser.2015.12.105
[21] Salas V, Olias E, Barrado A, Lazaro A. Review of the maximum power point tracking algorithms for stand-alone photovoltaic systems. Solar Energy Materials and Solar Cells 2006; 90 (11): 1555-1578. doi: 10.1016/j.solmat.2005.10.023
[22] Rezk H, Eltamaly AM. A comprehensive comparison of different MPPT techniques for photovoltaic systems. Solar Energy 2015; 112: 1-1. doi: 10.1016/j.solener.2014.11.010
[23] Patel H, Agarwal V. Maximum power point tracking scheme for PV systems operating under partially shaded conditions. IEEE Transactions on Industrial Electronics 2008; 55 (4): 1689-1698. doi: 10.1109/TIE.2008.917118
[24] Oulcaid M, El Fadil H, Yahya A, Giri F. Maximum power point tracking algorithm for photovoltaic systems under partial shaded conditions. IFAC-PapersOnLine 2016; 49 (13): 217-222. doi: 10.1016/j.ifacol.2016.07.954
[25] Jiang LL, Srivatsan R, Maskell DL. Computational intelligence techniques for maximum power point tracking in PV systems: A review. Renewable and Sustainable Energy Reviews 2018; 85: 14-45. doi: 10.1016/j.rser.2018.01.006
[26] Alabedin AZ, El-Saadany EF, Salama MM. Maximum power point tracking for photovoltaic systems using fuzzy logic and artificial neural networks. In: 2011 IEEE Power and Energy Society General Meeting; Detroit, MI, USA; 2011. pp. 1-9. doi: 10.1109/PES.2011.6039690
[27] Behera MK, Saikia LC. A new combined extreme learning machine variable steepest gradient ascent MPPT for PV system based on optimized PI-FOI cascade controller under uniform and partial shading conditions. Sustainable Energy Technologies and Assessments 2020; 42: 100859. doi: 10.1016/j.seta.2020.100859
[28] Eltamaly AM, Farh HM. Dynamic global maximum power point tracking of the PV systems under variant partial shading using hybrid GWO-FLC. Solar Energy 2019; 177: 306-316. doi: 10.1016/j.solener.2018.11.028
[29] Mao M, Cui L, Zhang Q, Guo K, Zhou L, Huang H. Classification and summarization of solar photovoltaic MPPT techniques: A review based on traditional and intelligent control strategies. Energy Reports 2020; 6: 1312-1327. doi: 10.1016/j.egyr.2020.05.013
[30] Kalogerakis C, Koutroulis E, Lagoudakis MG. Global MPPT based on machine-learning for PV arrays operating under partial shading conditions. Applied Sciences 2020; 10 (2): 700. doi: 10.3390/app10020700
[31] Fares D, Fathi M, Shams I, Mekhilef S. A novel global MPPT technique based on squirrel search algorithm for PV module under partial shading conditions. Energy Conversion and Management 2021; 230: 113773. doi: 10.1016/j.enconman.2020.113773
[32] Verma D, Nema S, Shandilya AM, Dash SK. Maximum power point tracking (MPPT) techniques: Recapit- ulation in solar photovoltaic systems. Renewable and Sustainable Energy Reviews 2016; 54: 1018-1034. doi: 10.1016/j.rser.2015.10.068
[33] Kumar N, Hussain I, Singh B, Panigrahi BK. Rapid MPPT for uniformly and partial shaded PV system by using JayaDE algorithm in highly fluctuating atmospheric conditions. IEEE Transactions on Industrial Informatics 2017; 13 (5): 2406-2416. doi: 10.1109/TII.2017.2700327
[34] Phan BC, Lai YC, Lin CE. A deep reinforcement learning-based MPPT control for PV systems under partial shading condition. Sensors 2020; 20 (11): 3039. doi: 10.3390/s20113039
[35] Avila L, De Paula M, Carlucho I, Reinoso CS. MPPT for PV systems using deep reinforcement learning algorithms. IEEE Latin America Transactions 2019; 17 (12): 2020-2027. doi: 10.1109/TLA.2019.9011547
[36] Tina GM, Ventura C, Ferlito S, De Vito S. A state-of-art-review on machine-learning based methods for PV. Applied Sciences 2021; 11 (16): 7550. doi: 10.3390/app11167550
[37] Xie Z, Wu Z. Maximum power point tracking algorithm of PV system based on irradiance estimation and multi-Kernel extreme learning machine. Sustainable Energy Technologies and Assessments 2021; 44: 101090. doi: 10.1016/j.seta.2021.101090
[38] Padmavathi N, Chilambuchelvan A, Shanker NR. Maximum power point tracking during partial shading effect in pv system using machine learning regression controller. Journal of Electrical Engineering & Technology 2021; 16 (2): 737-748. doi: 10.1007/s42835-020-00621-4
[39] Khan NM, Khan UA, Zafar MH. Maximum Power Point Tracking of PV System under Uniform Irradiance and Partial Shading Conditions using Machine Learning Algorithm Trained by Sailfish Optimizer. In: 2021 4th In- ternational Conference on Energy Conservation and Eﬀiciency (ICECE); Lahore, Pakistan; 2021. pp. 1-6. doi: 10.1109/ICECE51984.2021.9406288
[40] Sarvi M, Azadian A. A comprehensive review and classified comparison of mppt algorithms in pv systems. Energy Systems 2021: 1-40.
[41] Rizzo SA, Scelba G. A hybrid global MPPT searching method for fast variable shading conditions. Journal of Cleaner Production 2021; 298: 126775. doi: 10.1016/j.jclepro.2021.126775
[42] Díaz MD, Trujillo CR, Giral R, Vázquez SL. Evaluation of particle swarm optimization techniques applied to maximum power point tracking in photovoltaic systems. International Journal of Circuit Theory and Applications 2021 ; 49 (7): 1849-1867. doi: 10.1002/cta.2978
[43] Bollipo RB, Mikkili S, Bonthagorla PK. Hybrid, optimal, intelligent and classical PV MPPT techniques: A review. CSEE Journal of Power and Energy Systems 2020; 7 (1): 9-33. doi:10.17775/CSEEJPES.2019.02720
[44] Khan ZA, Khan L, Ahmad S, Mumtaz S, Jafar M et al. RBF neural network based backstepping terminal sliding mode MPPT control technique for PV system. Plos one 2021; 16 (4): e0249705. doi: 10.1371/journal.pone.0249705
[45] Başoğlu ME, Kazdaloğlu A, Erfidan T, Bilgin MZ, Çakır B. Performance analyzes of different photovoltaic module technologies under İzmit, Kocaeli climatic conditions. Renewable and Sustainable Energy Reviews 2015; 52: 357-365. doi: 10.1016/j.rser.2015.07.108
[46] Minar MR, Naher J. Recent advances in deep learning: An overview. arXiv preprint arXiv:1807.08169, 2018,21. [47] Schmidhuber J. Deep learning. 28; 10 (11): 32832: Scholarpedia, 2015.
[48] Heaton J. Ian goodfellow, yoshua bengio, and aaron courville: Deep learning. Springer, 2018.
[49] LeCun Y, Bengio Y, Hinton G. Deep learning. nature 2015; 521 (7553): 436-444.
[50] Haykin S. A comprehensive foundation on neural networks.Prentice Hall Upper Saddle River,1999
[51] Werbos PJ. Backpropagation through time: what it does and how to do it. In: Proceedings of the IEEE 1990; 78 (10): 1550-1560.
[52] Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation 1997; 9 (8): 1735-1780.
[53] Gers FA, Schmidhuber J, Cummins F. Learning to forget: Continual prediction with LSTM. Neural computation 2000; 12 (10): 2451-2471.
[54] Lipton ZC, Berkowitz J, Elkan C. A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019, 2015, 29.
[55] Kim TY, Cho SB. Predicting residential energy consumption using CNN-LSTM neural networks. Energy 2019; 182: 72-81.
[56] Kong W, Dong ZY, Jia Y, Hill DJ, Xu Y et al. Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Transactions on Smart Grid 2017; 10 (1): 841-51.
[57] Sagheer A, Kotb M. Time series forecasting of petroleum production using deep LSTM recurrent networks. Neuro- computing 2019; 323: 203-13.
[58] Wang JQ, Du Y, Wang J. LSTM based long-term energy consumption prediction with periodicity. Energy 2020; 197: 117197.
[59] Abdel-Nasser M, Mahmoud K. Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural Computing and Applications 2019; 31 (7): 2727-40.

APA	KARABINAOGLU M, ÇAKIR B, BASOGLU M, kazdaloglu a, GÜNEROGLU A (2022). Comparison of deep learning and regression-based MPPT algorithms in PV systems. , 2319 - 2338. 10.55730/1300-0632.3941
Chicago	KARABINAOGLU MURAT SALIM,ÇAKIR BEKIR,BASOGLU Mustafa Engin,kazdaloglu abdulvehhab,GÜNEROGLU AZİZ Comparison of deep learning and regression-based MPPT algorithms in PV systems. (2022): 2319 - 2338. 10.55730/1300-0632.3941
MLA	KARABINAOGLU MURAT SALIM,ÇAKIR BEKIR,BASOGLU Mustafa Engin,kazdaloglu abdulvehhab,GÜNEROGLU AZİZ Comparison of deep learning and regression-based MPPT algorithms in PV systems. , 2022, ss.2319 - 2338. 10.55730/1300-0632.3941
AMA	KARABINAOGLU M,ÇAKIR B,BASOGLU M,kazdaloglu a,GÜNEROGLU A Comparison of deep learning and regression-based MPPT algorithms in PV systems. . 2022; 2319 - 2338. 10.55730/1300-0632.3941
Vancouver	KARABINAOGLU M,ÇAKIR B,BASOGLU M,kazdaloglu a,GÜNEROGLU A Comparison of deep learning and regression-based MPPT algorithms in PV systems. . 2022; 2319 - 2338. 10.55730/1300-0632.3941
IEEE	KARABINAOGLU M,ÇAKIR B,BASOGLU M,kazdaloglu a,GÜNEROGLU A "Comparison of deep learning and regression-based MPPT algorithms in PV systems." , ss.2319 - 2338, 2022. 10.55730/1300-0632.3941
ISNAD	KARABINAOGLU, MURAT SALIM vd. "Comparison of deep learning and regression-based MPPT algorithms in PV systems". (2022), 2319-2338. https://doi.org/10.55730/1300-0632.3941

APA	KARABINAOGLU M, ÇAKIR B, BASOGLU M, kazdaloglu a, GÜNEROGLU A (2022). Comparison of deep learning and regression-based MPPT algorithms in PV systems. Turkish Journal of Electrical Engineering and Computer Sciences, 30(6), 2319 - 2338. 10.55730/1300-0632.3941
Chicago	KARABINAOGLU MURAT SALIM,ÇAKIR BEKIR,BASOGLU Mustafa Engin,kazdaloglu abdulvehhab,GÜNEROGLU AZİZ Comparison of deep learning and regression-based MPPT algorithms in PV systems. Turkish Journal of Electrical Engineering and Computer Sciences 30, no.6 (2022): 2319 - 2338. 10.55730/1300-0632.3941
MLA	KARABINAOGLU MURAT SALIM,ÇAKIR BEKIR,BASOGLU Mustafa Engin,kazdaloglu abdulvehhab,GÜNEROGLU AZİZ Comparison of deep learning and regression-based MPPT algorithms in PV systems. Turkish Journal of Electrical Engineering and Computer Sciences, vol.30, no.6, 2022, ss.2319 - 2338. 10.55730/1300-0632.3941
AMA	KARABINAOGLU M,ÇAKIR B,BASOGLU M,kazdaloglu a,GÜNEROGLU A Comparison of deep learning and regression-based MPPT algorithms in PV systems. Turkish Journal of Electrical Engineering and Computer Sciences. 2022; 30(6): 2319 - 2338. 10.55730/1300-0632.3941
Vancouver	KARABINAOGLU M,ÇAKIR B,BASOGLU M,kazdaloglu a,GÜNEROGLU A Comparison of deep learning and regression-based MPPT algorithms in PV systems. Turkish Journal of Electrical Engineering and Computer Sciences. 2022; 30(6): 2319 - 2338. 10.55730/1300-0632.3941
IEEE	KARABINAOGLU M,ÇAKIR B,BASOGLU M,kazdaloglu a,GÜNEROGLU A "Comparison of deep learning and regression-based MPPT algorithms in PV systems." Turkish Journal of Electrical Engineering and Computer Sciences, 30, ss.2319 - 2338, 2022. 10.55730/1300-0632.3941
ISNAD	KARABINAOGLU, MURAT SALIM vd. "Comparison of deep learning and regression-based MPPT algorithms in PV systems". Turkish Journal of Electrical Engineering and Computer Sciences 30/6 (2022), 2319-2338. https://doi.org/10.55730/1300-0632.3941