ANN based Predictive Control of Three Phase Grid Connected Photovoltaic Inverter

Abstract

Today, using renewable energy sources is critically essential for sustainable energy. Photovoltaic (PV) systems are widely preferred for using solar energy, one of the renewable energy sources. With the widespread use of PV systems, their efficiency has also gained importance. In grid-connected systems, synchronization with the grid is critical. One of the essential factors affecting synchronization is hardware and software delays. Inverter circuits, the effect of delays in the system can be reduced using predictive controllers. Inverter circuits, the effect of delays in the system can be reduced using predictive controllers. This study aims to increase the system efficiency using a predictive current controller. Therefore, a predictive artificial neural network (ANN) based current controller is proposed for three-phase grid-connected single-stage PV inverter system control. In this work firstly, a 4kVA three-phase grid-connected PV inverter is modeled in a Matlab/Simulink environment. Two different current controllers are used in the simulation, and the obtained results are compared. The Proportional Integrator (PI) was used as the current controller in the first PV inverter system. Then, a PI-based Reference Predictive ANN (PI-PNN) current controller was designed and trained using a simulation structure that includes a PI current controller and a Reference Predictive ANN (RefPNN) in the system. When the results obtained from the simulation study were compared, it was determined that PI-PNN was more efficient than the PI current controller.

Keywords

• Artificial Neural Networks
• Predictive Current Controller
• Grid Connected PV Inverter

Üç Fazlı Şebeke Bağlantılı Fotovoltaik Eviricinin YSA Tabanlı Öngörülü Kontrolü

Öz

Günümüzde sürdürülebilir enerji için yenilebilir enerji kaynaklarının kullanımı kritik bir öneme sahiptir. Yenilenebilir enerji kaynaklarından biri olan güneş enerjisinin kullanımı için yaygın olarak fotovoltaik (PV) sistemler tercih edilmektedir. PV sistemlerin kullanımının yaygınlaşmasıyla birlikte PV sistemlerin verimliliği de önem kazanmıştır. Şebeke bağlantılı sistemlerde, şebeke ile senkronizasyon çok önemlidir. Senkronizasyonu etkileyen önemli etkenlerden biri donanımsal ve yazılımsal gecikmelerdir. Evirici devrelerinde, öngörülü kontrolcüler kullanılarak sistemde oluşacak gecikmelerin etkisi azaltılabilmektedir. Bu çalışmada, öngörülü bir akım kontrolcüsü kullanılarak sistem verimliliğinin arttırılması amaçlanmıştır. Bundan dolayı, üç fazlı şebeke bağlantılı tek aşamalı PV evirici sistem kontrolünde kullanılması için öngörülü yapay sinir ağı (YSA) tabanlı bir akım kontrolcüsü önerilmektedir. Bu çalışmada ilk olarak, Matlab/Simulink ortamından 4kVA’lık üç fazlı şebeke bağlantılı bir PV evirici modellenmiştir. Benzetimde iki farklı akım kontrolcüsü kullanılmış ve elde edilen sonuçlar karşılaştırılmıştır. İlk PV evirici sistemde, akım kontrolcüsü olarak Oransal İntegratör (PI) kullanılmıştır. Daha sonra sistemde PI akım kontrolcüsü ve Referans Akım Öngörücü YSA (RefPNN) içeren bir benzetim yapısı kullanılarak PI tabanlı bir Referans Öngörülü YSA (PI-PNN) akım kontrolcüsü tasarlanmış ve eğitilmiştir. Yapılan simülasyon çalışmasından elde edilen sonuçlar karşılaştırıldığında PI-PNN’nin, PI akım kontrolcüsüne göre daha verimli olduğu tespit edilmiştir.

Anahtar Kelimeler

• Yapay Sinir Ağları
• Öngörülü Akım Kontrolcüsü
• Şebeke Bağlantılı PV evirici

Kaynakça

1. Arulkumar K., Vijayakumar D., Palanisamy K., Recent advances and control techniques in grid connected PV system - A review. International Journal of Renewable Energy Research 6(3), 1037-1049, 2016. https://doi.org/10.20508/ijrer.v6i3.4075.g6886
2. Babaie M., Sharifzadeh M., Mehrasa M., Chouinard G., Al-Haddad K., PV Panels Maximum Power Point Tracking based on ANN in Three-Phase Packed E-Cell Inverter. 2020 IEEE International Conference on Industrial Technology (ICIT), 854-859, 2020. https://doi.org/10.1109/ICIT45562.2020.9067218
3. Blaabjerg F., Chen Z., Kjaer S. B., Power electronics as efficient interface in dispersed power generation systems. IEEE Transactions on Power Electronics 19(5), 1184-1194, 2004. https://doi.org/10.1109/TPEL.2004.833453
4. Bouaouaou H., Lalili D., Boudjerda N., Model predictive control and ANN-based MPPT for a multi-level grid-connected photovoltaic inverter. Electrical Engineering 104(3), 1229-1246, 2022. https://doi.org/10.1007/s00202-021-01355-w
5. Boumaaraf H., Talha A., Bouhali O., A three-phase NPC grid-connected inverter for photovoltaic applications using neural network MPPT. In Renewable and Sustainable Energy Reviews 49, 1171-1179, 2015. https://doi.org/10.1016/j.rser.2015.04.066
6. Cameron S., Ameen G., M. E., H., Aman O., Model Predictive Control of Grid Connected Solar PV Inverter. 2020 Australasian Universities Power Engineering Conference (AUPEC), 1-6, 2020.
7. Carrasco J. M., Franquelo L. G., Bialasiewicz J. T., Galvan E., PortilloGuisado R. C., Prats M. A. M., Leon J. I., Moreno-Alfonso N., Power-Electronic Systems for the Grid Integration of Renewable Energy Sources: A Survey. IEEE Transactions on Industrial Electronics 53(4), 1002-1016, 2006. https://doi.org/10.1109/TIE.2006.878356
8. Ciobotaru M., Teodorescu R., Blaabjerg F., Control of single-stage single-phase PV inverter. EPE Journal (European Power Electronics and Drives Journal) 16(3), 20-26, 2006. https://doi.org/10.1080/09398368.2006.11463624

9. Çınar S. M., Bakım S., Hocaoğlu F. O., Designing a novel MPPT algorithm based on the extraterrestrial irradiance for photovoltaic energy generation systems and testing under partial shade conditions. Journal of Computational Electronics 21(4), 841-851, 2022. https://doi.org/10.1007/s10825-022-01906-9
10. Ge S. S., Yang C., Lee T. H., Adaptive Predictive Control Using Neural Network for a Class of Pure-Feedback Systems in Discrete Time. IEEE Transactions on Neural Networks 19(9), 1599-1614, 2008. https://doi.org/10.1109/TNN.2008.2000446
11. Gopakumar A., Vijayakumari A., Model predictive current controller for grid connected PV inverter. 2017 International Conference on Circuit, Power and Computing Technologies (ICCPCT), 1–6, 2017. https://doi.org/10.1109/ICCPCT.2017.8074309
12. Hannan M. A., Abd Ghani Z., Mohamed A., An Enhanced Inverter Controller for PV Applications Using the dSPACE Platform. International Journal of Photoenergy 2010, 1–10, 2010. https://doi.org/10.1155/2010/457562
13. Harashima F., Demizu Y., Kondo S., Hashimoto H., Application of neural networks to power converter control. Conference Record- IAS Annual Meeting (IEEE Industry Applications Society) pt 1, 1086–1091, 1989. https://doi.org/10.1109/ias.1989.96777
14. Hassaine L., Olias E., Quintero J., Haddadi M., Digital power factor control and reactive power regulation for grid-connected photovoltaic inverter. Renewable Energy 34(1), 315-321, 2009. https://doi.org/10.1016/j.renene.2008.03.016
15. Jana J., Saha H., Das Bhattacharya K., A review of inverter topologies for single-phase grid-connected photovoltaic systems. Renewable and Sustainable Energy Reviews 72, 1256-1270, 2017. https://doi.org/10.1016/j.rser.2016.10.049
16. Khan H. S., Mohamed I. S., Kauhaniemi K., Liu L., Artificial Neural Network-Based Voltage Control of DC/DC Converter for DC Microgrid Applications. 2021 6th IEEE Workshop on the Electronic Grid (eGRID), 1-6, 2021. https://doi.org/10.1109/eGRID52793.2021.9662132
17. Leon J. I., Kouro S., Franquelo L. G., Rodriguez J., Wu B., The Essential Role and the Continuous Evolution of Modulation Techniques for Voltage-Source Inverters in the Past, Present, and Future Power Electronics. IEEE Transactions on Industrial Electronics 63(5), 2688-2701, 2016. https://doi.org/10.1109/TIE.2016.2519321
18. Mohamed A. A. S., Metwally H., El-Sayed A., Selem S. I., Predictive neural network based adaptive controller for grid-connected PV systems supplying pulse-load. Solar Energy 193(September), 139-147, 2019. https://doi.org/10.1016/j.solener.2019.09.018
19. Mohamed I. S., Rovetta S., Do T. D., Dragicevic T., Diab A. A. Z., A neural-network-based model predictive control of three-phase inverter with an output LC Filter. IEEE Access 7, 124737-124749, 2019. https://doi.org/10.1109/ACCESS.2019.2938220
20. Panigrahi R., Mishra S. K., Srivastava S. C., Grid Integration of Small-Scale Photovoltaic Systems-A Review. 2018 IEEE Industry Applications Society Annual Meeting (IAS), 1-8, 2018. https://doi.org/10.1109/IAS.2018.8544503
21. Rajab Al-Jaboury, O. N., Hamodat Z., Daoud R. W., Design of Power Control Circuit for Grid-Connected PV System-Based Neural Network. Journal of Robotics and Control (JRC) 5(3), 821-828, 2024. https://doi.org/10.18196/jrc.v5i3.20751
22. Rivera M., Morales F., Baier C., Munoz J., Tarisciotti L., Zanchetta P., Wheeler P., A modulated model predictive control scheme for a two-level voltage source inverter. 2015 IEEE International Conference on Industrial Technology (ICIT), 2224-2229, 2015. https://doi.org/10.1109/ICIT.2015.7125425
23. Selvan S., Nair P., Umayal U., A Review on Photo Voltaic MPPT Algorithms. International Journal of Electrical and Computer Engineering (IJECE) 6(2), 567, 2016. https://doi.org/10.11591/ijece.v6i2.9204
24. Singh K., Swathi P., Reddy M. U., Performance analysis of PV inverter in microgrid connected with PV system employing ANN control. 2014 International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE), 1-6, 2014. https://doi.org/10.1109/ICGCCEE.2014.6922390
25. Syed I. M., Raahemifar K., Model Predictive Control of Three Phase Inverter for PV Systems. International Journal of Energy and Power Engineering 9(10), 1188-1193, 2015. https://doi.org/10.5281/zenodo.1109641
26. Vora K., Liu S., Dhulipati H., Deep Reinforcement Learning Based MPPT Control for Grid Connected PV System. 2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS), 1-5, 2024. https://doi.org/10.1109/ICPS59941.2024.10639977
27. Yağan Y. E., Vardar K., Ebeoğlu A., Investigation of MPPT Methods Used In PV Systems. IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE) 13(2), 84-95, 2018. https://doi.org/10.9790/1676-1302028495