Comparative Analysis of MPPT Techniques for PMSG-Based Wind Energy Systems Using ANN and P&O Algorithms
Abstract views: 39
/ 
PDF downloads: 11
Keywords:
Wind Energy, MPPT, PMSG, Artificial Neural Networks, Perturb and Observe, MATLAB/Simulink, Energy StorageAbstract
This paper presents a comprehensive comparative study of Maximum Power Point Tracking
(MPPT) techniques for wind energy systems utilizing a Permanent Magnet Synchronous Generator
(PMSG). The objective is to enhance energy harvesting efficiency in fluctuating wind conditions through
improved MPPT strategies. Traditional Perturb and Observe (P&O) algorithms, known for their
simplicity and low computational requirements, are evaluated against Artificial Neural Network (ANN)
based MPPT controllers, which leverage machine learning to adaptively optimize power output. Using
MATLAB/Simulink, a detailed simulation model incorporating wind turbine aerodynamics, PMSG
dynamics, full-bridge rectification, and double boost DC-DC conversion was developed. The P&O
method exhibited notable power oscillations and slower response to wind speed changes. In contrast, the
ANN-based MPPT, trained on real meteorological data, demonstrated superior performance with faster
convergence, higher tracking accuracy, and reduced ripple. The hybrid integration of P&O and ANN
approaches further balanced computational complexity with efficiency. Additionally, a stationary battery
storage system with a bidirectional DC-DC converter was implemented to assess energy storage
capability for electric vehicle charging. Simulation results validate the ANN-based controller's
effectiveness under variable wind profiles, making it a viable candidate for real-time wind power
applications. This study highlights the transformative potential of AI in renewable energy systems and
emphasizes the importance of integrating smart control algorithms for optimal wind energy conversion.
Future work will focus on real-world implementation and economic evaluation under diverse atmospheric
conditions.
Downloads
References
Ghatak, A., Pandit, T., & Kavitha, S. R. (2021, October). Design of PMSG based wind energy conversion system with MPPT for maximum power extraction. In 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC) (pp. 471-477). IEEE.
Belkhiri, D., Ajaamoum, M., Cherifi, K., Elidrissi, A., & Alaoui, M. R. E. M. (2023, May). Artificial intelligence-based MPPT techniques in wind energy systems: a literature review. In 2023 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) (pp. 1-6). IEEE.
Bihi, M. B., & Karasu, Y. E. (2024). Enhancing Photovoltaic System Performance: A Comparative Study of AI-Based Neural Networks and Traditional MPPT Techniques. International Journal of Advanced Natural Sciences and Engineering Researches, 8(11), 554-568.
Samokhvalov, D. V., Jaber, A. I., & Almahturi, F. S. (2021). Maximum power point tracking of a wind-energy conversion system by vector control of a permanent magnet synchronous generator. Russian Electrical Engineering, 92(3), 163-168
Beik, O., & Schofield, N. (2017). High-voltage hybrid generator and conversion system for wind turbine applications. IEEE Transactions on Industrial Electronics, 65(4), 3220-3229.
Putri, R. I., Syamsiana, I. N., & Rifa’i, M. (2020). Power extraction optimization of PMSG wind turbine system based on simple modified perturb & observe. ICIC Express Letters, Part B: Applications, 11(1), 17-24.
Rekioua, D. (2014). Wind power electric systems. Green Energy and Technology, London Springer.
Tiwari, R., Pandiyan, P., Saravanan, S., Chinnadurai, T., Prabaharan, N., & Kumar, K. (2022). Quadratic boost converter for wind energy conversion system using back propagation neural network maximum power point tracking. International Journal of Energy Technology and Policy, 18(1), 71-89.
Abo-Khalil, A. G., & Lee, D. C. (2006, June). Dynamic modeling and control of wind turbines for grid-connected wind generation system. In 2006 37th IEEE Power Electronics Specialists Conference (pp. 1-6). IEEE.
Saravanan, S., & Babu, N. R. (2016). Maximum power point tracking algorithms for photovoltaic system–A review. Renewable and Sustainable Energy Reviews, 57, 192-204.
Abo-Khalil, A. G., & Lee, D. C. (2006, June). Dynamic modeling and control of wind turbines for grid-connected wind generation system. In 2006 37th IEEE Power Electronics Specialists Conference (pp. 1-6). IEEE.
Yonıs, S. A., Yusupov, Z., & Guneser, M. T. Designing a Solar PV-Battery based on Electric Vehicle Charging Station. International Journal of Engineering and Innovative Research, 5(2), 123-136.
