Open Access Open Access  Restricted Access Subscription Access

A Review on Multilevel Inverters with Machine Learning Techniques

Dr.Y. Lalitha Kameswari

Abstract


Multilevel inverters have appeared as a promising technology for high-power and high-voltage applications due to their capability to produce higher-quality output waveforms with reduced harmonic distortion and improved power quality. However, to fully exploit the potential of multilevel inverters, advanced control strategies and intelligent decision-making are required to optimize their performance and efficiency under various operating conditions. Machine learning techniques have proven to be instrumental in achieving these goals. It highlights the various machine learning applications in multilevel inverters, focusing on their role in enhancing performance and control. By leveraging data-driven insights, machine learning algorithms optimize the switching strategies, modulation indices, and control parameters to minimize harmonic distortions, improve energy conversion efficiency and reduce electromagnetic interference (EMI). Additionally, predictive maintenance models based on machine learning allow for the early detection of potential faults, leading to proactive maintenance and improved system reliability. Furthermore, machine learning enables multilevel inverters to become adaptive and self-learning systems. Through continuous learning from historical data and real-time measurements, these inverters can dynamically adjust their control strategies to adapt to changing load demands and operating conditions, ensuring efficient power flow and stable grid integration. It also discusses the advantages of using machine learning in multilevel inverters, such as improved output waveform quality, higher voltage capability, reduced switching losses, and increased fault tolerance. These advantages position multilevel inverters as a compelling choice for various applications, including renewable energy systems, industrial processes, smart grid integration, and electric vehicle charging. Overall, the application of machine learning in multilevel inverters empowers these power conversion systems with intelligence, adaptability, and efficiency, making them more suitable for addressing the evolving challenges of modern power distribution and utilization. As machine learning techniques continue to evolve, their integration with multilevel inverters is expected to unlock further advancements in power conversion technologies and drive the transition towards a more sustainable and reliable energy landscape.


Full Text:

PDF

References


Adel, T., Valera, I., Ghahramani, Z., & Weller, A. (2019, July). One-network adversarial fairness. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, No. 01, pp. 2412-2420).

Ali, S. M., & Silvey, S. D. (1966). A general class of coefficients of divergence of one distribution from another. Journal of the Royal Statistical Society: Series B (Methodological), 28(1), 131-142.

Barocas, S., & Selbst, A. D. (2016). Big data's disparate impact. California law review, 671-732.

Berk, R., Heidari, H., Jabbari, S., Kearns, M., & Roth, A. (2021). Fairness in criminal justice risk assessments: The state of the art. Sociological Methods & Research, 50(1), 3-44.

Beutel, A., Chen, J., Zhao, Z., & Chi, E. H. (2017). Data decisions and theoretical implications when adversarially learning fair representations. arXiv preprint arXiv:1707.00075.

Blum, A., & Stangl, K. (2019). Recovering from biased data: Can fairness constraints improve accuracy?. arXiv preprint arXiv:1912.01094.

Buolamwini, J., & Gebru, T. (2018, January). Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency (pp. 77-91). PMLR.

Calders, T., Kamiran, F., & Pechenizkiy, M. (2009, December). Building classifiers with independency constraints. In 2009 IEEE international conference on data mining workshops (pp. 13-18). IEEE.

Chi, J., Tian, Y., Gordon, G. J., & Zhao, H. (2021, July). Understanding and mitigating accuracy disparity in regression. In International conference on machine learning (pp. 1866-1876). PMLR.

Chouldechova, A. (2017). Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big data, 5(2), 153-163.


Refbacks

  • There are currently no refbacks.