Edge-AI-Enabled Power Electronics with Embedded Intelligent Control
DOI:
https://doi.org/10.63282/3050-9416.ICAIDSCT26-126Keywords:
Edge Artificial Intelligence, Power Electronics, Intelligent Control, Firmware Automation, Machine Learning, Embedded Systems, Digital Power Converters, Adaptive ControlAbstract
Edge Artificial Intelligence (Edge-AI) is emerging as a transformative technology for next-generation power electronic systems by enabling localized intelligence, low-latency decision-making, and autonomous operation. However, practical implementation challenges, such as limited computational resources on embedded hardware (DSPs and MCUs), energy constraints, and system integration complexity, must be carefully addressed. This paper presents an Edge-AI-enabled framework designed to overcome these challenges and support real-world deployment. The proposed framework incorporates an automated firmware pipeline that leverages AI-driven parameter identification, control-law optimization, and adaptive code generation to enhance system reliability while reducing development time. By continuously learning from operational data, the Edge-AI module enables predictive performance optimization, fault awareness, and dynamic firmware adaptation without reliance on cloud connectivity. Simulation and experimental case-study results demonstrate improved efficiency, faster transient response, and increased system robustness compared with conventional rule-based control and static firmware approaches. Overall, the proposed methodology provides a scalable and practical pathway toward autonomous, intelligent, and resilient power electronic systems for Industry 4.0, electric mobility, and renewable energy applications.
References
1. R. W. Erickson and D. Maksimović, Fundamentals of Power Electronics, 2nd ed., Springer, 2001.
2. J. Sun, “Small-signal methods for AC distributed power systems—A review,” IEEE Trans. Power Electronics, vol. 24, no. 11, pp. 2545–2554, 2009.
3. S. J. Qin and T. A. Badgwell, “A survey of industrial model predictive control technology,” Control Engineering Practice, vol. 11, no. 7, pp. 733–764, 2003.
4. S. Teerapittayanon, B. McDanel, and H. T. Kung, “Distributed deep neural networks over the cloud, the edge, and end devices,” IEEE ICDCS, pp. 328–339, 2017.
5. Y. Duan, X. Li, and J. Liu, “Reinforcement learning–based control of DC–DC converters,” IEEE Trans. Power Electronics, vol. 35, no. 12, pp. 12315–12327, 2020.
6. M. Soliman, O. P. Malik, and D. T. Westwick, “Artificial neural network–based control of power electronic converters,” IEEE Trans. Industrial Electronics, vol. 66, no. 4, pp. 2964–2974, 2019.
7. P. Warden and D. Situnayake, TinyML: Machine Learning with TensorFlow Lite on Arduino and Microcontrollers, O’Reilly, 2020.
8. F. Tao et al., “Digital twins and cyber–physical systems toward smart manufacturing,” Engineering, vol. 5, no. 4, pp. 653–661, 2019.
