National Taiwan University of Science and Technology
The growing demand for clean energy has driven significant advancements in photovoltaic (PV) systems, necessitating design automation of PV converters to reduce time-to-market and development costs. This paper presents a novel design automation method that integrates finite element analysis (FEA) simulations with Bayesian optimization to minimize the need for physical prototypes. By addressing both efficiency and cost objectives, the proposed approach overcomes the limitations of traditional algorithms and accelerates the prototyping process. Demonstrated through a 10kW interleaved boost converter, this method achieves an optimal balance of performance objectives, enhancing the development of efficient and cost-effective power converters.
