AutoTG: Reinforcement Learning-Based Symbolic Optimization for AI-Assisted Power Converter Design

• Published in: IEEE journal of emerging and selected topics in industrial electronics (Print) Vol. 5; no. 2; pp. 680 - 689
• Main Authors: Silva, Felipe Leno da, Glatt, Ruben, Su, Wencong, Bui, Van-Hai, Chang, Fangyuan, Chaturvedi, Shivam, Wang, Mengqi, Murphey, Yi Lu, Huang, Can, Xue, Lingxiao, Zeng, Rong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial intelligence (AI)-based design; Capacitors; Circuit design; Convertibility; Design optimization; Electronic components; Electronic equipment; Energy requirements; Household appliances; Integrated circuit modeling; Mathematical models; Optimization; power converter design; Power converters; Power efficiency; Power management; Reinforcement learning; Specifications; symbolic optimization applications; Topology; Voltage
• ISSN: 2687-9735; 2687-9743
• DOI: 10.1109/JESTIE.2023.3303836

Power converters are pervasive in modern electronic component design. They can be found in all electronic devices from household appliances and cellphone chargers to vehicles. Currently, designing new circuit topologies is hard because it requires human expertise based on experience and is difficult to automate. However, artificial-intelligence-assisted design can significantly facilitate the development of new power converters and/or improve the final result. Intelligently designed highly efficient power converters can have a significant effect on many important attributes, such as power efficiency, layout size, cost, heat dissemination, energy requirements, etc. We propose Autonomous Topology Generator (AutoTG) , a reinforcement-learning-based framework that generates power converter topology candidates based on user specifications, optimized for user preferences. By modeling power converter design as a symbolic optimization problem, we sequentially sample components in an autoregressive manner until new topologies are formed, providing both the topology specification and the sizing (magnitude of each component parameter) of the proposed power converter. We provide an empirical evaluation and show that AutoTG is able to generate varied high-efficiency topologies within component restrictions based on user input and show that previously unknown topologies can be found for further evaluation.