From Specification to Topology: Automatic Power Converter Design via Reinforcement Learning

Shaoze Fan, Ningyuan Cao, Shun Zhang, Jing Li, Xiaoxiao Guo, Xin Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The tidal waves of modern electronic/electrical devices have led to increasing demands for ubiquitous application-specific power converters. A conventional manual design procedure of such power converters is computation- and labor-intensive, which involves selecting and connecting component devices, tuning component-wise parameters and control schemes, and iteratively evaluating and optimizing the design. To automate and speed up this design process, we propose an automatic framework that designs custom power converters from design specifications using reinforcement learning. Specifically, the framework embraces upper-confidence-bound-tree-based (UCT-based) reinforcement learning to automate topology space exploration with circuit design specification-encoded reward signals. Moreover, our UCT-based approach can exploit small offline data via the specially designed default policy to accelerate topology space exploration. Further, it utilizes a hybrid circuit evaluation strategy to substantially reduces design evaluation costs. Empirically, we demonstrated that our framework could generate energy-efficient circuit topologies for various target voltage conversion ratios. Compared to existing automatic topology optimization strategies, the proposed method is much more computationally efficient — it can generate topologies with the same quality while being up to 67% faster. Additionally, we discussed some interesting circuits discovered by our framework.

Original languageEnglish (US)
Title of host publication2021 40th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665445078
DOIs
StatePublished - 2021
Event40th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2021 - Munich, Germany
Duration: Nov 1 2021Nov 4 2021

Publication series

NameIEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
Volume2021-November
ISSN (Print)1092-3152

Conference

Conference40th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2021
Country/TerritoryGermany
CityMunich
Period11/1/2111/4/21

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Keywords

  • Design automation
  • Power converter topology design
  • Reinforcement learning
  • Upper-confidence-bound tree (UCT)

Fingerprint

Dive into the research topics of 'From Specification to Topology: Automatic Power Converter Design via Reinforcement Learning'. Together they form a unique fingerprint.

Cite this