1. A Nonisolated Single-Inductor Multiport DC–DC Topology Deduction Method Based on Reinforcement Learning
- Author
-
Yong Kang, Yu Chen, and Jingbo Bai
- Subjects
Set (abstract data type) ,Artificial neural network ,Computer science ,Power electronics ,Energy Engineering and Power Technology ,Reinforcement learning ,Topology (electrical circuits) ,Port (circuit theory) ,Electrical and Electronic Engineering ,Converters ,Network topology ,Topology - Abstract
Single-inductor multi-port converters have great application potential due to their “more silicon less magnetic” feature. However, the recent topology design methods, such as the forward design and reverse design, require strong power electronics knowledge, which troubles the application engineers lacking power electronics background. In this paper, a topology deduction method based on Reinforcement Learning (RL) is proposed to gain the benefits of both forward and inverse design. The proposed method uses a neural network (NN) for forward design, and takes a set of simple rules to give rewards for reverse design. With RL, the NN sums up experience during trial-and-error without human intervention, and finally finds the topology that gains the highest reward. Benefits of this method include: (1) it only requires design specifications such as components and port voltage as inputs and some simple rules as rewards, avoiding complicated feature predesign; (2) it allows the deduction to be started from any pre-connection, satisfying the prior constraints of application engineers, and (3) it can recommend several actions at each step, providing good diversity of deduction results. Using this method, many topologies in the literatures are deduced, and some new topologies are also found. One of the topologies is experimentally tested and the results show the validity.
- Published
- 2022