An Enhanced Deep Reinforcement Learning Algorithm for Decoupling Capacitor Selection in Power Distribution Network Design

The selection of decoupling capacitors (decap) is a critical but tedious process in power distribution network (PDN) design. In this paper, an improved decap-selection algorithm based on deep reinforcement learning (DRL), which seeks the minimum number of decaps through a self-exploration training to satisfy a given target impedance, is presented. Compared with the previous relevant work: the calculation speed of PDN impedance is significantly increased by adopting an impedance matrix reduction method; also, the enhanced algorithm performs a better convergence by utilizing the techniques of double Q-learning and prioritized experience replay; furthermore, a well-designed reward is proposed to facilitate long-term convergence when more decaps are required. The proposed algorithm demonstrates the feasibility of achieving decent performance using DRL with pre-trained knowledge for more complicated engineering tasks in the future.

I. Introduction

Placing decoupling capacitors (decap) is crucial to the power distribution network (PDN) design to lower down the impedance seen at IC ports and control the power supply fluctuation caused by large switching currents [1]–[5]. Typically, searching for the minimum number of decaps to satisfy a target impedance is desired in the industry to save cost and layout space. However, this process is usually tedious and time-consuming due to the tremendous search space induced by considerable decap library sizes and possible decap locations. Fig. 1.

Decap selection and placement in PDN.