Twisted and Folded Clos-Network Design Model with Two-Step Blocking Probability Guarantee

被引：5

作者：

Taka, Haruto ^{[1
]}

Inoue, Takeru ^{[2
]}

Oki, Eiji ^{[1
]}

机构：

[1] Kyoto University, Graduate School of Informatics, Kyoto,606-8501, Japan

[2] NTT Corporation, NTT Network Innovation Laboratories, Kanagawa,221-0031, Japan

来源：

IEEE Networking Letters | 2024年 / 6卷 / 01期

关键词：

Circuit simulation - Integrated circuits - Optical switches - Switching networks - Timing circuits;

D O I：

10.1109/LNET.2023.3322172

中图分类号：

学科分类号：

摘要：

A data center network often employs a Clos-network structure due to scalability nature. A previous design model analyzed blocking probability to guarantee the quality of Clos network. However, the conditions to guarantee the blocking probability in these models are stringent, which shrinks the switching capacity. This letter proposes a model that relaxes network design constraints to maximize switching capacity while guaranteeing blocking probability in a two-step manner, where the proposed model divides intermediate switches into two groups. Numerical results show that the proposed model achieves a larger switching capacity than a conventional one-step model. © 2019 IEEE.

引用

页码：60 / 64

共 32 条

[31] Integrated Coronary Vascular Disease Diagnosis System Based on Two-Step Neural Network Algorithm Trained by Synthetic Model and Patient Biometric Features
Kim, Young Woo
Kim, Junhong
Lee, Hyeong Jun
Lee, Joon Sang
CIRCULATION, 2021, 144
[32] LSCE-FFNN-v1: a two-step neural network model for the reconstruction of surface ocean pCO2 over the global ocean
Denvil-Sommer, Anna
Gehlen, Marion
Vrac, Mathieu
Mejia, Carlos
GEOSCIENTIFIC MODEL DEVELOPMENT, 2019, 12 (05) : 2091 - 2105

← 1 2 3 4 →