MMM
YYYY
Code design and latency analysis of distributed matrix multiplication with straggling servers in fading channels
衰落信道中散乱服务器分布式矩阵乘法的代码设计和时延分析
フェージングチャネル内のストラッグリングサーバーを使用した分散行列乗算のコード設計と遅延分析
페이딩 채널에서 지연 서버를 사용한 분산 행렬 곱셈의 코드 설계 및 대기 시간 분석
Diseño de código y análisis de latencia de la multiplicación de matrices distribuidas con servidores rezagados en canales que se desvanecen
Conception de code et analyse de latence de la multiplication matricielle distribuée avec des serveurs errants dans des canaux en déclin
Разработка кода и анализ задержки при распределенном умножении матриц с неравномерными серверами в каналах с замиранием
Ning Liu ¹, Kuikui Li 李奎奎 ², Meixia Tao 陶梅霞 ³
¹ School of Electronics, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
中国 上海 上海交通大学电子信息与电气工程学院
² Huawei Technologies Co., Ltd., Shanghai 201206, China
中国 上海 华为技术有限公司
³ Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
中国 上海 上海交通大学电子工程系
China Communications, 13 November 2021
Abstract

This paper exploits coding to speed up computation offloading in a multi-server mobile edge computing (MEC) network with straggling servers and channel fading. The specific task we consider is to compute the product between a user-generated input data matrix and a large-scale model matrix that is stored distributively across the multiple edge nodes.

The key idea of coding is to introduce computation redundancy to improve robustness against straggling servers and to create communication redundancy to improve reliability against channel fading. We utilize the hybrid design of maximum distance separable (MDS) coding and repetition coding. Based on the hybrid coding scheme, we conduct theoretical analysis on the average task uploading time, average edge computing time, and average output downloading time, respectively and then obtain the end-to-end task execution time.

Numerical results demonstrate that when the task uploading phase or the edge computing phase is the performance bottleneck, the hybrid coding reduces to MDS coding; when the downlink transmission is the bottleneck, the hybrid coding reduces to repetition coding. The hybrid coding also outperforms the entangled polynomial coding that causes higher uplink and downlink communication loads.
China Communications_1
China Communications_2
China Communications_3
Reviews and Discussions
https://www.hotpaper.io/index.html
Parametric study on the flutter sensitivity of a wide-chord hollow fan blade
Influence of aspect ratio and arrangement direction on the shear behavior of ellipsoids
Development of a double-layer shaking table for large-displacement high-frequency excitation
Effect of SiC Particle Size on Properties of SiC Porous Ceramics
Physical Layer Authentication in UAV-enabled Relay Networks Based on Manifold Learning
Risk assessment of fault water inrush during deep mining
Simvastatin Improves Outcomes of Endotoxin-induced Coagulopathy by Regulating Intestinal Microenvironment
Sound Insulation Performance of Pyramidal Truss Core Cylindrical Sandwich Structure
Coupling analysis of passenger and train flows for a large-scale urban rail transit system
Effects of minor B additions on tensile strength, fracture toughness and oxidation resistance of Nb–Si based alloys
Essential role of MALAT1 in reducing traumatic brain injury
Seasonal Cumulative Effect of Ural Blocking Episodes on the Frequent Cold events in China during the Early Winter of 2020/21



Previous Article                                Next Article
About
|
Contact
|
Copyright © Hot Paper