A Droplet Approach Based on Raptor Codes for Distributed Computing with Straggling Servers
Paper in proceeding, 2018

We propose a coded distributed computing scheme based on Raptor codes to address the straggler problem. In particular, we consider a scheme where each server computes intermediate values, referred to as droplets, that are either stored locally or sent over the network. Once enough droplets are collected, the computation can be completed. Compared to previous schemes in the literature, our proposed scheme achieves lower computational delay when the decoding time is taken into account.

Author

Albin Severinson

Simula UiB

Alexandre Graell i Amat

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Eirik Rosnes

Simula UiB

Francisco Lázaro

German Aerospace Center (DLR)

Gianluigi Liva

German Aerospace Center (DLR)

International Symposium on Turbo Codes and Iterative Information Processing, ISTC

21654700 (ISSN) 21654719 (eISSN)

8625292
978-153867048-4 (ISBN)

IEEE International Symposium on Turbo Codes & Iterative Information Processing (ISTC)
Hong Kong, Hong Kong,

Rethinking Distributed Storage for Data Storage and Wireless Content Delivery

Swedish Research Council (VR) (2016-04253), 2016-01-01 -- 2019-12-31.

Areas of Advance

Information and Communication Technology

Subject Categories

Telecommunications

Communication Systems

Computer Science

DOI

10.1109/ISTC.2018.8625292

More information

Latest update

3/15/2024