A distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments

Jong Beom Lim, Joon Min Gil, Heonchang Yu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Many artificial intelligence applications often require a huge amount of computing resources. As a result, cloud computing adoption rates are increasing in the artificial intelligence field. To support the demand for artificial intelligence applications and guarantee the service level agreement, cloud computing should provide not only computing resources but also fundamental mechanisms for efficient computing. In this regard, a snapshot protocol has been used to create a consistent snapshot of the global state in cloud computing environments. However, the existing snapshot protocols are not optimized in the context of artificial intelligence applications, where large-scale iterative computation is the norm. In this paper, we present a distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments. The proposed snapshot protocol is based on a distributed algorithm to run interconnected multiple nodes in a scalable fashion. Our snapshot protocol is able to deal with artificial intelligence applications, in which a large number of computing nodes are running. We reveal that our distributed snapshot protocol guarantees the correctness, safety, and liveness conditions.

Original languageEnglish
Article number30
JournalSymmetry
Volume10
Issue number1
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

artificial intelligence
Snapshot
Cloud computing
Cloud Computing
Artificial intelligence
Artificial Intelligence
Network protocols
Computing
resources
Service Level Agreement
Resources
Liveness
Parallel algorithms
norms
Vertex of a graph
Distributed Algorithms
safety
Correctness
Safety
Norm

Keywords

  • Artificial intelligence
  • Cloud computing
  • Iterative computation
  • Snapshot protocol

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Chemistry (miscellaneous)
  • Mathematics(all)
  • Physics and Astronomy (miscellaneous)

Cite this

A distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments. / Lim, Jong Beom; Gil, Joon Min; Yu, Heonchang.

In: Symmetry, Vol. 10, No. 1, 30, 01.01.2018.

Research output: Contribution to journalArticle

@article{00d09bc4cc4740f7857cfd21413517b8,
title = "A distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments",
abstract = "Many artificial intelligence applications often require a huge amount of computing resources. As a result, cloud computing adoption rates are increasing in the artificial intelligence field. To support the demand for artificial intelligence applications and guarantee the service level agreement, cloud computing should provide not only computing resources but also fundamental mechanisms for efficient computing. In this regard, a snapshot protocol has been used to create a consistent snapshot of the global state in cloud computing environments. However, the existing snapshot protocols are not optimized in the context of artificial intelligence applications, where large-scale iterative computation is the norm. In this paper, we present a distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments. The proposed snapshot protocol is based on a distributed algorithm to run interconnected multiple nodes in a scalable fashion. Our snapshot protocol is able to deal with artificial intelligence applications, in which a large number of computing nodes are running. We reveal that our distributed snapshot protocol guarantees the correctness, safety, and liveness conditions.",
keywords = "Artificial intelligence, Cloud computing, Iterative computation, Snapshot protocol",
author = "Lim, {Jong Beom} and Gil, {Joon Min} and Heonchang Yu",
year = "2018",
month = "1",
day = "1",
doi = "10.3390/sym10010030",
language = "English",
volume = "10",
journal = "Symmetry",
issn = "2073-8994",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "1",

}

TY - JOUR

T1 - A distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments

AU - Lim, Jong Beom

AU - Gil, Joon Min

AU - Yu, Heonchang

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Many artificial intelligence applications often require a huge amount of computing resources. As a result, cloud computing adoption rates are increasing in the artificial intelligence field. To support the demand for artificial intelligence applications and guarantee the service level agreement, cloud computing should provide not only computing resources but also fundamental mechanisms for efficient computing. In this regard, a snapshot protocol has been used to create a consistent snapshot of the global state in cloud computing environments. However, the existing snapshot protocols are not optimized in the context of artificial intelligence applications, where large-scale iterative computation is the norm. In this paper, we present a distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments. The proposed snapshot protocol is based on a distributed algorithm to run interconnected multiple nodes in a scalable fashion. Our snapshot protocol is able to deal with artificial intelligence applications, in which a large number of computing nodes are running. We reveal that our distributed snapshot protocol guarantees the correctness, safety, and liveness conditions.

AB - Many artificial intelligence applications often require a huge amount of computing resources. As a result, cloud computing adoption rates are increasing in the artificial intelligence field. To support the demand for artificial intelligence applications and guarantee the service level agreement, cloud computing should provide not only computing resources but also fundamental mechanisms for efficient computing. In this regard, a snapshot protocol has been used to create a consistent snapshot of the global state in cloud computing environments. However, the existing snapshot protocols are not optimized in the context of artificial intelligence applications, where large-scale iterative computation is the norm. In this paper, we present a distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments. The proposed snapshot protocol is based on a distributed algorithm to run interconnected multiple nodes in a scalable fashion. Our snapshot protocol is able to deal with artificial intelligence applications, in which a large number of computing nodes are running. We reveal that our distributed snapshot protocol guarantees the correctness, safety, and liveness conditions.

KW - Artificial intelligence

KW - Cloud computing

KW - Iterative computation

KW - Snapshot protocol

UR - http://www.scopus.com/inward/record.url?scp=85040866450&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040866450&partnerID=8YFLogxK

U2 - 10.3390/sym10010030

DO - 10.3390/sym10010030

M3 - Article

AN - SCOPUS:85040866450

VL - 10

JO - Symmetry

JF - Symmetry

SN - 2073-8994

IS - 1

M1 - 30

ER -