A Distributed Snapshot Protocol for Efficient Artificial Intelligence Computation in Cloud Computing Environments

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, clo...

Full description

Saved in:
Bibliographic Details
Published in:Symmetry (Basel) Vol. 10; no. 1; p. 30
Main Authors: Lim, JongBeom, Gil, Joon-Min, Yu, HeonChang
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.01.2018
Subjects:
ISSN:2073-8994, 2073-8994
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2073-8994
2073-8994
DOI:10.3390/sym10010030