Dynamically hierarchical resource-allocation algorithm in cloud computing environment

The development of big data challenges the computing power and communication capability of cloud architecture, but traditional resource-allocation algorithms perform poorly due to the large-scale communication among cloud nodes. In this paper, a dynamically hierarchical, resource-allocation algorith...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing 2015-07, Vol.71 (7), p.2748-2766
Main Authors: Wang, Zhanjie, Su, Xianxian
Format: Article
Language:English
Subjects:
Compilers
Computer Science
Interpreters
Processor Architectures
Programming Languages
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The development of big data challenges the computing power and communication capability of cloud architecture, but traditional resource-allocation algorithms perform poorly due to the large-scale communication among cloud nodes. In this paper, a dynamically hierarchical, resource-allocation algorithm is proposed for multiple cloud nodes collaborating in big data environment. Using fuzzy pattern recognition, the algorithm dynamically divides tasks and nodes into different levels based on computing power and storage factors. Thus a dynamically adjusted mapping is generated between tasks and nodes. When a new task arrives, only the nodes corresponding to the task level join in the bid. The algorithm takes advantages of dynamical hierarchy to reduce the communication traffic during resource allocation. Both theoretical and experimental results illustrate that the proposed algorithm outperforms the MinMin algorithm in terms of communication traffic and makespan.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-015-1416-x