Title :
Dynamic Load Balancing Algorithm in Cloud
Author :
Hao Shuixia;Shen Dandan
Author_Institution :
Sch. of Math. &
Abstract :
Distributed file system is an important part of the cloud platform, a number of uncertain factors may lead the file system unbalanced, which directly affects the performance of the cloud platform. So this paper proposed a dynamic load-balance algorithm of distributed file system in the cloud platform. The algorithm obtained the local node-information by the gossip protocol, allocated file workload by the node capacity and physical position information, and gradually realized load-balancing. Compared to Distributed, Centralized load-balancing algorithms, this algorithm has better performance in moving cost, message overhead and load transform cost.
Keywords :
"Load management","Heuristic algorithms","File systems","Cloud computing","Servers","Partitioning algorithms","Indexes"
Conference_Titel :
Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom), 2015 IEEE 12th Intl Conf on
DOI :
10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.181