An energy conservation replica placement strategy for Dynamo |
| |
Authors: | Junyang Yu Zhigang Hu Neal N. Xiong He Liu Zhou Zhou |
| |
Affiliation: | 1. Software School, Central South University, Changsha, Hunan, China 2. Software School, Henan University, Kaifeng, Henan, China 3. School of Computer Science, Colorado Technical University, Colorado Springs, CO, USA 4. School of Information Science and Technology, HanKou University, Wuhan, China
|
| |
Abstract: | With the fast development of cloud computing and wide application of cloud storage, the energy efficiency of cloud storage system is drawing significant attention from researchers or specialists. For the typical Dynamo cloud storage system, we design a new policy instead of the consistent hashing policy which is a combination of consistent hashing and sequential policy. The basic idea of this policy is that it divides the nodes into groups and allows each other to be mirror modes so it can find the full coverage subset of data items easily. Also we use autoregressive-moving-average model to estimate the task numbers of servers so that when under low utilization period, certain numbers of servers can be turned off to save energy. Based on the model, we demonstrate that it can save up to 23.7 % energy and maintain load balancing of servers. Furthermore, we compare our policy with Heuristic which is a classical energy conservation policy for cloud storage system that is based on consistent hash table. And we find several advantages of our policy which include finding the minimum subset of full coverage as well as other aspects. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|