International Conference on Mechanical Engineering and Technology (ICMET-London 2011)
108 Task Scheduling Strategy Based on Tree Network in Cloud Computing Environment
Download citation file:
- Ris (Zotero)
- Reference Manager
The task scheduling strategy has a great impact on system performance in cloud computing environment. In traditional distributed computation such as grid computing, scheduling algorithms for tree network were always based on single-port mode. However, single-port mode is not appropriate for cloud computing environment, because that in cloud environment, the participants of the cluster can do multiple tasks simultaneously. In recent years, some scholars have done a lot of researches of task scheduling in cloud computing environment. However, these researches, in terms of network topologies, were almost based on opaque cloud. When the participants of the cluster were organized into a tree structure, appropriate task scheduling strategy tailored to the situation of multitasking is still lacked. This paper focused on the feature of cloud computing environment, proposed a new framework of task scheduling strategy for tree network. This framework is based on master-slave model, it breaks the limitation of single-port mode. It is fit for the cloud environment, in which the host performance and network capacity are uncertain. This paper provided an available solution of the problem of task scheduling in tree network. It discussed about task scheduling strategy for tree depth of two, tree depth greater than two respectively. In addition, it proposed two algorithms for tree depth greater than two; finally, from three aspects: the rationality of target node selection, network overhead, time consumption of calculate, it compared these two algorithms.