Research on Optimization of Resources Allocation in Cloud Computing Based on Structure Supportiveness
In this paper, we focus on the problem of resources allocation scheduling in the context of cloud computing to satisfy the objective of QoS of both cloud providers and consumers. Firstly, we give the formal modeling of cloud resources and description of t
- PDF / 378,622 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 58 Downloads / 183 Views
Research on Optimization of Resources Allocation in Cloud Computing Based on Structure Supportiveness Wei-hua Yuan, Hong Wang and Zhong-yong Fan
Abstract In this paper, we focus on the problem of resources allocation scheduling in the context of cloud computing to satisfy the objective of QoS of both cloud providers and consumers. Firstly, we give the formal modeling of cloud resources and description of their performance, as well as applications and descriptions of the component constraints; secondly, we carry out compatibility reasoning of cloud resources and application components, and build up the directed graph between them to represent their structure supportiveness to infer the relationship between scarce resources and popular components; thirdly, the weight of scarce resources and popular components are computed iteratively, and prices of services are adjusted according to their weights to achieve the best match between cloud providers and consumers; lastly the allocation algorithm is presented. Keywords Resources allocation Scarce resources
Cloud computing Structure supportiveness
W. Yuan H. Wang (&) School of Infromation Science and Engineering, ShanDong Normal University, JiNan, Shandong, China e-mail: [email protected] W. Yuan e-mail: [email protected] W. Yuan School of Computer Science and Technology, ShanDong Jianzhu University, Jian, Shandong, China Z. Fan Online Learning Center, Rizhao Radio and TV University, Rizhao Shandong, China e-mail: [email protected]
S. Li et al. (eds.), Frontier and Future Development of Information Technology in Medicine and Education, Lecture Notes in Electrical Engineering 269, DOI: 10.1007/978-94-007-7618-0_83, Springer Science+Business Media Dordrecht 2014
849
850
W. Yuan et al.
83.1 Introduction Cloud computing [1] is a kind of calculation based on Internet, which is composed of a set of interrelated and virtual computers. Computing resources can be dynamically configured through the service-level agreements (SLA) between service providers and customers [2]. Many cloud providers such as Amazon and Google, offer a kind of resource-on-demand and pay-as-you-go computing resources [1]. The following are new characteristics of cloud computing resources [3]: (1) Constraint conditions In cloud computing, cloud service providers offer paid services and users need to ‘‘pay-on-demand’’. Therefore, the cost of task execution must be considered in scheduling problems of cloud. Besides, such factors as deadline for completing tasks and user fees are also important constraints. (2) Optimization objectives Li and Yang [4] introduced that, for a given price there were a lot of variations in performance of resources offered by different cloud providers. Most of the traditional resource allocation schemes focused on QoS of cloud providers, and less consideration had been taken into that of consumers. However, in cloud computing, consumers can independently choose cloud resources according to their own needs (money or reliability). So cloud computing should also
Data Loading...
