Online Cost-rejection Rate Scheduling for Resource Requests in Hybrid Clouds
Published in Parallel Computing, 2018
Recommended citation: Yanhua Cao, Li Lu, Jiadi Yu, Shiyou Qian, Yanmin Zhu, Minglu Li. "Online Cost-rejection Rate Scheduling for Resource Requests in Hybrid Clouds." Parallel Computing. 81(1). pp. 85-103. 2018. doi: 10.1016/j.parco.2018.12.003.
PARCOM is a CCF-B journal.
Abstract: The hybrid cloud computing model has attracted considerable attention in recent years. Due to security and controllability of private cloud, some resource requests are required to be scheduled in private parts of hybrid cloud. However, these requests could be rejected because of the resource limitation of private parts of hybrid cloud. In this paper, all resource requests are classified into two categories, i.e., the special requests required to process in private cloud, and the normal requests insensitive in private or public clouds. By considering the normal requests undivided to dispatch a cloud and divided to dispatch different clouds, we propose the online cost-rejection rate scheduling strategy (OCS) for the normal requests undivided, and the online scheduling strategy for some normal requests divided (OCS-divided), which could make suitable requests placement decisions in real-time and minimize the cost of renting public cloud resources with a low rate of rejected requests.