Online Cost-Aware Service Requests Scheduling in Hybrid Clouds for Cloud Bursting

The hybrid cloud computing model has been attracting considerable attention in the past years. Due to security and controllability of private cloud, some special requests ask to be scheduled on private cloud, when requests are "bursting", the requests may be rejected because of the limited resources of private cloud. In this paper, we propose the online cost-aware service requests scheduling strategy in hybrid clouds (OCS) which could make suitable requests placement decisions real-time and minimize the cost of renting public cloud resources with a low rate of rejected requests. All service requests are divided into two categories, the special requests ask to be accepted on private cloud, and the normal requests are insensitive on private or public cloud. In addition, all requests arrive in random, without any prior knowledge of future arrivals. We transform the online model into a one-shot optimization problem by taking advantage of Lyapunov optimization techniques, then employ the optimal decay algorithm to solve the one-shot problem. The simulation results demonstrate that OCS is trade-off between cost and rejection rate, meanwhile it can let the resource utilization arbitrarily close to the optimum.