A Hierarchical Control Framework of Load Balancing and Resource Allocation of Cloud Computing Services
Abstract
Service providers must guarantee the quality of service (QoS) requirements of the co-hosted applications in a data center and at the same time achieve optimal use of their infrastructure under varying workload. This A hierarchical control framework of load balancing and resource allocation of cloud computing services paper presents a hierarchical control framework aimed at compromising antagonistic goals within a data center
A hierarchical control framework of load balancing and resource allocation of cloud computing services The local control level tackles the resource allocation and admission control problems of virtual machines simultaneously, while the upper level tackles the load balancing of incoming requests and placing virtual machines in a cluster of physical servers together. Numerical results show that the cooperation of the two control layers ensures the satisfaction of the system’s constraints and the user’s requirements towards the fluctuations of incoming requests.
System Configuration
Conclusion
A consolidated application hierarchical management framework was proposed in a single cloud data center. At the lower level, a local controller for each virtual machine addresses resource allocation issues in terms of CPU share, and admission control of incoming requests. More specifically, the dynamic operation of virtual machines was described by fuzzy Takagi–Sugeno modeling and a set of feasible operating points were calculated to maximize the admitted requests.
