An inter-cloud outsourcing model to scale performance, availability and security

This paper presents a model of a horizontal cloud federation and studies the optimal resource selection and allocation policy a service provider should put in place to scale the performance, availability and security guarantees offered to customers. The proposed model considers: (i) resources located in different zones, characterized by different hourly costs and specific performance, availability, and security properties; (ii) service provider customers, dispersed in various zones (characterized by different latencies), and demanding services with different QoS levels defined in Service Level Agreements (SLAs). From this model we define an optimization problem allowing to determine the optimal distribution of the incoming load and the proper allocation of outsourced resources that satisfies the SLAs and that minimizes the outsourcing costs, thus allowing the maximization of the SP revenue. Experiments show how the optimal policy scales the service provider capabilities when the workload grows 10 times and more.