Adaptive admission control of distributed cloud services

Managing the performance of virtualized web applications is a critical problem for service providers. Meeting their Service Level Objectives (SLOs), such as response time, in a dynamic environment(dense load, variable capacity), is a challenging task. In this paper, we propose an autonomous scheme for admission control in cloud services aiming at preventing overloading, guaranteeing target response time and dynamically adapting the admitted workload to compensate for changes in system capacity. We employ an adaptive feedback control scheme alongside with a queue model of the application. We show that our solution effectively delimits the response time of requests maintaining high throughput levels while it adapts to variations of system capacity.