A Min-Max Framework for CPU Resource Provisioning in Virtualized Servers using H∞ Filters

Dynamic resource provisioning for virtualized server applications is integral to the efficiency of computing paradigms such as green and cloud computing. In these environments unpredicted workload changes occur frequently and controlbased resource adaptation should respond to them in a timely fashion while minimizing the expected loss during workload transitions. Our approach is to minimize the maximum expected loss using the same techniques as in two-person zero-sum games. We develop an H∞ filter that minimizes the worst-case estimation and allocate resources fast. Through simulations our H∞ filter demonstrates its effectiveness and good performance when compared against Kalman-based controllers.