A New Linear Model for Placement of Virtual Machines across Geo-Separated Data Centers

Cloud computing has recently emerged as a new technology for hosting and supplying services over the Internet. With an increasing demand for cloud computing, providing performance guarantees for applications that run over cloud become important. Applications can be abstracted into a set of virtual machines with certain guarantees depicting the quality of service of the application. In this paper, we consider the placement of these virtual machines across multiple data centers, meeting the quality of service requirements while minimizing the bandwidth cost of the data centers. This problem is a generalization of the NP-hard Generalized Quadratic Assignment Problem (GQAP). We present a new linear mathematical model, extending a formulation for GQAP from the literature and include a set of additional cuts. Experimental results show that the cuts improve significantly the quality of lower bounds and help CPLEX to reduce the running time to find good quality solutions.