Cloud infrastructures are designed to simultaneously service many, diverse applications that consist of collections of Virtual Machines (VMs). The placement policy used to map applications onto physical servers has important effects in terms of application performance and resource efficiency. We propose enhancing placement policies with network-aware optimizations, trying to simultaneously improve application performance, resource efficiency and power efficiency. The per-application placement decision is formulated as a bi-objective optimization problem (minimizing communication cost and the number of physical servers on which an application runs) whose solution is searched using evolutionary techniques. We have tested three multi-objective optimization algorithms with problem-specific crossover and mutation operators. Simulation-based experiments demonstrate how, in comparison with classic placement techniques, a low-cost optimization results in improved assignments of resources, making applications run faster and reducing the energy consumed by the data center. This is beneficial for both cloud clients and cloud providers.

This work has been partially supported by the Saiotek and Research Groups 2013-2018 (IT-609-13) programs (Basque Government), TIN2010-14931 and COM-BIOMED network in computational biomedicine (Carlos III Health Institute). Dr. Pascual is supported by a postdoctoral grant of the UPV/EHU. Mrs Lorido-Botran is supported by a doctoral grant from the Basque Government. Prof. Miguel-Alonso is a member of the HiPEAC European Network of Excellence.