A biobjective model for resource provisioning in multi-cloud environments with capacity constraints

Abstract Private and public clouds are good means for getting on-demand intensive computing resources. In such a context, selecting the most appropriate virtual machines (VMs) is complex task. From user’s point of view, challenge consists in efficiently managing cloud resources while integrating prices performance criteria. This paper focuses on problem VMs to run bags-of-tasks (BoT): big sets identical independent tasks. More precisely, we define new mathematical optimization models deal with time use each jointly integrate execution makespan cost into objective function through bi-objective problem. order provide trade-off solutions problem, propose lexicographic approach. addition, introduce, two different ways, capacity constraints or bounds number available clouds. A global limit resource at period can be defined. Computational experiments performed synthetic dataset. Sensitivity analysis highlights effect limits minimum makespan, deadline total operation cost, impact considering instantaneous instead between makespan.