An Optimal Technique for Computation-intensive Task Allocation at Virtual Machines

Currently, the world is moving towards data-driven cloud-based services for diverse applications. In such applications, the user is more willing to request space and computational resources from a virtual machine (VM) rather than investing in building more costly and space-consuming physical machines. This ever-increasing demand for VMs introduces a growing need for optimal task allocations. The goal of this study is to develop a model to allocate user requests for tasks into the least possible number of available VMs. The problem is designed as an integer linear programming (ILP) optimization problem. To solve the problem in a practical time span, a heuristic algorithm is also designed. The simulation results show that the heuristic approach achieves a near-optimal solution for task allocation and eventually leads to reduced setup and operational costs for the service providers.