A Load Balancing Approach to Resource Provisioning in Cloud Infrastructure with a Grouping Genetic Algorithm

In Infrastructure-As-A-Service Computational Cloud, a set of resources is leased out depending upon the requirements. A resource provisioning algorithm carries out this task by considering some overall objectives of the system under consideration. The algorithm takes the specifications of the Virtual Machines required and the characteristics of the Physical Machines present in the Data Centers as input and produces an assignment of the Virtual Machines to the Physical Machines as output while considering the objective function. We design a Genetic Algorithm-based resource provisioning strategy which attempts to distribute the requests uniformly among the available Physical Machines so as to keep the load on the machines as uniform as possible.