Scheduling Hard Real-Time Tasks in Cloud Computing Using Differential Evolution Algorithm

Abstract

The cloud computing environment, in which virtual resources/machines are made available over the Internet, is a smart option for many real-time applications. However, there are a number of critical problems that need to be addressed to successfully use cloud computing for real-time applications. One of the challenges is allocation and scheduling of real time tasks on the virtual machines which is addressed in this paper. The task allocation and scheduling problem is modeled as a binary optimization problem. The differential evolution (DE) algorithm has been customized to solve the problem. A detailed experimental study has been conducted to investigate the solution quality of DE algorithm. The results show that DE performs better than the GA and the greedy algorithm.