Energy and Security Awareness in Evolutionary-Driven Grid Scheduling

Abstract

Ensuring the energy efficiency, thermal safety, and security-awareness in today’s large-scale distributed computing systems is one of the key research issues that leads to the improvement of the system scalability and requires researchers to harness an understanding of the interactions between the system external users and the internal service and resource providers. Modeling these interactions can be computationally challenging especially in the infrastructures with different local access and management policies such as computational grids and clouds. In this chapter, we approach the independent batch scheduling in Computational Grid (CG) as a three-objective minimization problem with Makespan, Flowtime and energy consumption in risky and security scenarios. Each physical resource in the system is equipped with Dynamic Voltage Scaling (DVS) module for optimizing the cumulative power energy utilized by the system. The effectiveness of six genetic-based single- and multi-population grid schedulers has been justified in comprehensive empirical analysis.