Energy-aware workflow scheduling and optimization in clouds using bat algorithm

Abstract

With the ever-increasing deployment of data centers and computer networks around the world, cloud computing has emerged as one of the most important paradigms for large-scale data-intensive applications. However, these cloud environments face many challenges including energy consumption, execution time, heat and CO2 emission, as well as operational cost. Due to the extremely large scale of these applications and a huge amount of resource consumption, even a small portion of the improvements in any of the above fields can yield huge ecological and financial rewards. Efficient and effective workflow scheduling in cloud environments is one of the most significant ways to confront the above problems and achieve optimal resource utilization. We propose an Energy Aware, Time, and Throughput Optimization heuristic (EATTO) based on the bat algorithm. Our goal is to minimize energy consumption and execution time of computation-intensive workflows while maximizing throughput, without imposing any significant loss on the Quality of Service (QoS) guarantee.