A SURVEY AND ANALYSIS OF METAHEURISTIC BASED TASK SCHEDULING ALGORITHMS IN CLOUD COMPUTING ENVIRONMENT

Abstract

Cloud service providers wants to schedule as many user applications as possible on each
resource to maximize the utilization of resources, while the consumers wish to have their
requests served at minimal cost. Since Cloud Computing is an economic setting, cloud service
providers and consumers tries to increase their income and return on investment (ROI) by
optimal resource. Efficient scheduling of resources becomes central to meeting Service Level
Agreements (SLAs) in delivering effective cloud services. When the resource provisioning is
overestimated, it leads to under-utilization of resources and loss of revenue. Due to the practical
applications and challenges of executing large scale applications, task scheduling of applications
on the large scale have become an emerging research in cloud computing and have attracted
significant attention of researchers in recent times. Moreover, various heuristics have been
applied to solve task scheduling problems which generate optimal solutions for small size
problems. However, the quality of solutions produced by these techniques degrades woefully as
the problem size and number of variables to be optimized increases. Also, these heuristic
methods do not have provisions and support for meeting various Quality of Service (QoS)
requirements like response time, makespan time, reliability, availability, energy consumption,
cost, resource utilization. In contrast, many cloud users requires certain QoS satisfaction
especially for scientific and business domain applications. In recent times, attempts have been
made to address task scheduling problems using metaheuristic algorithms to address this problem.
Using metaheuristic algorithms for solving task scheduling problems in cloud have shown
promising improvements in achieving efficiency, by reducing the solution search space. This
paper provides the analysis of metaheuristic algorithms, which we hope to be of great interest to
the upcoming researchers in the field of optimizing cloud service resource provisioning.