Natural and environmental sciences are one of the scientific domains which seek a lot of attention as it requires high performance computation and large storage space. Cloud computing is such a platform that offers a customizable infrastructure where scientific applications can provision the required resources prior to execution. The elasticity characteristic of cloud computing and it’s pay-as-you-go pricing model can reduce the resource usage cost for cloud client’s. The various services offered by the cloud providers and the extravagant developments in the domain of cloud computing has attracted many scientists to deploy their applications on cloud. The change in number of tasks of scientific application directly affects the demand of cloud resources. Therefore, to handle the fluctuating demand of resources, there is a need to manage the resources in an efficient manner. This research work focuses on the design of a prediction based scheduling approach which maps the tasks of scientific application with the optimal VM by combining the features of swarm intelligence and multi-criteria decision making approach. The proposed approach improves the accuracy rate, minimizes the execution time, cost and service level agreement violation rate in comparison to existing scheduling heuristics.

由于自然科学和环境科学需要高性能的计算和较大的存储空间，因此是引起人们广泛关注的科学领域之一。云计算就是这样一种平台，它提供了可定制的基础架构，科学应用程序可以在其中执行之前配置所需的资源。云计算的弹性特性及其按需付费的定价模型可以减少云客户端的资源使用成本。云提供商所提供的各种服务以及云计算领域的飞速发展吸引了许多科学家将他们的应用程序部署在云上。科学应用任务数量的变化直接影响云资源的需求。因此，为了应对不断变化的资源需求，需要以有效的方式来管理资源。这项研究工作集中在基于预测的调度方法的设计上，该方法结合了群体智能和多准则决策方法的特征，将科学应用的任务映射到最佳VM。与现有的调度试探法相比，所提出的方法提高了准确率，最小化了执行时间，成本和服务水平协议违反率。