Computationally intensive applications with a wide range of requirements are advancing to cloud computing platforms. However, with the growing demands from users, cloud providers are not always able to provide all the...
详细信息
Computationally intensive applications with a wide range of requirements are advancing to cloud computing platforms. However, with the growing demands from users, cloud providers are not always able to provide all the prerequisites of the application. Hence, flexible computation and storage systems, such as multi-cloud systems, emerged as a suitable solution. Different charging mechanisms, vast resource configuration, different energy consumption, and reliability are the key issues for multi-cloud systems. To address these issues, we propose a multi-workflow scheduling framework for multi-cloud systems, intending to lower the monetary cost and energy consumption while enhancing the reliability of application execution. Our proposed platform presents different methods (utilizing resource gaps, the DVFS utilized method, and a task duplication mechanism) to ensure each application's requirement. The Weibull distribution is used to model task reliability at different resource fault rates and fault behavior. Various synthetic workflow applications are used to perform simulation experiments. The results of the performance evaluation demonstrated that our proposed algorithms outperform (in the terms of resource rental cost, efficient energy consumption, and improved reliability) state-of-the-art algorithms for multi-cloud systems.
In cloud computing, multiple workflow scheduling is important to optimize resource allocation and utilization for concurrent execution of diverse workflows across different applications. While previous research has fo...
详细信息
In cloud computing, multiple workflow scheduling is important to optimize resource allocation and utilization for concurrent execution of diverse workflows across different applications. While previous research has focused on clustering-based resource allocation to reduce communication overheads by grouping tasks, it often overlooks the significance of task execution ordering, limiting overall performance optimization. To address this limitation, we propose two genetic-based approaches, considering task and cluster-level characteristics, to introduce novel ordering techniques for multi-workflow scheduling under cluster-based resource allocation. By comparing two granularity ordering methods, we offer valuable insights for efficient task management in multi-workflow environments. Our experiments demonstrate that the proposed approaches, especially the task granularity-based ordering method, outperform existing primary clustering methods, particularly for scenarios involving a large number of workflows or highly parallel workflows.
暂无评论