workflows are an application model that enables the automated execution of multiple interdependent and interconnected tasks. They are widely used by the scientific community to manage the distributed execution and dat...
详细信息
workflows are an application model that enables the automated execution of multiple interdependent and interconnected tasks. They are widely used by the scientific community to manage the distributed execution and dataflow of complex simulations and experiments. As the popularity of scientific workflows continue to rise, and their computational requirements continue to increase, the emergence and adoption of multi-tenant computing platforms that offer the execution of these workflows as a service becomes widespread. This article discusses the scheduling and resource provisioning problems particular to this type of platform. It presents a detailed taxonomy and a comprehensive survey of the current literature and identifies future directions to foster research in the field of multiple workflow scheduling in multi-tenant distributed computing systems.
Prompted by the remarkable progress in mobile communication technologies, more and more users are starting to execute their workflow applications on the mobile edge computing environment. schedulingmultiple parallel ...
详细信息
ISBN:
(纸本)9783030967727;9783030967710
Prompted by the remarkable progress in mobile communication technologies, more and more users are starting to execute their workflow applications on the mobile edge computing environment. schedulingmultiple parallel workflows on a non-dedicated edge server is a great challenge because of different users' requirements. In this paper, we propose an approach based on Deep Reinforcement Learning (DRL) to schedule multipleworkflows on an edge server with multiple heterogeneous CPUs to minimise the violation rate of service level agreement of workflows. The effectiveness of our proposed approach is evaluated by simulation experiments based on a set of real-world scientific workflows. The results show that our approach performs better than the current state-of-the-art approaches applied to similar problems.
Fog computing is an emerging popular paradigm that extends the availability of resources to the network's edge in order to improve the quality metrics of existing Cloud-based applications. However, scheduling work...
详细信息
Fog computing is an emerging popular paradigm that extends the availability of resources to the network's edge in order to improve the quality metrics of existing Cloud-based applications. However, scheduling workflow applications with time-constraints are complex regarding the count of resources, physical topology of clusters, and the structure of the task graph of the workflows. Adding Fog resources to the intricate problem space of Cloud-based scheduling needs even more time-consuming and complicated algorithms. In this paper, a multi-criteria Mamdani fuzzy algorithm is proposed to analyze the workflow graphs with the assistance of a LongShort Term Memory neural network parallelism prediction module. The group-based priority assignment schema performed by the fuzzy inference system assigns a priority value to workflows to indicate the relative precedence of requests. Distributed schedulers then send the workflows to target sites according to their current workloads. The whole process is performed in a decentralized manner to prevent any bottlenecks. We have used an extensive software simulation study to compare the proposed algorithm in real workloads with two recent and notable algorithms. The simulation results confirm the proposed algorithm's superiority in fulfilling time-constraints, resource utilization, and overall application scheduling success rate.
schedulingworkflows in cloud environments is an important issue that many types of research have been conducted in this field. However, these approaches often focus on single workflow scheduling while the need for sc...
详细信息
schedulingworkflows in cloud environments is an important issue that many types of research have been conducted in this field. However, these approaches often focus on single workflow scheduling while the need for schedulingmultipleworkflows is growing. This study aims at presenting a cloud broker for executing Deadline-constrained Periodic scientific workflows (BDPW). BDPW acts as a Workflow as a Service (WaaS) broker and uses both reserved and on-demand resources in order to minimize the monetary cost of renting resources from a cloud provider. Furthermore, BDPW uses container technology by executing multiple containerized tasks on the same Virtual Machine (VM) to decrease the provisioning delay of VMs. The proposed broker uses a hybrid scheduling method, i.e., static planning and dynamic scheduling. The static planner uses resource leveling problem (RLP) to provide a scheduling plan and also recognizes the number of reserved resources that should be leased from a provider. Then, the dynamic scheduler tries to assign tasks to the reserved resources based on the primary static plan and leases on-demand instances if necessary. Also, it may make changes to the primary plan due to uncertainties in the task runtimes. The experimental results in CloudSim show that BDPW outperforms baseline algorithms in terms of monetary cost.
The cost of using a computational resource is measured from startup to shutdown, including the cost of time slots between tasks. Concurrent scheduling of multiple scientific workflows on heterogeneous resources can im...
详细信息
The cost of using a computational resource is measured from startup to shutdown, including the cost of time slots between tasks. Concurrent scheduling of multiple scientific workflows on heterogeneous resources can improve resources utilization and reduce the cost. To make full use of waste time slots between the tasks and improve the completion rate of workflows, Expansion Slot Backfill (ESB) algorithm is proposed in this paper for schedulingmultiple deadline-constrained workflows on a fixed set of resources. All workflows are mapped to the resources with one by one strategy. Each new task tries to backfill the earliest time slot in turn. When the time slot is not enough to backfill, it can be expanded elastically by the slide of the earlier tasks. If these tasks slide cause some workflow to exceed the deadline constraint, such workflow with fewer time slots is discarded and the slide is withdrawn. Experiments with multiple parameter variations show that the algorithm get better performance in resource utilization, workflows throughput and time complexity.
In this paper, the important issue of workflow scheduling on a large-scale distributed system, to achieve the scheduling quality and the energy consumption, is addressed. Since the traditional scheduling focused on mi...
详细信息
ISBN:
(纸本)9781509020331
In this paper, the important issue of workflow scheduling on a large-scale distributed system, to achieve the scheduling quality and the energy consumption, is addressed. Since the traditional scheduling focused on minimizing the execution time and not takes the energy consumption into account, developing a scheduling for achieving both objectives has become a challenge issue. In addition, the computing resources are shared in the large-scale system, scheduling of multiple workflow application further complicate. The efficient multiple workflows scheduling with energy-aware is called EMuWS is addressed the challenge. The proposed algorithm, to efficiently determine the inefficient processors and shut them down for reducing computing resources, is adopted by the RE and cost function, which is the threshold of resource reduction. After a set of the efficient processors known, the workflow is rescheduled to assign fewer processors to attain more energy efficiency. The performance of the proposed algorithm that is obtained by exhaustive examining the synthesis workflows and real-world data outperforms our previous work, compared from reducing the energy consumption ratio.
暂无评论