Search

With the wide deployment of cloud computing in scientific computing, cost minimization is increasingly critical for large-scale scientific workflow. Unfortunately, due to the highly intricate directed acyclic graph (DAG)-based workflow and the flexible usage of virtual machines (VMs) in cloud platform, the existing workflow scheduling approaches are inefficient to strike a balance between the parallelism and the topology of the DAG-based workflow while using the VMs, which causes a low utilization of VMs and consumes more cost. To address these issues, this paper presents a novel task scheduling framework named cost minimization approach with the DAG splitting method (COMSE) for minimizing the cost of running a deadline-constrained large-scale scientific workflow. First, we provide comprehensive theoretical analyses on how to improve the utilization of a resource-balanced multi-vCPU VM for running multiple tasks simultaneously. Second, considering the balance between the parallelism and the topology of a workflow, we simplify the DAG-based workflow, and based on the simplified DAG, a DAG splitting method is devised to preprocess the workflow. Third, since the cloud is charged by hours, we also design an exact algorithm to find the optimal operation pattern for a given schedule to make the consumed instance hours minimum, and this algorithm is named as instance hours minimization by Dijkstra (TOID). Finally, by employing the DAG splitting method and the TOID, the COMSE schedules a deadline-constrained large-scale scientific workflow on the multi-vCPU VMs and incorporates two important objects: minimizing the computation cost and the communication cost. Our solution approach is evaluated through rigorous performance evaluation study using real-word workflows, and the results show that the proposed COMSE approach outperforms existing algorithms in terms of computation cost and communication cost. [ABSTRACT FROM AUTHOR]

Cloud computing is recently getting increasingly popular for supporting scientific applications and complex business processes. Clouds are highly potent for executing workflow-based tasks due to the fact that they provide elastic resource provisioning styles through which computational-intensive workflows can obtain requested resources according to their elastic demand and establish execution environment over virtual machines (VMs). However, it remains a challenge to guarantee cost-effectiveness and quality of service of workflow deployed upon clouds due to the fact that real-world cloud infrastructures are usually with fluctuating and time-varying performance. Existing researches mainly consider that cloud infrastructures are with fixed, random, or bounded quality of service (QoS). In this work, however, we consider that scientific computing processes to be supported by decentralized cloud infrastructures with fluctuating QoS and aim at managing the monetary cost of workflows with the completion-time constraint to be satisfied. We address the performance-variation-aware workflow scheduling problem by leveraging a time-series-based prediction model and a Critical-Path-Duration-Estimation-based (CPDE for short) VM Selection strategy. The proposed method is capable of exploiting real-time trends of performance changes of cloud infrastructures and generating dynamic workflow scheduling plans. To prove the effectiveness of our proposed method, we perform extensive experimental case analysis over real-world third-party commercial clouds and show that our method clearly beats existing approaches. [ABSTRACT FROM AUTHOR]

Frost is an agro-meteorological event which causes both damage in crops and important economic losses, therefore frost prediction applications (FPA) are very important to help farmers to mitigate possible damages. FPA involves the execution of many CPU-intensive jobs. This work focuses on efficiently running FPAs in paid federated Clouds, where custom virtual machines (VM) are launched in appropriate resources belonging to different providers. The goal of this work is to minimize both the makespan and monetary cost. We follow a federated Cloud model where scheduling is performed at three levels. First, at the broker level, a datacenter is selected taking into account certain criteria established by the user, such as lower costs or lower latencies. Second, at the infrastructure level, a specialized scheduler is responsible for mapping VMs to datacenter hosts. Finally, at the VM level, jobs are assigned for execution into the preallocated VMs. Our proposal mainly contributes to implementing bio-inspired strategies at two levels. Specifically, two broker-level schedulers based on Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO), which aim to select the datacenters taking into account the network latencies, monetary cost and the availability of computational resources in datacenters, are implemented. Then, VMs are allocated in the physical machines of that datacenter by another intra-datacenter scheduler also based on ACO and PSO. Performed experiments show that our bio-inspired scheduler succeed in reducing both the makespan and the monetary cost with average gains of around 50% compared to genetic algorithms. [ABSTRACT FROM AUTHOR]