Data-intensive Scientific Workflows Research Articles

Comparison of the Execution Step Strategies on Scheduling Data-intensive Workflows on IaaS Cloud Platforms

The IaaS platforms of the Cloud hold promise for executing parallel applications, particularly data-intensive scientific workflows. An important challenge for users of these platforms executing scientific workflows is to strike the right trade-off between the execution time of the scientific workflow and the cost of using the platform. In a previous article, we proposed an efficient approach that assists the user in finding this compromise. This approach requires an algorithm aimed at minimizing the execution time of the workflow once the platform configuration is set. In this article, we compare two different strategies for executing a workflow after its offline scheduling using an algorithm. The algorithm that we proposed in the previous study has outperform the HEFT algorithm.
 The first strategy allows some ready tasks to execute earlier than other higher-priority tasks that are ready later due to data transfer times. This strategy is justified by the fact that although our scheduling algorithm attempts to minimize data transfers between tasks running on different virtual machines, this algorithm does not include data transfer times in the planned execution dates for the various tasks of the workflow. The second strategy strictly adheres to the predetermined order among tasks scheduled on the same virtual machine.
 The results of our evaluations show that the best execution strategy depends on the characteristics of the workflow. For each evaluated workflow, our results demonstrate that our scheduling algorithm combined with the best execution strategy surpasses HEFT. The choice of the best strategy must be determined experimentally following realistic simulations, such as the ones we conduct here using the WRENCH framework, before conducting simulations to find the best compromise between cost and execution time of a workflow on an IaaS platform..

Optimizing data regeneration and storage with data dependency for cloud scientific workflow systems

The characters of large volume, complex dependency and frequent reuse of the data in data-intensive scientific workflow systems make the data management more and more complex but crucial. Automating the data management is an urgent need for scientific workflow systems and, requires accurate models and efficient methods for data storage and request response. This paper deals with the problems of data regeneration and storage optimization by using data dependency for cloud scientific workflow systems. Through representing the data storage strategies as 0-1 strings, a global discrete model for data storage optimization is constructed, which has a complexity of O(2n) (n is the dataset number). In terms of data regeneration, we develop a deterministic method to determine optimal regeneration strategies for requested datasets with minimal computation under any data storage strategy, such that the systems can satisfy the data requests automatically and evaluate the computation cost accurately. To solve this storage optimization problem, the enumeration method and elitist canonical genetic algorithm are constructed by shortening the representation of storage strategies to avoid redundant computation. At last, experiments are conducted to test the proposed methods. Experimental results and comparisons show the positiveness and effectiveness of the proposed methods for data management in cloud scientific workflow systems.

Multitasking bi-level evolutionary algorithm for data-intensive scientific workflows on clouds

With the deployment of workflow and other applications, cloud computing is accessible and offers assistance for optimizing workflow execution and enhancing performance. Existing research, however, tends to disregard the influence of dataset migration on workflow execution and focuses more on task execution time. This study suggests a new model for the problem of data-intensive workflow execution. Firstly, according to the structure of the workflow scheduling problem, it is divided into two sub-problems: data placement and task scheduling. The two sub-problems interact with each other and a bi-level optimum model is established. By seeking a better allocation strategy for the dataset placement and then seeking the best task-scheduling solution. Secondly, an improved multitasking bi-level evolutionary algorithm (IM-BLEA) is proposed. When dealing with the lower-level optimization problem (LLOP), offspring are selected by sorting individuals by their performance and overall performance in the population, and this environmental selection enhances the diversity and searchability of the population. Finally, compared with the other multitasking algorithm, IM-BLEA has good performance. Simulation results based on real scientific workflows show that the algorithm improves the values of transfer time and number of selected data centers by 56% and 10% compared to the comparison algorithm.

Scalable adaptive optimizations for stream-based workflows in multi-HPC-clusters and cloud infrastructures

This work presents three new adaptive optimization techniques to maximize the performance of dispel4py workflows. dispel4py is a parallel Python-based stream-oriented dataflow framework that acts as a bridge to existing parallel programming frameworks like MPI or Python multiprocessing. When a user runs a dispel4py workflow, the original framework performs a fixed workload distribution among the processes available for the run. This allocation does not take into account the features of the workflows, which can cause scalability issues, especially for data-intensive scientific workflows. Our aim, therefore, is to improve the performance of dispel4py workflows by testing different workload strategies that automatically adapt to workflows at runtime. For achieving this objective, we have implemented three new techniques, called Naive Assignment, Staging and Dynamic Scheduling. We have evaluated our proposal with several workflows from different domains and across different computing resources. The results show that our proposed techniques have significantly (up to 10X) improved the performance of the original dispel4py framework.

Replication and data management-based workflow scheduling algorithm for multi-cloud data centre platform

Scientific workflow applications have a large amount of tasks and data sets to be processed in a systematic manner. These applications benefit from cloud computing platform that offer access to virtually limitless resources provisioned elastically and on demand. Running data-intensive scientific workflow on geographically distributed data centres faces massive amount of data transfer. That affects the whole execution time and monitory cost of scientific workflows. The existing efforts on scheduling workflow concentrate on decreasing make span and budget; little concern has been paid to contemplate tasks and data sets dependency. In this paper, we introduced workflow scheduling technique to overcome data transfer and execute workflow tasks within deadline and budget constraints. The proposed techniques consist of initial data placement stage, which clusters and distributes datasets based on their dependence and replication-based partial critical path (R-PCP) technique which schedules tasks with data locality and dynamically maintains dependency matrix for the placement of generated data sets. To reduce run time datasets movement, we use interdata centre tasks replication and data sets replication to make sure data sets availability. Simulation results with four workflow applications illustrate that our strategy efficiently reduces data movement and executes all chosen workflows within user specified budget and deadline. Results reveal that R-PCP has 44.93% and 31.37% less data movement compared to random and adaptive data-aware scheduling (ADAS) techniques, respectively. R-PCP has 26.48% less energy consumption compared with ADAS technique.

A Data and Task Co-Scheduling Algorithm for Scientific Cloud Workflows

Cloud computing has emerged as a promising computational infrastructure for cost-efficient workflow execution by provisioning on-demand resources in a pay-as-you-go manner. While scientific workflows require accessing community-wide resources, they usually need to be performed in collaborative cloud environments composed of multiple datacenters. Although such environments facilitate scientific collaboration, the movements of input and intermediate datasets across geographically distributed datacenters may cause intolerable latency that would hinder efficient execution of large-scale data-intensive scientific workflows. To address the problem, in this article we propose a novel multi-level K-cut graph partitioning algorithm to minimize the volume of data transfer across datacenters while satisfying load balancing and fixed data constraints. The algorithm first contracts the fixed input datasets in the same datacenter and their consuming tasks, and coarsens the contracted graph to a predefined scale in a level-by-level manner. Then, a K-cut algorithm is used to partition the resulted graph into K parts such that the cut size is minimized. After that, the partitioned graph is projected back to the original workflow graph, during which the load balancing constraint is maintained. We evaluate our algorithm using three real-world workflow applications and the results demonstrate that the proposed algorithm outperforms other state-of-the-art algorithms.

Measuring the impact of burst buffers on data-intensive scientific workflows

Science applications frequently produce and consume large volumes of data, but delivering this data to and from compute resources can be challenging, as parallel file system performance is not keeping up with compute and memory performance. To mitigate this I/O bottleneck, some systems have deployed burst buffers, but their impact on performance for real-world scientific workflow applications is still not clear. In this paper, we examine the impact of burst buffers through the remote-shared, allocatable burst buffers on the Cori system at NERSC. By running two data-intensive workflows, a high-throughput genome analysis workflow, and a subset of the SCEC high-performance CyberShake workflow, a production seismic hazard analysis workflow, we find that using burst buffers offers read and write improvements of an order of magnitude, and these improvements lead to increased job performance, and thereby increased overall workflow performance, even for long-running CPU-bound jobs.

Integer linear programming-based multi-objective scheduling for scientific workflows in multi-cloud environments

Scientific communities are motivated to schedule the data-intensive scientific workflows in multi-cloud environments, where considerable diverse resources are provided by multiple clouds and resource limitation imposed by individual clouds is overcome. However, this scheduling involves two conflicting objectives: minimizing cost and makespan. In general, dealing with such conflicting criteria is a difficult task. But fortunately recent efficient methods for solving multi-objective optimization problems motivated us to provide a multi-objective model considering minimization of cost and makespan as objectives. For solving this model, we use different scalarization procedures such as weighted-sum, Benson's scalarization and weighted min–max under different scenarios. Moreover, we investigate the stability of obtained solutions and propose a new approach for determining the most stable solution related to weighted-sum and weighted min–max as post-optimality analysis. Results indicate that our proposed weighted-sum approach outperforms the previously developed methods in terms of hypervolume.

Data-Aware Scheduling Strategy for Scientific Workflow Applications in IaaS Cloud Computing

Scientific workflows benefit from the cloud computing paradigm, which offers access to virtual resources provisioned on pay-as-you-go and on-demand basis. Minimizing resources costs to meet user’s budget is very important in a cloud environment. Several optimization approaches have been proposed to improve the performance and the cost of data-intensive scientific Workflow Scheduling (DiSWS) in cloud computing. However, in the literature, the majority of the DiSWS approaches focused on the use of heuristic and metaheuristic as an optimization method. Furthermore, the tasks hierarchy in data-intensive scientific workflows has not been extensively explored in the current literature. Specifically, in this paper, a data-intensive scientific workflow is represented as a hierarchy, which specifies hierarchical relations between workflow tasks, and an approach for data-intensive workflow scheduling applications is proposed. In this approach, first, the datasets and workflow tasks are modeled as a conditional probability matrix (CPM). Second, several data transformation and hierarchical clustering are applied to the CPM structure to determine the minimum number of virtual machines needed for the workflow execution. In this approach, the hierarchical clustering is done with respect to the budget imposed by the user. After data transformation and hierarchical clustering, the amount of data transmitted between clusters can be reduced, which can improve cost and makespan of the workflow by optimizing the use of virtual resources and network bandwidth. The performance and cost are analyzed using an extension of Cloudsim simulation tool and compared with existing multi-objective approaches. The results demonstrate that our approach reduces resources cost with respect to the user budgets.

Extended Balanced Scheduler with Clustering and Rep- lication for Data Intensive Scientific Workflow Applications in Cloud Computing

Cloud computing is an advance computing model using which several applications, data and countless IT services are provided over the Internet. Task scheduling plays a crucial role in cloud computing systems. The issue of task scheduling can be viewed as the finding or searching an optimal mapping/assignment of set of subtasks of different tasks over the available set of resources so that we can achieve the desired goals for tasks. With the enlargement of users of cloud the tasks need to be scheduled. Cloud’s performance depends on the task scheduling algorithms used. Numerous algorithms have been submitted in the past to solve the task scheduling problem for heterogeneous network of computers. The existing research work proposes different methods for data intensive applications which are energy and deadline aware task scheduling method. As scientific workflow is combination of fine grain and coarse grain task. Every task scheduled to VM has system overhead. If multiple fine grain task are executing in scientific workflow, it increase the scheduling overhead. To overcome the scheduling overhead, multiple small tasks has been combined to large task, which decrease the scheduling overhead and improve the execution time of the workflow. Horizontal clustering has been used to cluster the fine grained task further replication technique has been combined. The proposed scheduling algorithm improves the performance metrics such as execution time and cost. Further this research can be extended with improved clustering technique and replication methods.

Combining Static and Dynamic Storage Management for Data Intensive Scientific Workflows

Workflow management systems are widely used to express and execute highly parallel applications. For data-intensive workflows, storage can be the constraining resource: The number of tasks running at once must be artificially limited to not overflow the space available in the filesystem. It is all too easy for a user to dispatch a workflow which consumes all available storage and disrupts all system users. To address these issues, we present a three-tiered approach to workflow storage management: (1) A static analysis algorithm which analyzes the storage needs of a workflow before execution, giving a realistic prediction of success or failure. (2) An online storage management algorithm which accounts for the storage needed by future tasks to avoid deadlock at runtime. (3) A task containment system which limits storage consumption of individual tasks, enabling the strong guarantees of the static analysis and dynamic management algorithms. We demonstrate the application of these techniques on three complex workflows.

Supporting Data-Intensive Workflows in Software-Defined Federated Multi-Clouds

Cloud computing is emerging as a viable platform for scientific exploration. Elastic and on-demand access to resources (and other services), the abstraction of “unlimited” resources, and attractive pricing models provide incentives for scientists to move their workflows into clouds. Generalizing these concepts beyond a single virtualized datacenter, it is possible to create federated marketplaces where different types of resources (e.g., clouds, HPC grids, supercomputers) that may be geographically distributed, are collectively exposed as a single elastic infrastructure. This presents opportunities for optimizing the execution of application workflows with heterogeneous and dynamic requirements, and tackling larger scale problems. In this paper, we introduce a framework to manage the end-to-end execution of data-intensive application workflows in dynamic software-defined resource federation. This framework enables the autonomic execution of workflows by elastically provisioning an appropriate set of resources that meet application requirements, and by adapting this set of resources at runtime as the requirements change. It also allows users to customize scheduling policies that drive the way resources federated and used. To demonstrate the benefits of our approach, we study the execution of two different data-intensive scientific workflows in a multi-cloud federation using different policies and objective functions.

Serverless execution of scientific workflows: Experiments with HyperFlow, AWS Lambda and Google Cloud Functions

Scientific workflows consisting of a high number of interdependent tasks represent an important class of complex scientific applications. Recently, a new type of serverless infrastructures has emerged, represented by such services as Google Cloud Functions and AWS Lambda, also referred to as the Function-as-a-Service model. In this paper we take a look at such serverless infrastructures, which are designed mainly for processing background tasks of Web and Internet of Things applications, or event-driven stream processing. We evaluate their applicability to more compute- and data-intensive scientific workflows and discuss possible ways to repurpose serverless architectures for execution of scientific workflows. We have developed prototype workflow executor functions using AWS Lambda and Google Cloud Functions, coupled with the HyperFlow workflow engine. These functions can run workflow tasks in AWS and Google infrastructures, and feature such capabilities as data staging to/from S3 or Google Cloud Storage and execution of custom application binaries. We have successfully deployed and executed the Montage astronomy workflow, often used as a benchmark, and we report on initial results of its performance evaluation. Our findings indicate that the simple mode of operation makes this approach easy to use, although there are costs involved in preparing portable application binaries for execution in a remote environment.While our solution is an early prototype, we find the presented approach highly promising. We also discuss possible future steps related to execution of scientific workflows in serverless infrastructures. Finally, we perform a cost analysis and discuss implications with regard to resource management for scientific applications in general.

A hybrid evolutionary algorithm for task scheduling and data assignment of data-intensive scientific workflows on clouds

A growing number of data- and compute-intensive experiments have been modeled as scientific workflows in the last decade. Meanwhile, clouds have emerged as a prominent environment to execute this type of workflows. In this scenario, the investigation of workflow scheduling strategies, aiming at reducing its execution times, became a top priority and a very popular research field. However, few work consider the problem of data file assignment when solving the task scheduling problem. Usually, a workflow is represented by a graph where nodes represent tasks and the scheduling problem consists in allocating tasks to machines to be executed at a predefined time aiming at reducing the makespan of the whole workflow. In this article, we show that the scheduling of scientific workflows can be improved when both task scheduling and the data file assignment problems are treated together. Thus, we propose a new workflow representation, where nodes of the workflow graph represent either tasks or data files, and define the Task Scheduling and Data Assignment Problem (TaSDAP), considering this new model. We formulated this problem as an integer programming problem. Moreover, a hybrid evolutionary algorithm for solving it, named HEA-TaSDAP, is also introduced. To evaluate our approach we conducted two types of experiments: theoretical and practical ones. At first, we compared HEA-TaSDAP with the solutions produced by the mathematical formulation and by other works from related literature. Then, we considered real executions in Amazon EC2 cloud using a real scientific workflow use case (SciPhy for phylogenetic analyses). In all experiments, HEA-TaSDAP outperformed the other classical approaches from the related literature, such as Min–Min and HEFT.

Data-Locality Aware Scientific Workflow Scheduling Methods in HPC Cloud Environments

Efficient data-aware methods in job scheduling, distributed storage management and data management platforms are necessary for successful execution of data-intensive applications. However, research about methods for data-intensive scientific applications are insufficient in large-scale distributed cloud and cluster computing environments and data-aware methods are becoming more complex. In this paper, we propose a Data-Locality Aware Workflow Scheduling (D-LAWS) technique and a locality-aware resource management method for data-intensive scientific workflows in HPC cloud environments. D-LAWS applies data-locality and data transfer time based on network bandwidth to scientific workflow task scheduling and balances resource utilization and parallelism of tasks at the node-level. Our method consolidates VMs and consider task parallelism by data flow during the planning of task executions of a data-intensive scientific workflow. We additionally consider more complex workflow models and data locality pertaining to the placement and transfer of data prior to task executions. We implement and validate the methods based on fairness in cloud environments. Experimental results show that, the proposed methods can improve performance and data-locality of data-intensive workflows in cloud environments.

A Survey on Data Placement Strategies for Cloud based Scientific Workflows

workflows perform computations exceeding single workstation's capabilities. When running such data intensive workflows in the cloud distributed across several physical locations, the execution time and the resource utilization efficiency highly depends on the initial placement and distribution of the input datasets across these multiple virtual machines in the Cloud. The ideal data placement scheme optimizes the execution of the data intensive scientific workflows in cloud by assigning the tasks to the execution site in such a way that the file transfers and the cost associated are reduced. Several data placement strategies in cloud based scientific workflows are reviewed. A data placement scheme which uses big data to improve the performance and also the data movement cost is studied. BDAP (Big Data Placement strategy), improves workflow performance by minimizing data movement across multiple virtual machines. Keywordscomputing, Big data, Scientific workflow, Data

SDN-aware federation of distributed data

The introduction of software defined networking (SDN) has created an opportunity for file access services to get a view of the underlying network and to further optimize large data transfers. This opportunity is still unexplored while the amount of data that needs to be transferred is growing. Data transfers are also becoming more frequent as a result of interdisciplinary collaborations and the nature of research infrastructures. To address the needs for larger and more frequent data transfers, we propose an approach which enables file access services to use SDN. We extend the file access services developed in our earlier work by including network resources in the provisioning for large data transfers. A novel SDN-aware file transfer mechanism is prototyped for improving the performance and reliability of large data transfers on research infrastructure equipped with programmable network switches. Our results show that I/O and data-intensive scientific workflows benefit from SDN-aware file access services.

Recent research advances in cloud computing and big data

Recent research advances in cloud computing and big data

Learning Running-time Prediction Models for Gene-Expression Analysis Workflows

One of the central issues for the efficient management of Scientific workflow applications is the prediction of tasks performance. This paper proposes a novel approach for constructing performance models for tasks in data-intensive scientific workflows in an autonomous way. Ensemble Machine Learning techniques are used to produce robust combined models with high predictive accuracy. Information derived from workflow systems and the characteristics and provenance of the data are exploited to guarantee the accuracy of the models. A gene-expression analysis workflow application was used as case study over homogeneous and heterogeneous computing environments. Experimental results evidence noticeable improvements while using ensemble models in comparison with single/standalone prediction models. Ensemble learning techniques made it possible to reduce the prediction error with respect to the strategies of a single-model with values ranging from 14.47 percent to 28.36 percent for the homogeneous case, and from 8.34 percent to 17.18 percent for the heterogeneous case.

A Survey of Data-Intensive Scientific Workflow Management

Nowadays, more and more computer-based scientific experiments need to handle massive amounts of data. Their data processing consists of multiple computational steps and dependencies within them. A data-intensive scientific workflow is useful for modeling such process. Since the sequential execution of data-intensive scientific workflows may take much time, Scientific Workflow Management Systems (SWfMSs) should enable the parallel execution of data-intensive scientific workflows and exploit the resources distributed in different infrastructures such as grid and cloud. This paper provides a survey of data-intensive scientific workflow management in SWfMSs and their parallelization techniques. Based on a SWfMS functional architecture, we give a comparative analysis of the existing solutions. Finally, we identify research issues for improving the execution of data-intensive scientific workflows in a multisite cloud.