Byungsang Kim

An Adaptive Workflow Scheduling Scheme Based on an Estimated Data Processing Rate for Next Generation Sequencing in Cloud Computing

Abstract —The cloud environment makes it possible to analyze large data sets in a scalable computing infrastructure. In the bioinformatics field, the applications are composed of the complex workflow tasks, which require huge data storage as well as a computing-intensive parallel workload. Many approaches have been introduced in distributed solutions. However, they focus on static resource provisioning with a batch-processing scheme in a local computing farm and data storage. In the case of a large-scale workflow system, it is inevitable and valuable to outsource the entire or a part of their tasks to public clouds for reducing resource costs. The problems, however, occurred at the transfer time for huge dataset as well as there being an unbalanced completion time of different problem sizes. In this paper, we propose an adaptive resource-provisioning scheme that includes run-time data distribution and collection services for hiding the data transfer time. The proposed adaptive resource-provisioning scheme optimizes the allocation ratio of computing elements to the different datasets in order to minimize the total makespan under resource constraints. We conducted the experiments with a well-known sequence alignment algorithm and the results showed that the proposed scheme is efficient for the cloud environment.

Resource Reconfiguration Scheme Based on Temporal Quorum Status Estimation for Grid Management

Quality of Service (QoS)-constrained policy has an advantage in that it satisfies QoS requirements requested by users. We propose a Quorum based resource management scheme in Grid and resource reconfiguration algorithm based on temporal execution time estimation for satisfying QoS. We compare and evaluate the processing time and deviation of the resource reconfiguration algorithm using a Heart Hemodynamics analysis.

Design of P2P grid networking architecture using k -redundancy scheme based group peer concept

Currently, there are many system requirements to guarantee the scalability, fault-tolerance, and high performance in the rapidly evolving research fields such as Grid and P2P technologies. Due to the dynamic nature of the Grid computing and P2P in networks, the behavior of system might be very unpredictable in respect of reliability. In this paper, we propose the Group Peer based P2P Grid system architecture with k-Redundancy Scheme that can satisfy these requirements. With respect to load balancing, this P2P Grid system clearly shows that redundancy scheme of group peer guarantees the reliability for resource or service discovery. Through the theoretical analysis and simulation, we discuss the performance of the proposed scheme.

SLA-Constrained Policy-Based Scheduling Mechanism in Grid

Due to the dynamic nature and uncertainty of grid computing, system rehability can become very unpreaiciaDie. inus, a well-defined scheduling mechanism that provides high system availability for grid applications is required. In this letter, we propose a SLA-constrained policy-based scheduling mechanism to enhance system performance in grid. Also, we implement the proposed model and show that our policy-based scheduling mechanism can guarantee high system availability as well as support load balancing on an experimental basis.

Resource reconfiguration scheme based on temporal Quorum status estimation in computational grids

Quality of Service (QoS)-constrained policy has an advantage to guarantee QoS requirements requested by users. Quorum systems can ensure the consistency and availability of replicated data despite the benign failure of data repositories. We propose a Quorum based resource management scheme, which includes a system resource and network resource, both of which can satisfy the requirements of application QoS. We also propose the resource reconfiguration algorithm based on temporal execution time estimation method. Resource reconfiguration performs the reshuffling of the current available resource set for maintaining the quality level of the resources. We evaluate the effectiveness of resource reconfiguration mechanism in a Heart Hemodynamics analysis. Our approach increases the stability of execution environment as well as decreases the completion time compared to the method that does not adopt the proposed reconfiguration scheme.

Tree-based replica location scheme (TRLS) for data grids

Data grids provide researching groups with data management services such as Grid-Ftp, Reliable File Transfer Service (RFP), and Replica Location Service (RLS). Especially, Replica Location Service could improve data availability by storing multiple data to the distributed location. However, there is no economic scheme to decide the location of multiple replicas. In this paper, we propose Tree-based Replica Location Scheme (TRLS) that could support users to decide optimally the location of multiple replicas as well as the number of replicas. By TRLS, we could minimize the replication cost since it supports us to find an optimal location, satisfying both storage cost and communication cost at the same time. In addition to, we could decide the number of replicas to satisfy users requirements. By minimizing cost, we make an economic decision, and we expect our proposed scheme could be regarded as a basic economic model.

A Cost-Efficient Job Scheduling Algorithm in Cloud Resource Broker with Scalable VM Allocation Scheme

Cloud service users request dedicated virtual computing resource from the cloud service provider to process jobs in independent environment from other users. To optimize this process with automated method, in this paper we proposed a framework for workflow scheduling in the cloud environment, in which the core component is the middleware called broker mediating the interaction between users and cloud service providers. To process jobs in on-demand and virtualized resources from cloud service providers, many papers propose scheduling algorithms that allocate jobs to virtual machines which are dedicated to one machine one job. With this method, the isolation of being processed jobs is guaranteed, but we can`t use each resource to its fullest computing capacity with high efficiency in resource utilization. This paper therefore proposed a cost-efficient job scheduling algorithm which maximizes the utilization of managed resources with increasing the degree of multiprogramming to reduce the number of needed virtual machines; consequently we can save the cost for processing requests. We also consider the performance degradation in proposed scheme with thrashing and context switching. By evaluating the experimental results, we have shown that the proposed scheme has better cost-performance feature compared to an existing scheme.

QoS quorum-constrained Resource management in wireless Grid

In wireless Grid computing environment, end-to-end Quality of Service (QoS) could be very complex, and this highlights the increasing requirement for the management of QoS itself. Policy quorum-based management offers a more flexible, customizable management solution that allows controlled elements to be configured or scheduled on the fly, for a specific requirement tailored for a customer. This paper presents a QoS guaranteed management scheme, Policy Quorum Resource Management (PQRM), which facilitates the reliable scheduling of the wireless Grid system with dynamic resource management architecture aimed at fulfilling the QoS requirements. Experimental results show the proposed PQRM with resource reconfiguration scheme improves both performance and stability, which is suitable for a wireless Grid services.

Application-aware contention resolution scheme for grid services over OBS networks

Recently, there are many paradigms for supporting convergence for both networks and computing. Grid computing offers high levels of computational, storage and network capacity on the wide area environment. Optic based network is a good candidate for supporting the grid application. In this paper, we proposed a novel contention resolution scheme which is differentiated by specific application and their job type for supporting grid services in the OBS network

A Performance Evaluation of the Synchronized Provisioning with an Adaptive Buffer Resilience Scheme over Grid Networks

For widely distributed data analysis applications over that run the Internet, both the instability of the data transfer time and the dynamics of data processing rate require a more sophisticated data provisioning scheme to maximize parallel efficiency, in particular, under conditions in which real-time and limited data buffer (storage) constraints are given. In this letter, we propose a synchronized data provisioning scheme that implicitly avoids the data buffer overflow as well as explicitly controls the data buffer underflow by optimally adjusting the buffer resilience. In order to guarantee the designated quality of service, we further exploit an adaptive buffer resilience control algorithm based on sample path analysis of the state of the data buffer and the demand queue. The simulation results show that the proposed scheme is suitably efficient to apply to an environment that can not postulate the stochastic characteristics of the data transfer time and data processing rate.