Kuan-Ching Li

Energy-Aware Task Consolidation Technique for Cloud Computing

Task consolidation is a way of maximizing cloud computing resource, which brings many benefits such as better use of resources, rationalization of maintenance, IT service customization, QoS and reliable services, etc. However, maximizing resource utilization does not mean efficient energy usage. Many literature show that energy consumption and resource utilization in clouds are highly coupled. Some research works aim to decrease resource utilization for saving energy while some try to find the balance between resource utilization and energy consumption. In this paper, an energy-aware task consolidation (ETC) technique is presented aims to optimize energy consumption of virtual clusters in cloud data center. Conforming most cloud systems, a 70% principle of CPU utilization is proposed to manage task consolidation among virtual clusters. The simulation results show that ETC can significantly reduce power consumption in managing task consolidation for cloud systems. Up to 17% improvement as compare to a recent work in [10] that aims to maximize resource utilization can be obtained.

Improvements on dynamic adjustment mechanism in co-allocation data grid environments

Abstract Several co-allocation strategies have been coupled and used to exploit rate differences among various client-server links and to address dynamic rate fluctuations by dividing files into multiple blocks of equal sizes. However, a major obstacle, the idle time of faster servers having to wait for the slowest server to deliver the final block, makes it important to reduce differences in finishing time among replica servers. In this paper, we propose a dynamic co-allocation scheme, namely Recursive-Adjustment Co-Allocation scheme, to improve the performance of data transfer in Data Grids. Our approach reduces the idle time spent waiting for the slowest server and decreases data transfer completion time.

Scaling up MapReduce-based Big Data Processing on Multi-GPU systems

MapReduce is a popular data-parallel processing model encompassed with recent advances in computing technology and has been widely exploited for large-scale data analysis. The high demand on MapReduce has stimulated the investigation of MapReduce implementations with different architectural models and computing paradigms, such as multi-core clusters, Clouds, Cubieboards and GPUs. Particularly, current GPU-based MapReduce approaches mainly focus on single-GPU algorithms and cannot handle large data sets, due to the limited GPU memory capacity. Based on the previous multi-GPU MapReduce version MGMR, this paper proposes an upgrade version MGMR++ to eliminate GPU memory limitation and a pipelined version, PMGMR, to handle the Big Data challenge through both CPU memory and hard disks. MGMR++ is extended from MGMR with flexible C++ templates and CPU memory utilization, while PMGMR fine-tuned the performance through the latest GPU features such as streams and Hyper-Q as well as hard disk utilization. Compared to MGMR (Jiang et al., Cluster Computing 2013), the proposed schemes achieve about 2.5-fold performance improvement, increase system scalability, and allow programmers to write straightforward MapReduce code for Big Data.

An Enhanced Parallel Loop Self-Scheduling Scheme for Cluster Environments

Approaches for dealing with scheduling and load-balancing in PC-based cluster systems are famous and well known. In such environments, Self-Scheduling Schemes are suitable for parallel loops with independent iterations. However, while schemes such as FSS, GSS, and TSS fit most computer systems, they cannot provide good load-balancing. Chao-Tung Yang and Shun-Chi Chang proposed a parallel loop scheduling scheme for heterogeneous PC cluster systems in Yang and Chang [13]. Though the proposed scheme allows users to choose parameters before execution initialization, weaknesses in it motivated us to develop further improvements. For instance, using fixed and monotonous parameters can easily lead to invalid scheduling due to use of previously input information. Thus, in this paper we propose a new scheme that fits most widely available computer systems and allows the scheduling parameter to be adjusted dynamically in order to provide higher overall performance.

A high-performance computational resource broker for grid computing environments

Internet computing and grid technologies promise to change the way we tackle complex problems. They will enable large-scale aggregation and sharing of computational, data and other resources across institutional boundaries. As grid computing is becoming a reality, there is a need for managing and monitoring the available resources worldwide, as well as the need for conveying these resources to the everyday user. This paper describes a resource broker with its main function as to match the available resources to the users needs. The use of the resource broker provides a uniform interface to access any of the available and appropriate resources using users credentials. The resource broker runs on top of the Globus toolkit. Therefore, it provides security and current information about the available resources and serves as a link to the diverse systems available in the grid.

Design and Implementation of TIGER Grid: an Integrated Metropolitan-Scale Grid Environment

Internet computing and Grid technologies promise to change the way we tackle complex problems. Harnessing these new technologies effectively, it will transform scientific disciplines ranging from highenergy physics to life sciences. This paper describes a metropolitan-scale Grid computing platform named TIGER Project (standing for Taichung Integrating Grid Environment and Resource), which basically interconnects universities and high schools’ cluster computing resources and sharing available resources among them, for investigations in system technologies and high performance applications. This novel project shows the viability of implementation of such project in a metropolitan city.

Performance analysis of applying replica selection technology for data grid environments

The Data Grid enables the sharing, selection, and connection of a wide variety of geographically distributed computational and storage resources for solving large-scale data intensive scientific applications. Such technology efficiently manage and transfer terabytes or even petabytes of data for data-intensive, high-performance computing applications in wide-area, distributed computing environments. Replica selection process allows an application to choose a replica from replica catalog, based on its performance and data access features. In this paper, we build a Grid environment based on three existing PC Cluster environments and perform performance analysis of data transfers using GridFTP protocol over these systems. In addition, based on experimental results, it is proposed a cost model to pick the best replica, in real and dynamic network situations.

A secure and scalable storage system for aggregate data in IoT

In recent years, with the impressive rapid development of integrated circuit and networking technologies, computers, devices and networking have become highly pervasive, incurring the introduction, development and deployment of the Internet of Things (IoT). The tiny identifying devices and wearables in IoT have transformed daily life in human society, as they generate, process and store the amount of data increasing at exponential rate all over the world. Due to high demand on data mining and analytics activities in IoT, secure and scalable mass storage systems are highly demanded for aggregate data in efficient processing. In this paper, we propose such a secure and scalable IoT storage system based on revised secret sharing scheme with support of scalability, flexibility and reliability at both data and system levels. Shamirs secret sharing scheme is applied to achieve data security without complex key management associated with traditional cryptographic algorithms. The original secret sharing scheme is revised to utilize all coefficients in polynomials for larger data capacity at data level. Flexible data insert and delete operations are supported. Moreover, a distributed IoT storage infrastructure is deployed to provide scalability and reliability at system level. Multiple IoT storage servers are aggregated for large storage capacity whereas individual servers can join and leave freely for flexibility at system level.?Experimental results have demonstrated the feasibility and benefits of the proposed system as well as tangible performance gains. Shamirs secret sharing is revised for multi-coefficient utilization.An internal padding scheme is proposed for flexible data management.Local storage systems are designed with secrecy and reliability at data level.IoT storage systems are deployed with scalability and reliability at system level.Major data operations are supported in distributed IoT storage environments.

A Recursively-Adjusting Co-allocation scheme with a Cyber-Transformer in Data Grids

A co-allocation architecture was developed in order to enable parallel downloads of datasets from multiple servers. Several co-allocation strategies have been coupled and used to exploit rate differences among various client-server links and to address dynamic rate fluctuations by dividing files into multiple blocks of equal sizes. However, a major obstacle, the idle time of faster servers having to wait for the slowest server to deliver the final block, makes it important to reduce differences in finish times among replica servers. In this paper, we propose Recursively-Adjusting Co-Allocation, a dynamic co-allocation scheme for improving data transfer performance in Data Grids. The experimental results show that our approach can reduce the idle time spent waiting for the slowest server and decrease data transfer completion times. We developed Cyber-Transformer, a new toolkit with a friendly GUI interface that makes it easy for inexperienced users to manage replicas and download files in Data Grid environments. We also provide an effective scheme for reducing the cost of reassembling data blocks.

An Efficient Parallel Loop Self-scheduling on Grid Environments

The approaches to deal with scheduling and load balancing on PC-based cluster systems are famous and well-known. Self-scheduling schemes, which are suitable for parallel loops with independent iterations on cluster computer system, they have been designed in the past. In this paper, we propose a new scheme that can adjust the scheduling parameter dynamically on an extremely heterogeneous PC-based cluster and grid computing environments in order to improve system performance. A grid computing environment consists of multiple PC-based clusters is constructed using Globus Toolkit and SUN Grid Engine middleware. The experimental results show that our scheduling can result in higher performance than other similar schemes.