• KIISE Transactions on Computing Practices
• /
• v.22 no.6
• /
• pp.296-301
• /
• 2016

Object-based storage is an efficient storage solution that can handle unstructured data and shows better security and scalability than traditional block-based storage. However, in terms of power management, Object-based storage writes multiple copies in storage cluster, hence many servers consume unnecessary power in idle state. In order to resolve this problem, it is necessary to apply power management strategy by adjusting power mode of servers in idle state according to their workloads. In this paper, we proposed a new dynamic power management (DPM) method to transform power mode of storage servers dynamically according to workload information sent from proxy server. The experimental result shows that the proposed power management technic reduces total power consumption by 12% in the OpenStack based Swift object storage.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.4
• /
• pp.247-258
• /
• 2009

Distributed file systems running on a cluster of inexpensive commodity hardware are being recognized as an effective solution to support the explosive growth of storage demand in large-scale Internet service companies. This paper presents the design and implementation of BeanFS, a distributed file system for large-scale e-mail services. BeanFS is adapted to e-mail services as follows. First, the volume-based replication scheme alleviates the metadata management overhead of the central metadata server in dealing with a very large number of small files. Second, BeanFS employs a light-weighted consistency maintenance protocol tailored to simple access patterns of e-mail message. Third, transient and permanent failures are treated separately and recovering from transient failures is done quickly and has less overhead.

• KIISE Transactions on Computing Practices
• /
• v.21 no.10
• /
• pp.651-657
• /
• 2015

The amount of web traffic has increased as a result of the rapid growth of the use of web-based applications. In order to obtain valuable information from web logs, we need to develop systems that can support interactive, flexible, and efficient ways to analyze and handle large amounts of data. In this paper, we present CERES, a log-based, interactive web analytics system for backbone networks. Since CERES focuses on analyzing web log records generated from backbone networks, it is possible to perform a web analysis from the perspective of a network. CERES is designed for deployment in a server cluster using the Hadoop Distributed File System (HDFS) as the underlying storage. We transform and store web log records from backbone networks into relations and then allow users to use a SQL-like language to analyze web log records in a flexible and interactive manner. In particular, we use the data cube technique to enable the efficient statistical analysis of web log. The system provides users a web-based, multi-modal user interface.

• The KIPS Transactions:PartC
• /
• v.12C no.2 s.98
• /
• pp.157-168
• /
• 2005

Group key agreement protocols are designed to provide a group of parties securely communicating over a public network with a session key. The mobile computing architecture is asymmetric in the sense of computational capabilities of participants. That is, the protocol participants consist of the stationary server(application servers) with sufficient computational Power and a cluster of mobile devices(clients) with limited computational resources. It is desirable to minimize the amount of computation performed by each group member in a group involving low-power mobile devices such as smart cards or personal digital assistants(PDAs). Furthermore we are required to update the group key with low computational costs when the members need to be excluded from the group or multiple new members need to be brought into an existing group. In this paper, we propose a dynamic group key protocol which offers computational efficiency to the clients with low-power mobile devices. We compare the total communicative and computational costs of our protocol with others and prove its suity against a passive adversary in the random oracle model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.91-97
• /
• 2021

A microserver is a type of a computing server, in which two or more CPU nodes are implemented on a separate computing board, and a plurality of computing boards are integrated on a main board. In building a cluster system, the microserver has advantages in several points such as energy efficiency, area occupied, and ease of management compared to the existing method of mounting legacy servers in multiple racks. In addition, since the microserver uses a fast interconnection network between CPU nodes, performance improvement for data transfers is expected. The proposed microserver can mount a total of 16 computing boards with 4 CPU nodes on the main board, and uses Serial-RapidIO (SRIO) as an interconnection network. In order to analyze the performance of the proposed microserver in terms of the interconnection network which is a core performance issue of the microserver, we compare and quantify the performance of commercial microservers. As a result of the test, it showed up to about 7 times higher bandwidth improvement when transmitting data using the interconnection network. In addition, with CloudSuite benchmark programs used in actual cloud computing, maximum 60% reduction in execution time was obtained compared to commercial microservers with similar CPU performance specification.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.316-318
• /
• 2019

Recently, healthy life has become an issue in an aging society, and the number of people who have been interested in continuous health care for better life is increasing. In this paper, we implemented a personalized recommendation systm to provide convenient healthcare management for user. The PHR (Personal Health Record) of user could be stored in the server along with health related information such as lifestyle, disease, and physical condition. The users could be classified into similar clusters according to the PHR profile in order to provide healthcare contents to the users who had similar PHR profile. K-Means clustering was applied to generate clusters based on PHR profile and ACDT(Ant Colony Decision Tree) algorithm was used to provide personalised recommendation of health information stored in knowledge base. The app system developed in this paper is useful for users to perform healthcare themselves by providing information on serious diseases and lifestyle habits to be improved according to the clusters classified by PHR profile.

• Database Research
• /
• v.34 no.3
• /
• pp.58-68
• /
• 2018

Distributed computing helps to efficiently store and process large data on a cluster of multiple machines. The performance of distributed computing is greatly influenced depending on the state of the servers constituting the distributed system. In this paper, we propose a self-diagnosis system that collects log data in a distributed system, detects anomalies and visualizes the results in real time. First, we divide the self-diagnosis process into five stages: collecting, delivering, analyzing, storing, and visualizing stages. Next, we design a real-time self-diagnosis system that meets the goals of real-time, scalability, and high availability. The proposed system is based on Apache Flume, Apache Kafka, and Apache Storm, which are representative real-time distributed techniques. In addition, we use simple but effective moving average and 3-sigma based anomaly detection technique to minimize the delay of log data processing during the self-diagnosis process. Through the results of this paper, we can construct a distributed real-time self-diagnosis solution that can diagnose server status in real time in a complicated distributed system.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.10
• /
• pp.231-238
• /
• 2019

Analyzing next-generation genome sequencing data in a conventional way using single server may take several tens of hours depending on the data size. However, in order to cope with emergency situations where the results need to be known within a few hours, it is required to improve the performance of a single genome analysis. In this paper, we propose a parallelized method for pre-processing genome sequence data which can reduce the analysis time by utilizing the big data technology and the highperformance computing cluster which is connected to the high-speed network and shares the parallel file system. For the reliability of analytical data, we have chosen a strategy to parallelize the existing analytical tools and algorithms to the new environment. Parallelized processing, data distribution, and parallel merging techniques have been developed and performance improvements have been confirmed through experiments.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.81-90
• /
• 2013

During the past decade, many changes and attempts have been tried and are continued developing new technologies in the computing area. The brick wall in computing area, especially power wall, changes computing paradigm from computing hardwares including processor and system architecture to programming environment and application usage. The high performance computing (HPC) area, especially, has been experienced catastrophic changes, and it is now considered as a key to the national competitiveness. In the late 2000's, many leading countries rushed to develop Exascale supercomputing systems, and as a results tens of PetaFLOPS system are prevalent now. In Korea, ICT is well developed and Korea is considered as a one of leading countries in the world, but not for supercomputing area. In this paper, we describe architecture design of MAHA supercomputing system which is aimed to develop 300 TeraFLOPS system for bio-informatics applications like human genome analysis and protein-protein docking. MAHA supercomputing system is consists of four major parts - computing hardware, file system, system software and bio-applications. MAHA supercomputing system is designed to utilize heterogeneous computing accelerators (co-processors like GPGPUs and MICs) to get more performance/$, performance/area, and performance/power. To provide high speed data movement and large capacity, MAHA file system is designed to have asymmetric cluster architecture, and consists of metadata server, data server, and client file system on top of SSD and MAID storage servers. MAHA system softwares are designed to provide user-friendliness and easy-to-use based on integrated system management component - like Bio Workflow management, Integrated Cluster management and Heterogeneous Resource management. MAHA supercomputing system was first installed in Dec., 2011. The theoretical performance of MAHA system was 50 TeraFLOPS and measured performance of 30.3 TeraFLOPS with 32 computing nodes. MAHA system will be upgraded to have 100 TeraFLOPS performance at Jan., 2013.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.65-73
• /
• 2016

Peer-to-Peer (P2P) systems with super-peer overlay networks show combined advantages of both hybrid and pure P2P systems. Super-peer is a special peer acting as a server to a cluster of generic peers. Organizing a super-peer network is one of important issues for P2P systems with super-peer networks. Conventional P2P systems are based on two-level hierarchies of peers. One is a layer for generic peers and the other is for super-peers. And it is usual that super-peer networks have forms of random graphs. However, for accommodating a large-scale collection of generic peers, the super-peer network has also to be extended. In this paper, we propose a scheme of hierarchically constructing super-peer networks for large-scale P2P systems. At first, a two-level tree, called a simple super-peer network, is proposed, and then a scheme of generalizing and then extending the simple super-peer network to multi-level super-peer network is presented to construct a large-scale super-peer network. We call it an extended super-peer network. The simple super-peer network has several good features, but due to the fixed number of levels, it may have a scalability problem. Thus, it is extended to k-level tree of a super-peer network, called extended super-peer network. It shows good scalability and easy management of generic peers for large scale P2P system.