• 대한공업교육학회지
• /
• v.32 no.2
• /
• pp.199-216
• /
• 2007

Stream Control Transmission Protocol(SCTP) is a transport layer protocol to support the data transmission. SCTP is similar to Transmission Control Protocol(TCP) in a variety of aspects. However, several features of SCTP including multi-homing and multi-streaming incur the performance difference from TCP. This paper highlights the data transfer during the initial slow start phase in SCTP congestion control composed of slow start phase and congestion avoidance phase. In order to compare the mean transfer time between SCTP and TCP, we experiment with different performance parameters including bandwidth, round trip time, and data length. By varying data length, we also measure the corresponding initial window size, which is one of factors affecting the mean transfer time. For the experiment, we have written server and client applications by C language using SCTP socket API and have measured the transfer time by ethereal program. We transferred data between client and server using round-robin method. Analysis of these experimental results from the testbed implementation shows that larger initial window size of SCTP than that of TCP brings the reduction in the mean transfer time of SCTP compared with TCP by 15 % on average during the initial slow start phase.

• Journal of KIISE:Information Networking
• /
• v.35 no.4
• /
• pp.268-281
• /
• 2008

It is difficult to construct streaming services based on the overlay networks without any loss of scalability. DONet is one of the most representative streaming overlay network protocols without managing any specific structure. Since DONet does not support the nodes on private networks, it can be considered that the performance of the overlay is not the best. Hole Punching is one of the famous techniques participating the nodes on private networks to streaming overlay networks by using a rendezvous server. However, using only a single rendezvous server cannot be suggested in P2P environment, because it can cause problems in terms of scalability and so on. In this paper, we propose DONet-p, an extension of DONet with Distributed Hole Punching techniques. It supports the nodes on private networks without toss of scalability. The experimental results show the better performance and scalability than DONet with a minimum overhead for additional control messages.

• Journal of KIISE
• /
• v.44 no.10
• /
• pp.1005-1018
• /
• 2017

Recently, virtualization has become an essential component of cloud computing due to its various strengths, including maximizing server resource utilization, easy-to-maintain software, and enhanced data protection. However, since virtualization allows sharing physical resources among the VMs, the system performance can be deteriorated due to device contentions. In this paper, we first investigate the I/O overhead based on the number of VMs on the same server platform and analyze the block I/O process of the KVM hypervisor. We also propose an in-memory block cache mechanism, called QBic, to overcome I/O virtualization latency. QBic is capable of monitoring the block I/O process of the hypervisor and stores the data with a high access frequency in the cache. As a result, QBic provides a fast response for VMs and reduces the I/O contention to physical devices. Finally, we present a performance measurement of QBic to verify its effectiveness.

• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.639-646
• /
• 2003

Conventional two-tier databases have shown performance limitation in the presence of many concurrent clients. To this end, the three-tier architecture that exploits similarities in client's object access behavior has been proposed. In this system, clients are partitioned into clusters, and object requests can be then served in inter-cluster manner. Introducing an intermediate layer between server(s) and clients enables this. In this paper, we introduce the problem of client realignment in which access behavior changes, and propose on-line client clustering. This system facilitates adaptive reconfiguration and redistribution of sites. The core issue in this paper is to demonstrate the effectiveness of on-line client clustering. We experimentally investigate the performance of the scheme and necessary costs.

• Journal of Korea Multimedia Society
• /
• v.11 no.10
• /
• pp.1338-1346
• /
• 2008

In this paper, we propose a new P2P-based music recommendation system. In comparison with previous system in client-server environment, the proposed system shows higher quality of music recommendation through real-time sharing of music preference information between peers. A collaborative filtering is implemented as a recommendation algorithm. As a user preference profile, we use the inherit KID music genre index contained in all legitimate music file instead of music feature vectors as in previous research so that the proposed system can mitigate the performance degradation and high computational load caused by feature inaccuracy and feature extraction. The performance of the proposed system is evaluated in various ways with real 16-weeks transaction data provided by Korean music portal, 5 company and it shows comparative quality of recommendation with only small amount of computational load.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.12
• /
• pp.3088-3096
• /
• 1997

In this paper, we present WWW system over native ATM services. The use of native ATM services through ATM API can provide better performance and functionality than that of IP over ATM, LAN Emulation or Multiprotocol over ATM. Our WWW browser and server provide advanced WWW services based on enhanced performance and guaranteed QoS support by using native ATM service benefits. This paper describes and compares advantages and disadvantages of Native ATM Services and ATM Internet Services, and addresses ATM API standardization and development trend that are made by the ATNI Forum for the support of native ATM services, and then describes the architecture and operation of our WWW browser and server using ATM API. The system architecture is based on HTTP over ATM API capable of supporting guaranteed QoS over its connections. The system defines and uses new HTML attributes within hyperlinking HTML elements for the description of ATM QoS and traffic characteristics that are derived from UNI signaling 3.1 connection characteristics information elements. Our system uses WinSock 2 API as its ATM API.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.8
• /
• pp.1818-1824
• /
• 2015

Cloud computing draws attention as an application to provide dynamically scalable infrastructure for application, data and file storage. An untrusted remote server can cause a variety of problems in the field of data protection. It may process intentionally or involuntarily user's data operations(modify, insert, delete) without user's permission. It may provide false information in order to hide his mistakes in the auditing process. Therefore, it is necessary to audit the integrity of data stored in the cloud server. In this paper, we propose a new data auditing system that can verify whether servers had a malicious behavior or not. Performance and security analysis have proven that our scheme is suitable for cloud computing environments in terms of performance and security aspects.

• The KIPS Transactions:PartA
• /
• v.13A no.5 s.102
• /
• pp.435-444
• /
• 2006

Recently, various applications of location trigger service have been required and developed as users of location-based services are increasing. The location trigger is detecting event of entering in, existing in or leaving from pre-specified area, and then alerting by short message service, an e-mall or servicing other pre-defined action to mobile subscribers. The conventional methodology of supporting location trigger is detecting location trigger events as periodical requesting location of mobile communication terminal to location gateway server in mobile communication network. But these conventional methods cause mobile communication interruption when the location trigger services are overloaded; thereby inducing performance of core server to be fell off. So in this paper, we have studied a new location trigger technology, named multilevel location trigger, to reduce mobile core network sewer triggering bottleneck and power consumption caused embedded GPS device of mobile phone. Actually, as design and evaluating the performance of location trigger after building test-bed environment, we contribute toward improving echnology of location trigger.

• Journal of Internet Computing and Services
• /
• v.11 no.4
• /
• pp.1-10
• /
• 2010

As recent fusion industry and ubiquitous technology have grown fast, network contents, which require high load, are provided in various infrastructures and facilities such as u-city and smart phones. Therefore, it is anticipated that the playback quality of multimedia compared to network loads degrades dramatically due to the drastic increment of real-time reference of conventional high load contents (eg. multimedia data). In this paper, we improved the method of the traffic assignment based on MPP which elevated the playback quality of multimedia by assigning discriminately the possible traffic of MMS with TP coefficients. When the TP coefficient which combines content preference with media preference was applied to a real-time traffic assignment scheduler, the simulation results showed that the multimedia playback stream was assigned within the possible traffic of a server. The real-time scheduling algorithm was improved by using the TP coefficient that combines the time-dependent image contents and the weighted value of media preference. It was observed from the experiment that the loss of the possible traffic decreases to 3.91% and 3.88% for three and four clients respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.4
• /
• pp.1035-1044
• /
• 1998

A new multi-channel access scheme and the associated network architecture for a single-hop WDM local area network is proposed in this paper. The proposed architecture has Central Scheduling Node (CSN) for the transmission coordination among many users, which is one of the key issues in single-hop WDM networks. The data channels, source nodes, and destination nodes are selected at CSN in very simple menner. Our scheme can relive the control processing overhead at all nodes in the network which is caused in existing distributed scheduling algorithms. CSN is simple in the architecture can be implemented easily. in respect to the network performance, the maximum obtainable throughput is up to that of the ideal output queuing because of collision free scheduling. We use the MQMS (multi-queue multi-server) model for performance analaysis.