• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.106-109
• /
• 2004

This study designs a load balancer via direct routing that share a virtual service on a single IP address in the Linux system and suggests an efficient load balancing method to improve transmission speed in the web server cluster environment. It will increase performance and scalability with fast packet transfer and removing bottleneck problem by using TCP Splicing and Content-Aware Distributor method. This method is expected to be the noticeable technology that provides an important interface, which make application services for e-commerce effectively be applied to high-speed network infrastructure. At this time, it is required to study further on the optimum balancing method in the web server cluster environment so as to apply the hybrid (optimum load balancing method by software and hardware) method and improve the reuse of security cession based on high-speed TCP connections.

• Annual Conference of KIPS
• /
• 2009.04a
• /
• pp.1202-1205
• /
• 2009

본 논문은 단말 호스트에서 발생한 트래픽 정보를 분석하여 단말 호스트의 다양한 정보를 수집하는 방법론에 대하여 기술한다. 본 논문에서는 첫째로 TCP 의 3-way handshake 중 SYN 패킷의 정보를 이용한 호스트의 운영체제를 예측하는 방법론과 해당 호스트에서 발생한 TCP 연결의 응답시간 분포를 분석하여 호스트의 네트워크 접근 밥법이 유 무선인지 분류하는 새로운 방법론을 제안한다. 분석이 완료된 호스트는 데이타베이스에 해당 호스트의 정보를 기록한다. 이는 웹을 통해 손쉽게 확인 가능하도록 하기 위함이다. 또한 하나의 호스트에서 유 무선 트래픽이 동시에 발생되었을 경우, 이에 대한 정보를 기반으로 유 무선 공유기 설치 유무를 판별할수 있도록 설계하였다.

• The KIPS Transactions:PartC
• /
• v.9C no.4
• /
• pp.513-522
• /
• 2002

Current end-to-end congestion control depends only on the information of end points (using three duplicate ACK packets) and generally responds slowly to the network congestion. This mechanism can't avoid TCP global synchronization which TCP congestion window size is fluctuated during congestion occurred and if RTT (Round Trip Time) is increased, three duplicate ACK packets is not a correct congestion signal because congestion maybe already disappeared and the host may send more packets until receive the three duplicate ACK packets. Recently there is increasing interest in solving end-to-end congestion control using active network frameworks to improve the performance of TCP protocols. ACC (Active congestion control) is a variation of TCP-based congestion control with queue management In addition traffic modifications nay begin at the congested router (active router) so that ACC will respond more quickly to congestion than TCP variants. The advantage of this method is that the host uses the information provided by the active routers as well as the end points in order to relieve congestion and improve throughput. In this paper, we model enhanced ACC, provide its algorithm which control the congestion by using information in core networks and communications between active routers, and finally demonstrate enhanced performance by simulation.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.5
• /
• pp.583-589
• /
• 2002

The Internet is absolutely contributed to information telecommunication revolution nowadays. Realizing local network at the various type of buildings such as a company and a university, ethernet is used for subnet and FDDI, ATM are used for backbone mainly in order to get internet services. Processing TCP/IP protocol suite and analyzing the protocol exactly is essential to detecting the problem occurring in the network and developing communication equipment. This paper presents implementation of ethernet LAN protocol analyser which monitors and simulates ICP/IP protocol suite carrying the Internet and non-Internet protocol such as Netware and NetBIOS. MS window98 and visual C are used for development environment and application program operates on the NDIS firmware. The performance analysis on the proposed system is carried out as monitoring and simulating the traffic over LAN of a university. In the result of monitoring the system, the processing time of a packet captured over the LAN is about 1.5ms. In case of simulating the system, the processing time to be taken carrying out TCP connection and disconnection once is packet is about 8.6ms. The performance analysis of monitoring and simulation results satisfies with 10 Mbps ethernet LAN environment.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.8
• /
• pp.261-270
• /
• 2014

As Internet traffic increases recently, much effort has been put on improving the performance of a web server. In addition to hardware side solutions such as replacement by high-end hardware or expansion of the number of servers, there are software side solutions to improve performance. Recent studies on these software side solutions have been actively performed. In this paper, we identify performance degradation problems occurring in a conventional TCP networking reception process and propose a way to solve them. We improve performance by combining three kinds of existing methods for Linux Networking Performance Improvement and two kinds of newly proposed methods in this paper. The three existing methods include 1) an allocation method of a packet flow to a core in a multi-core environment, 2) ITR(Interrupt Throttle Rate) method to control excessive interrupt requests, and 3) sk_buff data structure recycling. The two newly proposed methods are fd data structure recycling and epoll_event data structure recycling. Through experiments in a web server environment, we verify the effect of our two proposed methods and its combination with the three existing methods for performance improvement, respectively. We use three kinds of web servers: a simple web server, Lighttpd generally used in Linux, and Apache. In a simple web server environment, fd data structure recycling and epoll_event data structure recycling bring out performance improvement by about 7 % and 6%, respectively. If they are combined with the three existing methods, performance is improved by up to 40% in total. In a Lighttpd and an Apache web server environment, the combination of five methods brings out performance improvement by up to 36% and 20% in total, respectively.

• KSCI Review
• /
• v.14 no.2
• /
• pp.235-244
• /
• 2006

This paper attacked the unknown DoS which mixed a DoS attack, Worm and the Trojan horse which used IP Source Address Spoofing and Smurf through the SYN Flooding way that UDP, ICMP, Echo, TCP Syn packet operated. the applications that used TCP/UDP in VoIP service networks. Define necessity of a Dynamic Update Engine for a prevention, and measure Miss traffic at RT statistics of inbound and outbound parts in case of designs of an engine at IPS regarding an Self-learning module and a statistical attack spread. and design a logic engine module. Three engines judge attack grades (Attack Suspicious, Normal), and keep the most suitable filtering engine state through AND or OR algorithms at Footprint Lookup modules. A Real-Time Dynamic Engine and Filter updated protected VoIP service from DoS attacks, and strengthened Ubiquitous Security anger, and were turned out to be.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.165-174
• /
• 2006

This paper attacked the unknown DoS which mixed a DoS attack, Worm and the Trojan horse which used IP Source Address Spoofing and Smurf through the SYN Flooding way that UDP, ICMP, Echo, TCP Syn packet operated, the applications that used TCP/UDP in VoIP service networks. Define necessity of a Dynamic Update Engine for a prevention, and measure Miss traffic at RT statistics of inbound and outbound parts in case of designs of an engine at IPS regarding an Self-learning module and a statistical attack spread, and design a logic engine module. Three engines judge attack grades (Attack, Suspicious, Normal), and keep the most suitable filtering engine state through AND or OR algorithms at Footprint Lookup modules. A Real-Time Dynamic Engine and Filter updated protected VoIP service from DoS attacks, and strengthened Ubiquitous Security anger, and were turned out to be.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.2
• /
• pp.104-113
• /
• 2009

Recently, high-speed Internet users and broadband network infrastructure are increasing. However, the TCP protocol widely used in the Internet is an appropriate transport only for the legacy Internet, it is inefficient for traffic transport for network environments with large bandwidth-delay product. In order to remedy this problem, there have been many researches about improved congestion control algorithms for broadband networks. In these studies, most of performance evaluation has been done by simulations. In this paper, after we reviewed the proposed high bandwidth transport layer protocols, we implemented a real testbed, measured the performance and analyzed the problems of high-speed transport protocols through the international research network TEIN2 between three nations, Korea, China, and Germany.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.1
• /
• pp.285-290
• /
• 2018

Vehicular ad hoc network (VANET) is one of the future communication technologies in which it offers safe-driving information and Internet access for both drivers and passengers by communicating among cars on the road. In case of applying Content Centric Network (CCN) rather than TCP/IP over VANET, called VCCN, it can provide efficient multicast communication of shared information among participating cars as well as offer corresponding one-to-one communications. This paper introduces SUMO for simulating traffic flows, VANET for car-to-car ad hoc communications, and CCN for a future Internet architecture. In addition, it compares and analyses the transmission performance of moving cars over VCCN. According to the simulation results using SUMO and VCCN, the larger the packet size, the better the transmission performance. In addition, VCCN provides higher packet transmission rate than that of TCP/IP when the clients shares the same contents. Furthermore, the overall data reception rate exceeds the physical transmission channel rate.

• Journal of KIISE:Information Networking
• /
• v.30 no.5
• /
• pp.595-603
• /
• 2003

To provide mobile nodes with continuous communication services, it is important to reduce the packet losses during handoffs. The handoffs of mobile nodes cause packet losses and decrease of TCP throughput on account of a variety of factors. One of those is the congestion in the new cell. Due to the congestion, not only the node moving into the cell but also the already existing nodes that were successfully communicating in the cell suffer the performance degradation. In this paper we propose a new handoff mechanism called‘packet freeze control’, which avoids the congestion caused by handoffs by regulating the influx of traffic burst into the new cell. Packet freeze control is applicable to a wireless network domain in which FAs(Foreign Agents) are connected hierarchically and constitute a logical tree. It gradually increases the number of packets transferred to the new cell by buffering packets in the FAs on the packet delivery path over the wireless network domain. The simulation results show that the proposed mechanism not only reduces the packet losses but also enhances the TCP throughput of other mobile nodes in the cell.