• Journal of the Korea Society for Simulation
• /
• v.18 no.3
• /
• pp.91-102
• /
• 2009

The average window size is most closely related to average throughput. In order to improve fairness, the proposed dropper tries to control the window size of each flow to equal level by intentional packet drop. Intentional packet drop is performed only to the flows that have been occupied bandwidth in a large amount. Because of intentional packet drop, this flow cut down its transmission rate to a half. Accordingly, somewhat capacity of core link comes into existence. And other flow can use this new capacity of this link. Hence other flows have more throughput than before. In this paper, we propose the TRC (Transmission Rate Control) Dropper improving the fairness between individual flows of aggregated sources on DiffServ network. It has the fairness improvement mechanism mentioned above paragraph.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.4787-4807
• /
• 2016

Although the dense interconnection datacenter networks (DCNs) (e.g. FatTree) provide multiple paths and high bisection bandwidth for each server pair, the single-path TCP (SPT) and ECMP which are widely used currently neither achieve high bandwidth utilization nor have good load balancing. Due to only one available transmission path, SPT cannot make full use of all available bandwidth, while ECMP's random hashing results in many collisions. In this paper, we present OFPT, an OpenFlow based Parallel Transport framework, which integrates precise routing and scheduling for better load balancing and higher network throughput. By adopting OpenFlow based centralized control mechanism, OFPT computes the optimal path and bandwidth provision for each flow according to the global network view. To guarantee high throughput, OFPT dynamically schedules flows with Seamless Flow Migration Mechanism (SFMM), which can avoid packet loss in flow rerouting. Finally, we test OFPT on Mininet and implement it in a real testbed. The experimental results show that the average network throughput in OFPT is up to 97.5% of bisection bandwidth, which is higher than ECMP by 36%. Besides, OFPT decreases the average flow completion time (AFCT) and achieves better scalability.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11S
• /
• pp.3269-3277
• /
• 1999

To promote the inclusion of end-to-end congestion control in the design of future protocols using best-effort traffic, we propose a router mechanism, Extended FRED(ex-FRED). In this paper, we catagorize the TCP controlled traffics into robust and fragile traffic and discuss several unfairness conditions between them caused by the diverse applications. For example, fragile traffic from bursty application cannot use its fair share due to their slow adaptation. Ex-FRED modifies the FRED(Fair Random Early Drop), which can show wrong information due to the narrow view of actual buffer. Therefore, Ex-FRED uses per-flow accounting in larger virtual buffer to impose an each flow a loss rate that depends on the virtual buffer use of a flow. The simulation results show that Ex-FRED uses fair share and has good throughput.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.717-720
• /
• 2011

고속 네트워크 환경에서 AR UDT(Adaptive Rate control UDT)는 표준 전송 프로토콜인 TCP에 비해 뛰어난 성능을 보인다. UDT(UDP-based Data Transfer)를 기반으로 하는 AR UDT의 혼잡제어는 네트워크 상태를 예측하여 패킷 간 전송시간을 변화시킴으로써 기존 UDT보다 향상된 성능을 보인다. 그러나 AR UDT는 네트워크 상태 예측의 오차가 클 뿐만 아니라 rate control만을 공격적으로 조절하기 때문에 수신 버퍼의 초과로 인해 안정적인 성능을 기대하기 어렵다. 본 논문에서는 AR UDT환경에서 네트워크 상태에 따라 적응적으로 혼잡제어를 하는 기법을 제안한다. RTT(Round Trip Time)의 변화량에 따라 네트워크 상태를 예측하여 flow control과 rate control을 적응적으로 조절한다. 네트워크 시뮬레이션 결과를 통하여 AR UDT에 비해 전송속도와 안정성이 향상되었음을 보였다.

• Journal of Korea Multimedia Society
• /
• v.14 no.7
• /
• pp.905-916
• /
• 2011

Recently, the W3C has developed the HTML 5 standard to provide various multimedia services as well as a web based streaming. HTML5 based web browsers with the built-in video codecs can be used directly for streaming services, though previous web browsers should contain playback plug-in for streaming services. In addition, an adaptive streaming technology using HTTP/TCP has been standardized, since an Internet firewall does not support RTP/UDP streaming protocol but HTTP/TCP streaming protocol. In this paper, we propose the service migration mechanism among various devices in the HTML5-based adaptive HTTP streaming environments. The proposed algorithm and architecture were modeled for migrating media flows, media flow control, and session control and implemented using JavaScript. Finally, we showed that the proposed mechanism was effective to migrate HTTP streaming service among various devices by performing several experiments.

• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.477-480
• /
• 2010

This paper develops a sensor gateway for using Internet for traffic flow control and remote monitoring, it suggest the required protocol with authentication and encryption. The traffic Surveillance and Control System is an important service to the ITS(Intelligent Transportation System). The traffic surveillance and control system's TCP / IP and the Internet network using is may cause damage means accessing from unauthorized users, Subsequent authentication and encryption of data is essential.

• 한국정보통신설비학회:학술대회논문집
• /
• 2008.08a
• /
• pp.45-50
• /
• 2008

Many applications of sensor network require connection to the Internet. The transmission protocol of traditional sensor network was designed within the sensor network itself. However, based on 6LoWPAN which can be accessed using IPv6, direct connection is possible between the sensor network and the TCP/IP network outside. Transmission of data in applications of sensor network falls into two main categories. One is a small packet that is periodically produced such as packet related to temperature and humidity. The other is a relatively large packet that brings about network overheads such as images. We investigated the conformance test and pros and cons of application data over the transmission protocol of Zigbee and 6LoWPAN. As a result, both Zigbee and 6LoWPAN have shown low rate of loss for periodic data and have in creased reliability of data transfer. When transmitting streaming image data, both ACK, non ACK mode of Zigbee and UDP of 6LoWPAN minimized transmission time but suffered the consequences of high packet loss. Even though TCP of 6LoWPAN required a long transmission time, we were able to confirm that no loss has occurred.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.881-889
• /
• 2022

As interest in environmental pollution caused by ship emissions is increasing worldwide, many studies are being conducted on the development of systems that increase energy efficiency to reduce ship emissions. In order to test the energy management system controller driven in real time on a large ship, it is necessary to perform the test through the simulator. In this study, addresses were set for each signal according to Modbus TCP/IP so that each control system and energy management system could be linked, and the algorithm was configured according to the signal flow. In addition, the signal generator was designed and manufactured so that each controller could artificially generate the signal collected from the vessel. As a result of the simulator production and interlocking, it was confirmed that each controller operated in real time performed its role appropriately, and that the algorithm of the ship energy management system was properly applied.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.43-48
• /
• 2004

RTP that is proposed supplement of real-time services on internet environment, as Real-time Transport Protocol, is the protocol that for the purpose of sending data of stream type. RTP and RTCP(Real-time Transport Control Protocol) basically work at the same time, RTCP serves with state information of network at present. RTP has important properties of a transport protocol that runs on end-to-end systems and provides demultiplexing. It also offer reliability and protocol-defined flow／congestion control that transport protocol like TCP can not provides. In this paper, we look around concept and construction of Differentiated sen1ice tint run on RTP and by setting parameters of packet transfer method be used CBQ(Class-Based Queuing) for packet transfer on Differentiated service, each service queue controls properly through packet scheduling method, such as WRR(Weighted Round Robin) and PRR(Packet-by-packet Round Robin) all service classes do not experience the starvation and confirm the performance through computer simulation to achieve fairly scheduling.