• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.1371-1374
• /
• 2004

본 논문에서는 내부 LAN(Local area network)에서 MSS(Maximum segment size)의 변화가 네트워크 성능에 미치는 영향에 대하여 분석한다. 내부 LAN에 웹 클라이언트와 웹 서버를 두고 이더넷(Ethernet)이 허용하는 사이즈 내에서 MSS 값의 변화가 네트워크의 성능에 미치는 영향을 분석한다. 처리량(Throughput), 이용률(Utilization), 분실율, 수신율, RTT(Round Trip Time)를 사용하여 성능을 평가하였다. 실험은 네트워크 시뮬레이터 중의 사실상 표준 도구인 NS-2로 한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.1
• /
• pp.33-40
• /
• 2017

In this Paper, Analyse the Steady State Behavior of TCP and TFRC with Packet Error when both TCP and TFRC Flows Co-exist in the Network. First, Model the Network with TCP and TFRC Connections as a Discrete Time System. Second, Calculate Average Round Trip Time of the Packet Between Source and Destination on Packet Loss Environment. Then Derive the Steady State Performance i.e. Throughput of TCP and TFRC, and Average Buffer Size of RED Router Based on the Analytic Network Model. The Throughput of TCP and TFRC Connection Decrease Rapidly with the Growth of Sending Window Size and Their Transmission Rate but Their Declines become Smoothly when the Number of Sending Window Arrives on Threshold Value. The Average Queue Length of RED Router Increases Slowly on Low Transmission Rate but Increases Rapidly on High Transmission Rate.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.3 s.345
• /
• pp.126-134
• /
• 2006

Traditional TCP implementations have the under-utilization problem in large bandwidth delay product networks especially during the startup phase. In this paper, we propose a delay-based congestion control(DCC) mechanism to solve the problem. DCC is subdivided into linear and exponential growth phases. When there is no queueing delay, the congestion window grows exponentially during the congestion avoidance period. Otherwise, it maintains linear increase of congestion window similar to the legacy TCP congestion avoidance algorithm. The exponential increase phase such as the slow-start period in the legacy TCP can cause serious performance degradation by packet losses in case the buffer size is insufficient for the bandwidth-delay product, even though there is sufficient bandwidth. Thus, the DCC uses the RTT(Round Trip Time) status and the estimated queue size to prevent packet losses due to excessive transmission during the exponential growth phase. The simulation results show that the DCC algorithm significantly improves the TCP startup time and the throughput performance of TCP in large bandwidth delay product networks.

• Journal of the Korea Society for Simulation
• /
• v.20 no.1
• /
• pp.61-67
• /
• 2011

Smart TV System will lead to drastic change of communication and media industries as one of the emerging next generation network services. However, when the number of concurrent users increases rapidly, the issue of service quality degradation occurs because providing services to many users simultaneously stresses both the server and the network. The server limitation can be circumvented by deploying server clusters. but the network limitation is far less easy to cope with, due to the difficulty in determining the cause and location of congestion and in provisioning extra resources. In order to alleviate these problems, a number of schemes have been developed. Prior works mostly focus on reducing user-centric performance metrics of individual connection, such as the round-trip time(RTT), downloading time or packet loss rate, but tend to ignore the network loads caused by the concurrent connections or global network load balance. In this work, we make an in-depth investigation on the issue of user grouping for massive Smart TV services through simulations on actual Internet test-bed, PlanetLab.

• The KIPS Transactions:PartC
• /
• v.13C no.3 s.106
• /
• pp.353-358
• /
• 2006

Unlike TCP Reno, TCP Vegas recognizes network congestion through the measuring of RTT (Round Trip Time) and decides the main congestion control parameters, such as Windows size. But, congestion avoidance scheme of Vegas poorly reflects asymmetric characteristics of packet path because TCP Vegas uses the measuring of RTT that reflects forward/backward packet transmission delay as a forward delay. The RTT can't infer the forward/backward transmission delay variation because it only measures the packet's turn around time. In this paper, We have designed and implemented a new Vegas congestion control algorithm that can distinguish forward/backward network congestion. We have modified the source codes of TCP Vegas in Linux 2.6 kernel and verified their performance.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.3 no.1
• /
• pp.31-46
• /
• 1978

Consider a time interval during which the demand for trips is fixed (e.g. the rush hour period). The traveller has a choice between various public modes, whose travel times and fares are fixed, and the automobile mode, for which travel time and cost depend on the volume of traffic flow on those roads, which are subject to congestion. We consider the equilibrium in terms of a representative travellerm, who choses for any trip the mode and route with the least combined money and time cost. When several (parallel) model or routes are chosen, then the combined cost of money and time must be equal among these. Our problem is first, to find the optimal flows of cars and of public mode carriers on the various links of their networks and second the optimal fares for trips by the variousmodes. The object is to minimize the total operating costs of the carriers and car plus the total time costs to travellers. The optimal fares are related to, but not identical with the dual variables of the underlying Nonlinear Program. They are equal to these dual variables only in the case, when congestion tolls on trips or on the use of specific roads are collected from automobile users. When such tolls are not collected, they must be passed on as subsidies to travellers using competing modes. The optimal fares of public modes are then reduced by the amounts of these subsidies. Note that subsidies are not a flat payment to public carriers, but are calculated on the basis of tickets sold. Fares and subsidies depend in general on tile period considered. They will be higher during periods of higher demand. When the assumption of fixed trip demand is relaxed, this tare system is no longer best, but only second best since too much traffic will, in general, be generated. The Free Rider Theorem states the following : Suppose road tolls can be charged, so that a best pricing system for public modes is posssible. Then there may exist free rides on some routes and modes, but never on a complete round trip.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1322-1331
• /
• 2015

According to the hypervisor scheduler, the vCPU (virtual CPU) operates under two states: the running state and the stop state. When the vCPU is in the stop state, incoming events are delayed until that vCPU's state changes to the running state. The latency in handling such events that are sent to the vCPU is regarded as the I/O latency. Since a SMP (symmetric multiprocessing) VM (virtual machine) incorporates multiple vCPUs, the event latency on a SMP VM can vary according to specific vCPU that receives the event. In this paper, we propose a new scheme named event routing that sends events according to the operation state of each vCPU to reduce the event latency on an SMP VM. We implemented the proposed event routing scheme in Xen ARM hypervisor and confirmed the reduction of I/O latency from measuring the network RTT (round trip time) and the TCP bandwidth under a variety of testing conditions. The network RTT decreases by up to 94% and the TCP bandwidth increases up to 35% when compare to native Xen ARM.

• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.359-369
• /
• 2005

Delay estimation is a difficult Problem in computer networks. Accurate one-way delay estimation is crucial because it serves a very important role in network performance and thus application design. RTT(Round Trip Time) is often used as an approximation of the delay, but because it is a sum of the forward and reverse delays, the actual one-way delay cannot be estimated accurately from RTT. To estimate one-way delay accurately, this paper proposes a new scheme that analytically derives one-way delay, forward and reverse delay respectively. We show that the performance of TCP can improve dramatically in asymmetric networks using our scheme. A key contribution of this paper is that our one-way deiay estimation is much more accurate than RTT estimation so that TCP can quickly find the network capacity in the slow start phase. Since RTT is the sum of the forward and reverse delays, our scheme can be applied to any protocol that is based on RTT.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.2
• /
• pp.97-103
• /
• 2009

Improving TCP performance has long been the focus of many research efforts in 802.11 wireless networks study. Hop count and Round Trip Time (RTT) are the critical sources which serious affect the TCP performance on end to end connection. In this paper, we analytical derived the affection and based on the analysis we propose TCP should Change its Expected Value (TCP-CEV) when hop count and RTT change by setting a reasonable CWND change rate to improve the performance. The proposed scheme is applicable to a wide range of transport protocols using the basic TCP mechanism, and the protocol behavior is analytically tractable. We show that our simple strategy improves TCP performance at least over 12% in a chain topology, 4.9% in a grid topology and improve the TCP convergence.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.4B
• /
• pp.218-225
• /
• 2005

Although Snoop protocol can enhance TCP throughput efficiently in a wired-cum-wireless environment, it has a problem in performing local packet retransmissions under a burst error-prone wireless link. AT-Snoop protocol is proposed to cope with this Snoop protocol's problem by adopting adaptive timer. In this paper, TCP throughputs of AT-Snoop protocol have been analyzed with varying wireless link conditions and the ways of setting parameters of AT-Snoop protocol for higher TCP throughput are found out through computer simulations. From the simulation results, AT-Snoop protocol's two parameters, local retransmission threshold value and local retransmission timeout value, are closely related with the fading changing rate. To get higher TCP throughput, local retransmission threshold value and local retransmission timeout value should be set to a little bit larger values than average WSRTT(Wireless Smoothed Round Trip Time) and mean bad period of the wireless link, respectively.