• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.2B
• /
• pp.130-142
• /
• 2009

In this paper, we propose a self-adaptation framework that selects a TCP variant adapted to current end-to-end path among available TCP variants. There is no single version of TCP that is suitable to all network environments since the causes for performance degradation are different one another according to characteristics of network environments. Thus, determining that which TCP variants should be selected in order to get best performance is very important. To enable adaptation through such determination, we integrate the existing network estimation schemes and some TCP variants into our framework then make light-weight performance knowledge database for TCP selection. Through implementing and evaluating the proposed framework we show that our solution can help TCP get high and stable performance on the various types of network environments by pure end-to-end.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.4
• /
• pp.241-255
• /
• 2015

Recent network environment has been rapidly evolved to cloud computing environment based on the development of the Internet technologies. Furthermore there is an increasing demand on mobile cloud computing due to explosive growth of smart devices and wide deployment of LTE-based cellular networks. Thus mobile Desktop-as-a-Service(DaaS) could be a pervasive service for nomadic users. In addition, video streaming traffic is currently more than two-thirds of mobile traffic and ever increasing. All such trends enable that video streaming in mobile DaaS could be an important concern for mobile cloud computing. It should be noted that the performance of the Transmission Control Protocol(TCP) on cloud host servers greatly affects Quality of Service(QoS) of video streams for mobile users. With widely deployed Linux server platforms for cloud computing, in this paper, we conduct an experimental analysis of the twelve Linux TCP variants in mobile DaaS environments. The results of our experiments show that the TCP Illinois outperforms the other TCP variants in terms of wide range of packet loss rate and propagation delay over LTE-based wireless links between cloud servers and mobile devices, even though TCP CUBIC is usually used in default in the current Linux systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.1
• /
• pp.24-51
• /
• 2011

When supporting both voice and TCP in a wireless multihop network, there are two conflicting goals: to protect the VoIP traffic, and to completely utilize the remaining capacity for TCP. We investigate the interaction between these two popular categories of traffic and find that conventional solution approaches, such as enhanced TCP variants, priority queues, bandwidth limitation, and traffic shaping do not always achieve the goals. TCP and VoIP traffic do not easily coexist because of TCP aggressiveness and data burstiness, and the (self-) interference nature of multihop traffic. We found that enhanced TCP variants fail to coexist with VoIP in the wireless multihop scenarios. Surprisingly, even priority schemes, including those built into the MAC such as RTS/CTS or 802.11e generally cannot protect voice, as they do not account for the interference outside communication range. We present VAGP (Voice Adaptive Gateway Pacer) - an adaptive bandwidth control algorithm at the access gateway that dynamically paces wired-to-wireless TCP data flows based on VoIP traffic status. VAGP continuously monitors the quality of VoIP flows at the gateway and controls the bandwidth used by TCP flows before entering the wireless multihop. To also maintain utilization and TCP performance, VAGP employs TCP specific mechanisms that suppress certain retransmissions across the wireless multihop. Compared to previous proposals for improving TCP over wireless multihop, we show that VAGP retains the end-to-end semantics of TCP, does not require modifications of endpoints, and works in a variety of conditions: different TCP variants, multiple flows, and internet delays, different patterns of interference, different multihop topologies, and different traffic patterns.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.211-214
• /
• 2005

There are emerging many eScience applications. More and more scientists want to collaborate on their investigation with international partners without space limitation by using these applications. Since these applications have to analyze the massive raw data, scientists need to send and receive the data in short time. So today's network related requirement is high speed networking. The key point of network performance is transport protocol. We can use TCP and UDP as transport protocol but we use TCP due to the data reliability. However, TCP was designed under low bandwidth network, therefore, general TCP, for example Reno, cannot utilize the whole bandwidth of high capacity network. There are several TCP variants to solve TCP problems related to high speed networking. They can be classified into two groups: loss based TCP and delay based TCP. In this paper, I will compare two approaches of TCP variants and propose a hybrid approach for high speed networking.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.3A
• /
• pp.221-231
• /
• 2006

TCP is needed as a transport protocol to provide reliable end-to-end message delivery for MANETs in order to achieve a smooth integration with the fixed Internet. Particularly, TCP has its variants, namely TCP-Reno and TCP-Vegas. However, there has been no research work on extensive performance comparison of TCP-Reno and TCP-Vegas over AODV and OLSR. This paper is the first trial to perform the research by using ns-2 simulator. Through the extensive simulations, we found that which to select among routing protocols is more important than which to select among TCP variants, because the performance difference between TCP-Reno and TCP-Vegas over uy selected routing protocol is not so much outstanding. Particularly, TCP-Vegas relies on an accurate BaseRTT estimation in order to decide the sending rate of a TCP Sender. However, it cannot be directly applied to MANET because a route change makes the Base an used over a Previous Path obsolete. Therefore, we propose a technique for improving the performance of TCP-Vegas by considering the route change, and show the performance improvement through simulation study.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.139-145
• /
• 2016

Dumbbell is the most basic topology that can be used in almost all kind of network experiment within it or just by little expansion. While Transmission Control Protocol TCP is the basic protocol that is used for the connectivity among networks and stations. TCP major and basic goal is to provide path and services to different applications for communication. For that reason TCP has to transfer a lot of data through a communication medium that cause serious congestion problem. To calculate the congestion problem, different kind of pre-cure solutions are developer which are Loss Based Variant and Delay Based Variant. While LBV keep track of the data that is going to be passed through TCP protocol, if the data packets start dropping that means congestion occurrence which notify as a symptom, TCP CUBIC use LBV for notifying the loss. Similarly the DBV work with the acknowledgment procedure that is used in when data ACK get late with respect to its set data rate time, TCP COMPOUND/VAGAS are examples of DBV. Many algorithms have been purposed to control the congestion in different TCP variants but the loss of data packets did not completely controlled. In this paper, the congestion control algorithms are implemented and corresponding results are analyzed in Dumbbell topology, it is typically used to analyze the TCP traffic flows. Fairness of throughput is evaluated for different TCP variants using network simulator (NS-2).

• Journal of Communications and Networks
• /
• v.18 no.2
• /
• pp.238-245
• /
• 2016

A sequence number checking technique is proposed to improve the performance of TCP connections in mobile ad hoc networks. While a TCP connection is initialized, a routing protocol takes the responsibility for checking the hop count between a source and destination pair. If the hop count is greater than a predefined value, the routing protocol decides to use a proxy node. The responsibility of a proxy node is to check the correctness of data packets and inform the missing packets by sending an acknowledgement from a proxy node to the source node. By doing so, the source node is able to retransmit any missing packet in advance without waiting until an end-to-end acknowledgement is received from the destination. Simulation results show that the proposed mechanism is able to increase throughput up to 55% in static network and decrease routing overhead up to 95%in mobile network.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.129-137
• /
• 2016

Transmission Control Protocol as a transport layer protocol provides steady data transfer service. There are some serious concerns about the performance of TCP over diverse networks. The vital concern in TCP network environment is congestion which may occur due to quick transmission rates or because of large number of new connections entering the network at the same time. Size of queues in routers grows thus resulting in packet drops. Retransmission of the dropped packets, and reduced throughput can prove costly. Explicit Congestion Notification (ECN) in conjunction with Active Queue Management mechanisms (AQM) such as Random early detection (RED) is used for packet marking rather than dropping. In IP packet header ECN bits can be added as a sign of congestion thus avoiding needless packet drops. The proposed ECN and AQM mechanism can be implemented with help of ns2 simulator and the performance can be tested on different TCP variants.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06d
• /
• pp.514-519
• /
• 2007

본 논문에서는 기존의 TCP 변종들을 바탕으로 종단간 네트워크 환경에 가장 적응이 잘 이루어진 변종의 알고리즘을 선택하는 TCP 프레임워크를 제안한다. 프로토콜 선택의 문제가 중요한 이유는 모든 네트워크 환경에 적합한 단일 버전의 프로토콜이 존재하지 않기 때문이며, 이것은 각 네트워크마다 TCP의 성능 저하 원인이 서로 다르기 때문이다. 이러한 판단 및 프로토콜의 적응이 가능하게 하기 위해 본 논문에서는 기존에 연구되어온 여러 가지 네트워크 측정 기법들과 TCP 변종들을 하나로 합치는 과정을 거쳤으며, 여기에 각 TCP들의 성능 정보들을 제공하여 세션 중간에 적절한 전송 알고리즘을 선택하여 사용할 수 있도록 하였다. 실험을 통해 우리는 end-to-end로 여러 환경 하에서 높은 성능을 이끌어낼 수 있다는 것을 보였으며, 제안한 방법이 지금까지 연구되어온 여러 TCP 변종들이 실제로 적절하게 활용될 수 있도록 하는데 중요한 역할을 할 것으로 믿는다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.1
• /
• pp.7-13
• /
• 2011

While the TCP throughput degradation problem in coded wireless mesh networks is well-known, few effective solutions have been proposed. Most schemes proposed attempts to mask packet reordering by ordering packets at a lower layer or to adjust a packet transmission rate to solve the scarcity problem of coding opportunities. Through the throughput comparison of traditional standard TCP variants, we show that losses and duplication of TCP acknowledgements in coded wireless mesh networks can impact throughput. In addition, we show that a TCP variant that does not rely on duplicate acknowledgements is more suitable for coded wireless mesh networks.