• Journal of the Korea Society of Computer and Information
• /
• v.4 no.4
• /
• pp.148-154
• /
• 1999

TCP has improved by many papers which suggest the new algorithms and modify the previous algorithms. This paper compares Tahoe, Reno, New-Reno, Vegas, and SACK. The first version is Tahoe and is globally used. Reno has optimal performance during occurring one packet loss within a window of data, but can suffer from performance when multiple packets are dropped from a window of data. New-Reno avoids some of the performance problems of Reno TCP when multiple packets are dropped from a window of data. but is occurring the problem of the necessary retransmission. SACK resolves the all above problems and is used in bandwidth delay product environment. Vegas uses network bandwidth more efficiently and is a new implementation of TCP that achieves between 40 and 70 better throughput, with one-fifth to one-half the losses, as compared to the implementation of Reno TCP.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.113-116
• /
• 2005

In general, multiple mobile hosts (MH) access at a base station (BS) that terminates the wired link and relays data flow to the wireless link in wired and wireless heterogeneous network. In this network, the BS is tend to be a bottleneck and to degrade a network performance. Many studies have been done throughout several protocol layers. Especially on the transport layer, many techniques were studied to enhance TCP performance. But most of them are concerned to enhance TCP throughput and TCP fairness is hardly considered. In this paper, an algorithm for enhancing TCP fairness is proposed and its performance is verified by ns-2 simulation.

• Journal of KIISE:Information Networking
• /
• v.30 no.5
• /
• pp.649-655
• /
• 2003

Network-based computing such as cluster computing requires a reliable high-speed transport protocol. TCP is a representative reliable transport protocol on the Internet, which implements many mechanisms, such as flow control, congestion control, and retransmission, for reliable packet delivery. This paper, however, finds out that Myrinet does not incur any packet losses caused by network congestion. In addition, we ascertain that Myrinet supports reliable and ordered packet delivery. Consequently, most of reliable routines implemented in TCP produce unnecessarily additional overheads on Myrinet. In this paper, we show that we can attain the reliability only by flow control on Myrinet and propose a new reliable protocol based on UDP named RUM (Reliable UDP on Myrinet) that performs a flow control. As a result, RUM achieves a higher throughput by 45% than TCP and shows a similar one-way latency to UDP.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.8
• /
• pp.1955-1961
• /
• 2009

As a core technology realizing ubiquitous world, recent researches are being concentrated to wireless sensor network. However, most research results were focused to the sensor network technology itself, even though interworking between the sensor network and Internet is also one of primitive requirements for ubiquitous world. In this paper, we design the tiny TCP/IPv6 profile which makes it possible to inter-connect the sensor network device to IPv6 based Internet. To confirm operation of the designed profile, we experimentally implemented and evaluated minimum TCP/IPv6 based on TinyOS. The evaluation result shows that throughput of our tiny TCP/IPv6 is almost same as that of TinyOS component.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.63-70
• /
• 2010

In IEEE 802.11e system providing differentiated services, there exist some problems as follows; collision probability increase due to the increase in the number of nodes by employing CSMA/CA transmission mode, transmission speed declining tendency towards the worst of it, which is caused by different transmission mode and decrease of TCP transmission rate as the result of the link occupancy by UDP when TCP shares the link with UDP by the TCP’s flow control characteristic. In this thesis, the initial minimum and maximum CW are set differently according to the number of connected nodes in the network to avoid collisions and TXOP is adjusted according to the channel state, in which ACs with low priority but better channel state will get gradually more chances to transmit leading to optimal channel capacity. Also, by allowing higher priority for ACK frames which control the TCP transmission, the flow control becomes better because that reduces the channel occupancy by UDP flow, and by this, fair transmission is obtained from the result of the more fair transmission and active resource allocation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10A
• /
• pp.965-973
• /
• 2007

We analyzed that the loss of data in TCP protocol based wireless networks caused by overlapped responses in bi-directional nodes that were resulted in out of the data sequence. This loss can be prevented by using revised TCP rate control algorithm and the performance of throughput can also be improved. The rate control algorithm is applied when the congestion happens between nodes while traffic packets are retransmitting in TCP bandwidth. In addition to applying the rate control algorithm, we determine the number of system clients in bandwidth and the average of pausing time between transmitting serial files to produce a competitive level so that an efficient performance of rapid retransmitting for the loss of multi-packets. This paper discusses the improvement of congestion control in that the decrease of the loss, firstly, as ensuring an efficient connection rate and, secondly, as using sliding window flow control.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.5
• /
• pp.659-665
• /
• 2013

IPCS(Inter Process Communication Service) is a real-time communication middleware designed for warship combat battle systems based on publisher-subscriber communication model. Because IPCS was originally designed to operated under 100 Mbps network environment, increasing network speed into Gigabit environment does not linearly increase the throughput of IPCS. To solve this problem, we anaylized IPCS structure and optimized IPCS into Gigabit-Ethernet environment. We found parameters to improve IPCS based on UDP and Token-ring structure. By improving, IPCS has reliability and higher throughput than TCP although IPCS is based on UDP.

• The KIPS Transactions:PartC
• /
• v.10C no.5
• /
• pp.595-602
• /
• 2003

In this paper, we proposed new buffer management and cell scheduling scheme of GFR service for improving fairness of TCP/IP traffic in ATM networks. The proposed algorithm used untagged cell, which came to ATM switch, to decide the policy for discard of frame and what kind of VC cell it would serve. Performance analysis through the simulation present that proposed scheme can meet fairness 2 (MCR Plus equal share), which are not met by conventional scheduling mechanism such as WRR. Also, proposed scheme is superior to WRR about 30% in throughput and more efficiency in fairness criteria.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.39 no.7
• /
• pp.22-29
• /
• 2002

The Gauranteed Frame Rate service category was proposed by the ATM Forum as an enhancement to the UBR service. This service aims to support minimum cell rate gaurantee for each virtual connection and allow any excess bandwidth in the network to be shared among the contending VCs in a fair manner. We propose a new buffer management algorithm for GFR service through FIFO queuing discipline. Proposed scheme can provide minimum bandwidth guarantee for GFR VCs as well as improve the fairness among the competing GFR VCs on a single FIFO queue. From simulation results, we demonstrate the proposed scheme fulfills the requirement of GFR service as well as improves the TCP throughput.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.48-53
• /
• 1997

The multicasting of MCS(Multicast Server) requires a effective traffic control scheme to prevent buffer overflow on ATM subnetworks. This paper considers MCS multicasting to TCP packets, and propose EPD + SPD scheme(Early Packet Discard-same Source Packet Discard) using common buffer. When the threshold of output buffer is reached, MCS drops an entire packet prior to buffer overflow, so that corrupted packets will not be transmitted by the server. And SPD scheme show that the EPD + SPD results in higher TCP throughput than that of tail drop and EPD + DFF.