全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

Modeling of Packet Switched Network over TCP Veno: TCP Improvement for Transmission over Wireless Access Networks.

Keywords: Congestion control , congestion loss , random loss , transmission control protocol (TCP) Reno , TCP Vegas , TCP Veno wireless access networks

Full-Text   Cite this paper   Add to My Lib

Abstract:

Computer networks form an essential substrate for the multitude of distributed application which is nowan essential part of modern business and personal life. It is important to optimize the performance ofcomputer networks, so that users can derive optimum utility from the expertise in network infrastructure.Most networks perform well when lightly used, but problems appear when network load increases. Thisloss of network performance when a network is heavily loaded is called congestion. Wired networks arebecoming an integral part of the Internet. Unlike wireless networks, random packet loss due to bit errorsis not negligible in wired networks, and this causes significant performance degradation of transmissioncontrol protocol (TCP). We propose and study a novel end-to-end congestion control mechanism calledTCP Veno that is simple and effective for dealing with random packet loss. A key ingredient of Veno isthat it monitors the network congestion level and uses that information to decide whether packet lossesare likely to be due to congestion or random bit errors. Specifically: A). it refines the multiplicativedecrease algorithm of TCP Reno—the most widely deployed TCP version in practice—by adjusting theslow-start threshold according to the perceived network congestion level rather than a fixed drop factorand B) it refines the linear increase algorithm so that the connection can stay longer in an operatingregion in which the network bandwidth is fully utilized, based on extensive network testbed experimentsand live Internet measurements.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133