An algorithm to detect TCP spurious timeouts and its application to operational UMTS/GPRS networks

Vacirca, Francesco; Ziegler, Thomas; Hasenleithner, Eduard

doi:10.1016/j.comnet.2005.11.003

Cited by 16 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[3] reports on measurements from a relatively early GPRS setup, where most problems seem to be associated with mobile connections and automatic link adaption. The results of passively monitoring live GPRS/UMTS networks are shown in [4], [5]. Both actually identify a low rate of spurious timeouts in live networks.…”

Section: Related Workmentioning

confidence: 92%

Spurious TCP Timeouts in 802.11 Networks

Malone¹,

Leith²,

Aggarwal³

et al. 2008

Proceedings of the 6th Intl Symposium on Modeling and Optimization

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 92%

Spurious TCP Timeouts in 802.11 Networks

Malone¹,

Leith²,

Aggarwal³

et al. 2008

Proceedings of the 6th Intl Symposium on Modeling and Optimization

View full text Add to dashboard Cite

show abstract

“…Because TCP cannot distinguish congestion-induced from the loss over the wireless link or a sudden increase in delay, it retransmits a packet and reduces the sending rate unnecessarily. Varcica et al have detected spurious retransmissions in the operational UMTS/GPRS network and concluded that spurious timeouts are infrequent [14]. However, they could not distinguish the TCP flows of mobile users from those without mobility.…”

Section: Tcp Traffic Analysismentioning

confidence: 99%

3G and 3.5G wireless network performance measured from moving cars and high-speed trains

Jang

Han

Cho³

et al. 2009

Proceedings of the 1st ACM Workshop on Mobile Internet Through Cellular Networks

View full text Add to dashboard Cite

In recent years, the world has witnessed the deployment of several 3G and 3.5G wireless networks based on technologies such as CDMA 1x EVolution Data-Only (EVDO), High-Speed Downlink Packet Access (HSDPA), and mobile WiMax (e.g., WiBro). Although 3G and 3.5G wireless networks support enough bandwidth for typical Internet applications, their performance varies greatly due to the wireless link characteristics.We present a measurement analysis of the performance of UDP and TCP over 3G and 3.5G wireless networks. The novelty of our measurement experiments lies in that we took our measurements in a fast moving car on a highway and in a high-speed train running at 300 km/h. Our results show that mobile nodes experience far worse performance than stationary nodes over the same network.

show abstract

“…The frequency of occurrence for spurious timeouts is not well understood over the range of networks that comprise the Internet of today. There are several proposed solutions for the spurious timeout problem (for example (Sarolahti et al, 2003)) that implies that it is a common problem, but other research has shown very little frequency of spurious timeouts (Vacirca et al, 2006).…”

Section: Modified Retransmit Calculationsmentioning

confidence: 99%

The Effect of Packet Loss on the Response Times of Web Services

Garcia¹,

Hurtig²,

Brunström³

2007

Proceedings of the Third International Conference on Web Information Systems and Technologies

View full text Add to dashboard Cite

Abstract:Web services have today become an important technology for information exchange over the Internet. Although web services are designed to support interoperable machine-to-machine interaction, humans are often the final recipients of the produced information. This makes the performance of web services important from a user perspective. In this paper we present a comprehensive experimental evaluation on the response times of web services. The limited amount of data transfered in a typical web service message makes its performance sensitive to packet loss in the network and we focus our investigation on this issue. Using a web service response time model, we evaluate the performance of two typical web services over a wide range of network delays and packet loss patterns. The experiments are based on network emulation and two real protocol implementations are examined. The experimental results indicate that a single packet loss may more than double the response times of the evaluated services and lead to noticeable delays for the end user. We briefly review previous solutions that can be applied to improve performance and outline an improved approach that is based on packet loss detection at the receiver.

show abstract

An algorithm to detect TCP spurious timeouts and its application to operational UMTS/GPRS networks

Cited by 16 publications

References 14 publications

Spurious TCP Timeouts in 802.11 Networks

Spurious TCP Timeouts in 802.11 Networks

3G and 3.5G wireless network performance measured from moving cars and high-speed trains

The Effect of Packet Loss on the Response Times of Web Services

Contact Info

Product

Resources

About