Congestion avoidance and control
SIGCOMM '88 Symposium proceedings on Communications architectures and protocols
Analysis of the increase and decrease algorithms for congestion avoidance in computer networks
Computer Networks and ISDN Systems
A control-theoretic approach to flow control
SIGCOMM '91 Proceedings of the conference on Communications architecture & protocols
TCP/IP illustrated (vol. 1): the protocols
TCP/IP illustrated (vol. 1): the protocols
End-to-end packet delay and loss behavior in the internet
SIGCOMM '93 Conference proceedings on Communications architectures, protocols and applications
Simulation-based comparisons of Tahoe, Reno and SACK TCP
ACM SIGCOMM Computer Communication Review
End-to-end routing behavior in the Internet
Conference proceedings on Applications, technologies, architectures, and protocols for computer communications
Improving the start-up behavior of a congestion control scheme for TCP
Conference proceedings on Applications, technologies, architectures, and protocols for computer communications
End-to-end Internet packet dynamics
SIGCOMM '97 Proceedings of the ACM SIGCOMM '97 conference on Applications, technologies, architectures, and protocols for computer communication
An integrated congestion management architecture for Internet hosts
Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
On network-aware clustering of Web clients
Proceedings of the conference on Applications, Technologies, Architectures, and Protocols for Computer Communication
On the constancy of internet path properties
IMW '01 Proceedings of the 1st ACM SIGCOMM Workshop on Internet Measurement
ACM SIGCOMM Computer Communication Review
End-to-end available bandwidth: measurement methodology, dynamics, and relation with TCP throughput
Proceedings of the 2002 conference on Applications, technologies, architectures, and protocols for computer communications
The Case for Informed Transport Protocols
HOTOS '99 Proceedings of the The Seventh Workshop on Hot Topics in Operating Systems
On the relationship between file sizes, transport protocols, and self-similar network traffic
On the relationship between file sizes, transport protocols, and self-similar network traffic
A measurement study of available bandwidth estimation tools
Proceedings of the 3rd ACM SIGCOMM conference on Internet measurement
Improving TCP Startup Performance Using Active Measurements: Algorithm and Evaluation
ICNP '03 Proceedings of the 11th IEEE International Conference on Network Protocols
Computer Networking: A Top-Down Approach Featuring the Internet
Computer Networking: A Top-Down Approach Featuring the Internet
Packet-Pair Bandwidth Estimation: Stochastic Analysis of a Single Congested Node
ICNP '04 Proceedings of the 12th IEEE International Conference on Network Protocols
IEEE/ACM Transactions on Networking (TON)
FlowMate: scalable on-line flow clustering
IEEE/ACM Transactions on Networking (TON)
A hierarchical characterization of a live streaming media workload
IEEE/ACM Transactions on Networking (TON)
Human-computer network interaction: delay effects and its mediators
Human-computer network interaction: delay effects and its mediators
Geographic locality of IP prefixes
IMC '05 Proceedings of the 5th ACM SIGCOMM conference on Internet Measurement
IEEE Communications Magazine
Evaluation and characterization of available bandwidth probing techniques
IEEE Journal on Selected Areas in Communications
TCP Vegas: end to end congestion avoidance on a global Internet
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
The initial start-up performance of TCP largely depends on two parameters -ssthresh and cwnd. When these values are not accurate, TCP cannot utilize the bandwidth fully or may generate multiple packet drops. Unfortunately, estimating these parameters are not easy, since little network state information is available for the TCP connection initially. From earlier research, a TCP parameter of a previous connection with the same destination was suggested to be used for a new TCP connection. However, the effectiveness of this method is limited, since the cached parameter of single destination is used. As another attempt, a network monitor was adopted to identify the connections sharing the same subnet, and an averaged parameter of those connections was used for a new TCP connection. In this approach, the overhead of the network monitor may be high. In this paper, fairness of TCP connections sharing the same bottleneck links is considered in obtaining ssthresh and cwnd of a new TCP connection without a network monitor. For evaluation, these parameters are used in simulation with four different slow start strategies, namely, LISS, ISS, MISS, and JS, depending on which parameters are used and whether packet pacing is used. The simulation results show that our estimation method works well for homogeneous and moderately heterogenous environments.