TCP fusion

Not to be confused with the Oracle Solaris optimization for loopback TCP performance.

TCP Fusion is a proposed congestion control algorithm for the Transmission Control Protocol (TCP) designed to improve quality of service over high-speed and long-distance networks. Primarily studied in research contexts and has contributed to ongoing efforts to design more adaptive and efficient congestion control methods, it combines elements from several earlier TCP variants to better adapt to varying network conditions, achieving higher throughput, and improved fairness among flows.[1]

Traditional TCP algorithms, such as TCP Reno, rely primarily on packet loss as a signal of network congestion, which can limit performance in high-bandwidth or high-latency environments. TCP Fusion instead integrates both loss-based and delay-based approaches, drawing on ideas from algorithms like TCP Vegas and TCP Westwood. By monitoring network delay as well as packet loss, it aims to detect congestion earlier and adjust transmission rates more smoothly.[2]

TCP-Fusion’s tuning for low-latency, high-bandwidth terrestrial links limits its effectiveness over satellite Internet.[3]

References

  1. ^ Kaneko, Kazumi; Fujikawa, Tomoki; Su, Zhou; Katto, Jiro (2007). "TCP-Fusion: A hybrid congestion control algorithm for high-speed networks". Proceedings of PFLDnet 2007 (PDF). Vol. 7. pp. 31–36.
  2. ^ Katto, Jiro; Ogura, Kazumine; Fujikawa, Tomoki; Kaneko, Kazumi; Su, Zhou (2008). "On Hybrid TCP Congestion Control". Proceedings of ICCCS, TCP (PDF).
  3. ^ Obata, Hiroyasu; Nishimoto, Shingo; Ishida, Kenji (2009). "TCP congestion control method of improving friendliness over satellite Internet". 2009 7th International Conference on Information, Communications and Signal Processing (ICICS). IEEE. pp. 1–4. doi:10.1109/ICICS.2009.5397708.
This article is issued from Wikipedia. The text is available under Creative Commons Attribution-Share Alike 4.0 unless otherwise noted. Additional terms may apply for the media files.