Transmission control protocol (TCP) Vegas detects
network congestion in the early stage and successfully prevents
periodic packet loss that usually occurs in TCP Reno. It has been
demonstrated that TCP Vegas outperforms TCP Reno in many
aspects. However, TCP Vegas suffers several problems that affect its
congestion avoidance mechanism. One of the most important
weaknesses in TCP Vegas is that alpha and beta depend on a good
expected throughput estimate, which as we have seen, depends on a
good minimum RTT estimate. In order to make the system more
robust alpha and beta must be made responsive to network conditions
(they are currently chosen statically). This paper proposes a modified
Vegas algorithm, which can be adjusted to present good performance
compared to other transmission control protocols (TCPs). In order to
do this, we use PSO algorithm to tune alpha and beta. The simulation
results validate the advantages of the proposed algorithm in term of
performance.
[1] V. Jacobson, Congestion avoidance and control, in: ACM
SIGCOMM_88, Stanford, CA, 1988, pp. 314-329.
[2] L.S. Brakmo, L.L. Peterson, TCP Vegas: end to end congestion
avoidance on a global Internet, IEEE J. Select. Areas Commun. 13 (8)
(1995) 1465-1480.
[3] T. Bonald,Comparison of TCP Reno and TCP Vegas via fluid
approximation, Tech. Rep. RR, 3563, 1998.
[4] J. Mo, R.J. La, V. Anantharam, J.C. Walrand, Analysis and comparison
of TCP Reno and Vegas, in: INFOCOM, vol. 3, 1999, pp. 1556-1563.
[5] S.H. Low, L.L. Peterson, L. Wang, Understanding Vegas: a duality
model, J. ACM 49 (2002) 207-235.
[6] E. H. Miller, "A note on reflector arrays (Periodical styleÔÇöAccepted for
publication)," IEEE Trans. Antennas Propagat., to be published.
[7] J. Wang, "Fundamentals of erbium-doped fiber amplifiers arrays
(Periodical styleÔÇöSubmitted for publication)," IEEE J. Quantum
Electron., submitted for publication.
[8] R. Eberhart, and J. Kennedy, "A New Optimizer Using Particles Swarm
Theory, Proc. Sixth International Symposium on Micro Machine and
Human Science , IEEE Service Center, Piscataway, NJ, 39-43, 1995.
[9] J. Kennedy and R. Eberhart, Particle Swarm Optimization, IEEE
International Conference on Neural Networks NJ, IV: 1942-1948, 1995.
[10] Y. Shi, R. Eberhart, Parameter Selection in Particle Swarm
Optimization, The 7th Annual Conference on Evolutionary
Programming, San Diego, USA, 1998.
[11] Ns-2.Network Simulator. http://www.isi.edu/nsnam/ns.
[1] V. Jacobson, Congestion avoidance and control, in: ACM
SIGCOMM_88, Stanford, CA, 1988, pp. 314-329.
[2] L.S. Brakmo, L.L. Peterson, TCP Vegas: end to end congestion
avoidance on a global Internet, IEEE J. Select. Areas Commun. 13 (8)
(1995) 1465-1480.
[3] T. Bonald,Comparison of TCP Reno and TCP Vegas via fluid
approximation, Tech. Rep. RR, 3563, 1998.
[4] J. Mo, R.J. La, V. Anantharam, J.C. Walrand, Analysis and comparison
of TCP Reno and Vegas, in: INFOCOM, vol. 3, 1999, pp. 1556-1563.
[5] S.H. Low, L.L. Peterson, L. Wang, Understanding Vegas: a duality
model, J. ACM 49 (2002) 207-235.
[6] E. H. Miller, "A note on reflector arrays (Periodical styleÔÇöAccepted for
publication)," IEEE Trans. Antennas Propagat., to be published.
[7] J. Wang, "Fundamentals of erbium-doped fiber amplifiers arrays
(Periodical styleÔÇöSubmitted for publication)," IEEE J. Quantum
Electron., submitted for publication.
[8] R. Eberhart, and J. Kennedy, "A New Optimizer Using Particles Swarm
Theory, Proc. Sixth International Symposium on Micro Machine and
Human Science , IEEE Service Center, Piscataway, NJ, 39-43, 1995.
[9] J. Kennedy and R. Eberhart, Particle Swarm Optimization, IEEE
International Conference on Neural Networks NJ, IV: 1942-1948, 1995.
[10] Y. Shi, R. Eberhart, Parameter Selection in Particle Swarm
Optimization, The 7th Annual Conference on Evolutionary
Programming, San Diego, USA, 1998.
[11] Ns-2.Network Simulator. http://www.isi.edu/nsnam/ns.
@article{"International Journal of Information, Control and Computer Sciences:51079", author = "Sh. Jamali and A. Eftekhari", title = "SMCC: Self-Managing Congestion Control Algorithm", abstract = "Transmission control protocol (TCP) Vegas detects
network congestion in the early stage and successfully prevents
periodic packet loss that usually occurs in TCP Reno. It has been
demonstrated that TCP Vegas outperforms TCP Reno in many
aspects. However, TCP Vegas suffers several problems that affect its
congestion avoidance mechanism. One of the most important
weaknesses in TCP Vegas is that alpha and beta depend on a good
expected throughput estimate, which as we have seen, depends on a
good minimum RTT estimate. In order to make the system more
robust alpha and beta must be made responsive to network conditions
(they are currently chosen statically). This paper proposes a modified
Vegas algorithm, which can be adjusted to present good performance
compared to other transmission control protocols (TCPs). In order to
do this, we use PSO algorithm to tune alpha and beta. The simulation
results validate the advantages of the proposed algorithm in term of
performance.", keywords = "Self-managing, Congestion control, TCP.", volume = "3", number = "9", pages = "2173-4", }