Journal article
IEEE Transactions on Control of Network Systems, vol. 8(2), 2021 Jun, pp. 859--871
APA
Click to copy
Teymoori, P., Hayes, D. A., Welzl, M., & Gjessing, S. (2021). Estimating an Additive Path Cost With Explicit Congestion Notification. IEEE Transactions on Control of Network Systems, 8(2), 859–871. https://doi.org/10.1109/TCNS.2021.3053179
Chicago/Turabian
Click to copy
Teymoori, P., D. A. Hayes, M. Welzl, and S. Gjessing. “Estimating an Additive Path Cost With Explicit Congestion Notification.” IEEE Transactions on Control of Network Systems 8, no. 2 (June 2021): 859–871.
MLA
Click to copy
Teymoori, P., et al. “Estimating an Additive Path Cost With Explicit Congestion Notification.” IEEE Transactions on Control of Network Systems, vol. 8, no. 2, June 2021, pp. 859–71, doi:10.1109/TCNS.2021.3053179.
BibTeX Click to copy
@article{p2021a,
title = {Estimating an Additive Path Cost With Explicit Congestion Notification},
year = {2021},
month = jun,
issue = {2},
journal = {IEEE Transactions on Control of Network Systems},
pages = {859--871},
volume = {8},
doi = {10.1109/TCNS.2021.3053179},
author = {Teymoori, P. and Hayes, D. A. and Welzl, M. and Gjessing, S.},
month_numeric = {6}
}
Network utility maximization is a well-accepted theoretical framework that describes how congestion controls cooperate to achieve an ideal sending rate allocation, for given utility functions of senders and constraints of the network. These network constraints are expressed as a “cost” in the framework. In practice, most congestion control mechanisms obtain feedback that is different from the framework's “cost.” This article focuses on explicit congestion notification (ECN), which has been shown to be advantageous when it is available, e.g., with the popular datacenter transmission control protocol mechanism. However, different from the framework's cost, ECN marks are not additive. We present a practical solution to this problem; it changes how end hosts interpret the ECN signal, while for routers, a special configuration of random early detection is used.