A machine learning framework for TCP round-trip time estimation
Open accessAbstract
In this paper, we explore a novel approach to end-to-end round-trip time (RTT) estimation using a machine-learning technique known as the experts framework. In our proposal, each of several ‘experts’ guesses a fixed value. The weighted average of these guesses estimates the RTT, with the weights updated after every RTT measurement based on the difference between the estimated and actual RTT. Through extensive simulations, we show that the proposed machine-learning algorithm adapts very quickly to changes in the RTT. Our results show a considerable reduction in the number of retransmitted packets and an increase in goodput, especially in more heavily congested scenarios. We corroborate our results through ‘live’ experiments using an implementation of the proposed algorithm in the Linux kernel. These experiments confirm the higher RTT estimation accuracy of the machine learning approach which yields over 40% improvement when compared against both standard transmission control protocol (TCP) as well as the well known Eifel RTT estimator. To the best of our knowledge, our work is the first attempt to use on-line learning algorithms to predict network performance and, given the promising results reported here, creates the opportunity of applying on-line learning to estimate other important network variables.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Several ML-based approaches have addressed limitations of inferring congestion by estimating throughput, RTT, and mobility in TCP-based networks, table entries rate in NDNs, and congestion level in DTNs.
“For the aforementioned reasons, several ML-based approaches have addressed the limitations of inferring the congestion in various network architectures by estimating different network parameters: throughput [238, 316, 371], RTT [22,128], and mobility [309] in TCP-based networks, table entries rate in NDNs [230], and congestion level in DTNs [412].”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [22]
For synthetic data, Fixed-Share Experts provide a lower prediction error in comparison to real data even with a higher tick value of 500ms.
“For synthetic data, Fixed-Share Experts provide a lower prediction error in comparison to real data even with a higher tick value of 500ms.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [22]
On real data, SENSE achieves a lower prediction error than Fixed-Share Experts for predicting RTT.
“The results on real data show that SENSE achieves a lower prediction error-measured in ticks of 4ms-than Fixed-Share Experts for predicting RTT.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [22]
SENSE requires more computational resources than Fixed-Share Experts due to the adoption of EWMA as experts and the meta-learning step.
“In terms of complexity, it is important to mention that SENSE requires more computational resources than Fixed-Share Experts, due to the adoption of EWMA as experts and the meta-learning step.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [22]
TCP, as well as some multicast and multipath protocols, infer the congestion state from estimated network parameters such as RTT and throughput to adapt their behavior.
“TCP, as well as some multicast and multipath protocols, infer the congestion state from estimated network parameters (e.g.RTT and throughput) to adapt their behavior.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [22]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Ad-hoc on-demand distance vector routing
Perkins, C. E., & Royer, E. M. (1999) · doi:10.1109/mcsa.1999.749281 · Cited by 10,338 · see citing works
Congestion avoidance and control
Jacobson, V. L. (1995) · ACM SIGCOMM Computer Communication Review · doi:10.1145/205447.205462 · Cited by 5,306 · see citing works
Mobility increases the capacity of ad hoc wireless networks
Grossglauser, M., & Tse, D. N. C. (2002) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2002.801403 · Cited by 2,882 · see citing works
IEEE Standard for Binary Floating Point Arithmetic
Ieee, A. (1985) · Medical Entomology and Zoology · Cited by 886 · see citing works
Herbster, M., & Warmuth, M. K. (1998) · Machine Learning · doi:10.1023/a:1007424614876 · Cited by 559 · see citing works
On estimating end-to-end network path properties
Allman, M. C., & Paxson, V. (1999) · doi:10.1145/316188.316230 · Cited by 344 · see citing works
Cruz, R. L., & Varghese, G. (2001) · Cited by 240 · see citing works
A dynamic disk spin-down technique for mobile computing
Helmbold, D. P., Long, D. D. E., & Sherrod, B. (1996) · Proceedings of the 28th Annual International Conference on Mobile Computing And Networking · doi:10.1145/236387.236423 · Cited by 213 · see citing works
Improving round-trip time estimates in reliable transport protocols
Karn, P., & Partridge, C. (1991) · ACM Transactions on Computer Systems · doi:10.1145/118544.118549 · Cited by 179 · see citing works
Computer arithmetic systems: algorithms, architecture and implementation
Omondi, A. R. (1994) · Prentice Hall International (UK) Ltd. eBooks · Cited by 137 · see citing works
Tracking a Small Set of Experts by Mixing Past Posteriors
Bousquet, O., & Warmuth, M. K. (2001) · Lecture notes in computer science · doi:10.1007/3-540-44581-1_3 · Cited by 123 · see citing works
A machine learning approach to TCP throughput prediction
Mirza, M., Sommers, J., Barford, P., & Zhu, X. (2007) · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · doi:10.1145/1254882.1254894 · Cited by 109 · see citing works
Optimizing qos routing in hierarchical atm networks using computational intelligence techniques
Vasilakos, A. V., Saltouros, M. P., Atlassis, A. F., et al. (2003) · IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) · doi:10.1109/tsmcc.2003.817354 · Cited by 105 · see citing works
The Eifel retransmission timer
Ludwig, R., & Sklower, K. (2000) · ACM SIGCOMM Computer Communication Review · doi:10.1145/382179.383014 · Cited by 76 · see citing works
The use of learning algorithms in ATM networks call admission control problem: a methodology
Atlasis, A. F., Loukas, N., & Vasilakos, A. V. (2000) · Computer Networks · doi:10.1016/s1389-1286(00)00090-6 · Cited by 55 · see citing works
A machine learning approach to TCP throughput prediction
Mirza, M., Sommers, J., Barford, P., & Zhu, X. (2007) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/1269899.1254894 · Cited by 48 · see citing works
TCP Retransmission Timeout Algorithm Using Weighted Medians
Ma, L., Arce, G. R., & Barner, K. E. (2004) · IEEE Signal Processing Letters · doi:10.1109/lsp.2004.827957 · Cited by 30 · see citing works
TCP Throughput Adaptation in WiMax Networks Using Replicator Dynamics
Αναστασόπουλος, Μ., Petraki, D. K., Kannan, R., et al. (2010) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2009.2036148 · Cited by 29 · see citing works
Methods to improve TCP throughput in wireless networks with high delay variability
Leung, K. K., Klein, T. E., Mooney, C., et al. (2005) · IEEE Vehicular Technology Conference (VTC-Fall) · doi:10.1109/vetecf.2004.1400614 · Cited by 20 · see citing works
Estimation of SRTT using techniques from the practice of SPC and change detection algorithms
Ngwenya, D. W., & Hancke, G. P. (2005) · IEEE AFRICON · doi:10.1109/africon.2004.1406702 · Cited by 6 · see citing works
TCP retransmission timer adjustment mechanism using model-based RTT predictor
Haeri, ء., & Rad, A. H. M. (2004) · Cited by 5 · see citing works
Adaptive timer-based TCP control algorithm for wireless system
Lou, W., & Huang, C. (2005) · doi:10.1109/wirles.2005.1549538 · Cited by 4 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- IW Group, Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specification. IEEE Std. 802.11, 345 E. 47th St, New York, NY 10017. (IEEE Computer Society, USA, 1997)
Cited by
Sorted by citations
Boutaba, R., Salahuddin, M. A., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F., & Caicedo, O. M. (2018) · Journal of Internet Services and Applications · doi:10.1186/s13174-018-0087-2 · Cited by 1,036 · see citing works
CS2P: Improving Video Bitrate Selection and Adaptation with Data-Driven Throughput Prediction
Sun, Y., Yin, X., Jiang, J., Sekar, V., Lin, F., Wang, N., Liu, T., & Sinopoli, B. (2016) · Proceedings of the 2016 ACM SIGCOMM Conference · doi:10.1145/2934872.2934898 · Cited by 407 · see citing works
Smart Experts for Network State Estimation
Edalat, Y., Ahn, J.-S., & Obraczka, K. (2016) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2016.2586506 · Cited by 27 · see citing works
Self-citationSmart Congestion Control for Delay- and Disruption Tolerant Networks
Silva, A. P., Obraczka, K., Burleigh, S., & Hirata, C. M. (2016) · 2016 13th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/sahcn.2016.7733018 · Cited by 20 · see citing works
Self-citation
- Authors
- Arouche Nunes, B. A., Veenstra, K., Ballenthin, W., Lukin, S., & Obraczka, K.
- Affiliations
- University of California, Santa Cruz (US)
- Columbia University (US)
- Loyola University Maryland (US)
- Venue
- EURASIP Journal on Wireless Communications and Networking
- Published
- 2014-03-26
- Volume
- 2014
- Issue
- 1
- ISSN
- 1687-1472 (ISSN-L)
- 1687-1499
- OpenAlex
- W2163905250
- Cited by
- 43
- References
- 22
- Citations by year
- 2025: 1 · 2024: 5 · 2023: 4 · 2022: 8 · 2021: 5 · 2020: 4 · 2019: 7 · 2018: 3 · 2017: 2 · 2016: 3 · 2014: 1
- FWCI
- 2.30
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- EURASIP Journal on Wireless Communications and Networking (publishedVersion, cc-by)
- Funders
- National Science Foundation
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (DF 70.040–020)
- Multidisciplinary University Research Initiative
- Army Research Office
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Traffic and Congestion Control
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Computer Science › Computer Networks and Communications › Wireless Networks and Protocols
- Keywords
- online learning, goodput, network congestion, Linux kernel implementation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
