Bayesian packet loss detection for TCP
Abstract
One of TCP's critical tasks is to determine which packets are lost in the network, as a basis for control actions (flow control and packet retransmission). Modern TCP implementations use two mechanisms: timeout, and fast retransmit. Detection via timeout is necessarily a time-consuming operation; fast retransmit, while much quicker, is only effective for a small fraction of packet losses. In this paper we consider the problem of packet loss detection in TCP more generally. We concentrate on the fact that TCP's control actions are necessarily triggered by inference of packet loss, rather than conclusive knowledge. This suggests that one might analyze TCP's packet loss detection in a standard inferencing framework based on probability of detection and probability of false alarm. This paper makes two contributions to that end: first, we study an example of more general packet loss inference, namely optimal Bayesian packet loss detection based on round trip time. We show that for long-lived flows, it is frequently possible to achieve high detection probability and low false alarm probability based on measured round trip time. Second, we construct an analytic performance model that incorporates general packet loss inference into TCP. We show that for realistic detection and false alarm probabilities (as are achievable via our Bayesian detector) and for moderate packet loss rates, the use of more general packet loss inference in TCP can improve throughput by as much as 25%.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
A TCP variant enhanced with the Bayesian packet loss classifier results in a throughput improvement of up to 25% over standard TCP-Reno.
“resulting in a throughput improvement of up to 25% over the standard TCP-Reno.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [150]
Performance is superior for the BU dataset due to poor quality of RTT measurements in the PMA dataset.
“The performance is superior for the BU dataset due to the poor quality of RTT measurements in the PMA dataset.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [150]
Cites
Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A., & Rubin, D. B. (2013) · doi:10.1201/b16018 · Cited by 27,276 · see citing works
Padhye, J. D., Firoiu, V., Towsley, D., & Kurose, J. (1998) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/285237.285291 · Cited by 2,107 · see citing works
The macroscopic behavior of the TCP congestion avoidance algorithm
Mathis, M., Semke, J., Mahdavi, J., & Ott, T. J. (1997) · ACM SIGCOMM Computer Communication Review · doi:10.1145/263932.264023 · Cited by 1,496 · see citing works
The NewReno Modification to TCP's Fast Recovery Algorithm
Henderson, T., Floyd, S., Gurtov, A., & Nishida, Y. (2012) · doi:10.17487/rfc6582 · Cited by 1,410 · see citing works
Brakmo, L. S., O'Malley, S. W., & Peterson, L. (1994) · ACM SIGCOMM Computer Communication Review · doi:10.1145/190809.190317 · Cited by 1,203 · see citing works
Simulation-based comparisons of Tahoe, Reno and SACK TCP
Fall, K., & Floyd, S. (1996) · ACM SIGCOMM Computer Communication Review · doi:10.1145/235160.235162 · Cited by 1,150 · see citing works
End-to-end Internet packet dynamics
Paxson, V. (1999) · IEEE/ACM Transactions on Networking · doi:10.1109/90.779192 · Cited by 912 · see citing works
Computing TCP's Retransmission Timer
Paxson, V., Allman, M. C., Chu, J., & Sargent, M. (2011) · doi:10.17487/rfc6298 · Cited by 826 · see citing works
End-to-end packet delay and loss behavior in the internet
Bolot, J.-C. (1993) · doi:10.1145/166237.166265 · Cited by 729 · see citing works
Brakmo, L. S., O'Malley, S. W., & Peterson, L. (1994) · doi:10.1145/190314.190317 · Cited by 698 · see citing works
The NewReno Modification to TCP's Fast Recovery Algorithm
Floyd, S., & Henderson, T. (1999) · doi:10.17487/rfc2582 · Cited by 632 · see citing works
Measurements and analysis of end-to-end Internet dynamics
Lawrence Berkeley National Lab. (LBNL), B., & Paxson, V. (1997) · doi:10.2172/551971 · Cited by 572 · see citing works
Packet reordering is not pathological network behavior
Bennett, J. C. R., Partridge, C., & Shectman, N. (1999) · IEEE/ACM Transactions on Networking · doi:10.1109/90.811445 · Cited by 403 · see citing works
Ludwig, R., & Katz, R. H. (2000) · ACM SIGCOMM Computer Communication Review · doi:10.1145/505688.505692 · Cited by 393 · see citing works
The NewReno Modification to TCP's Fast Recovery Algorithm
Floyd, S., Henderson, T., & Gurtov, A. (2004) · doi:10.17487/rfc3782 · Cited by 335 · see citing works
On making TCP more robust to packet reordering
Blanton, E., & Allman, M. (2002) · ACM SIGCOMM Computer Communication Review · doi:10.1145/510726.510728 · Cited by 257 · see citing works
Improving TCP performance over mobile ad-hoc networks with out-of-order detection and response
Wang, F., & Zhang, Y. (2002) · doi:10.1145/513800.513827 · Cited by 230 · see citing works
In search of path diversity in ISP networks
Teixeira, R., Marzullo, K., Savage, S., & Voelker, G. M. (2003) · ACM Internet Measurement Conference (IMC) · doi:10.1145/948205.948247 · Cited by 156 · see citing works
Variability in TCP round-trip times
Aikat, J., Kaur, J., Smith, F. D., & Kevin Jeffay, B. (2003) · ACM Internet Measurement Conference (IMC) · doi:10.1145/948205.948241 · Cited by 153 · see citing works
Sarolahti, P., Kojo, M., & Raatikainen, K. E. E. (2003) · ACM SIGCOMM Computer Communication Review · doi:10.1145/956981.956987 · Cited by 112 · see citing works
TCP in wired-cum-wireless environments
Pentikousis, K. (2000) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2000.5340805 · Cited by 109 · see citing works
End-to-End Inference of Loss Nature in a Hybrid Wired/Wireless Environment
Liu, J., Matta, I., & Crovella, M. E. (2002) · Cited by 90 · see citing works
Self-citationEffectiveness of loss labeling in improving TCP performance in wired/wireless networks
Barman, D., & Matta, I. (2003) · Proceedings/Proceedings - International Conference on Network Protocols · doi:10.1109/icnp.2002.1181381 · Cited by 82 · see citing works
TCP-PR: TCP for persistent packet reording
Bohacek, S. K., Hespanha, J. P., Lee, J., Lim, C., & Obraczka, K. (2004) · Proceedings of the ... International Conference on Distributed Computing Systems/Proceedings of the International Conference on Distributed Computing Systems · doi:10.1109/icdcs.2003.1203469 · Cited by 64 · see citing works
Measurement and classification of out-of-sequence packets in a tier-1 IP backbone
Jaiswal, S. K., Iannaccone, G., Diot, C., Kurose, J., & Towsley, D. (2003) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infcom.2003.1208956 · Cited by 51 · see citing works
Is the round-trip time correlated with the number of packets in flight?
Biaz, S., & Vaidya, N. H. (2003) · doi:10.1145/948205.948240 · Cited by 47 · see citing works
Measurement and classification of out-of-sequence packets in a tier-1 IP backbone
Jaiswal, S. K., Iannaccone, G., Diot, C., Kurose, J., & Towsley, D. (2002) · ACM SIGCOMM Internet Measurement Workshop (IMW) · doi:10.1145/637201.637218 · Cited by 43 · see citing works
Flagged first, then by citations
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
When machine learning meets congestion control: A survey and comparison
Jiang, H., Li, Q., Jiang, Y., Shen, G., Sinnott, R., Tian, C., & Xu, M. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.108033 · Cited by 107 · see citing works
In-Network Machine Learning Using Programmable Network Devices: A Survey
Zheng, C., Hong, X., Ding, D., Vargaftik, S., Ben-Itzhak, Y., & Zilberman, N. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3344351 · Cited by 90 · see citing works
Passive analysis of TCP anomalies
Mellia, M., Meo, M., Muscariello, L., & Rossi, D. (2008) · Computer Networks · doi:10.1016/j.comnet.2008.05.010 · Cited by 55 · see citing works
Leveraging Internet Background Radiation for Opportunistic Network Analysis
Benson, K., Dainotti, A., claffy, K., Snoeren, A. C., & Kallitsis, M. (2015) · ACM Internet Measurement Conference (IMC) · doi:10.1145/2815675.2815702 · Cited by 44 · see citing works
A Performance Study of Loss Detection/Recovery in Real-world TCP Implementations
Rewaskar, S., Kaur, J., & Smith, F. D. (2007) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp.2007.4375856 · Cited by 30 · see citing works
Gaining insight into AS-level outages through analysis of Internet Background Radiation
Benson, K., Dainotti, A., claffy, K., & Aben, E. (2013) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infcomw.2013.6562915 · Cited by 22 · see citing works
End-to-end packet-channel Bayesian model applied to heterogeneous wireless networks
Iannello, G., Palmieri, F., Pescapè, A., & Rossi, P. S. (2005) · Globecom · doi:10.1109/glocom.2005.1577673 · Cited by 21 · see citing works
LossDetection: Real-Time Packet Loss Monitoring System for Sampled Traffic Data
Wu, H., Liu, Y., Ni, S., Cheng, G., & Hu, X. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3203389 · Cited by 17 · see citing works
Gaining insight into AS-level outages through analysis of internet background radiation
Benson, K., Dainotti, A., claffy, K., & Aben, E. (2012) · ACM CoNEXT Student Workshop · doi:10.1145/2413247.2413285 · Cited by 11 · see citing works
Gaining insight into AS-level outages through analysis of Internet background radiation
Benson, K., Dainotti, A., claffy, K., & Aben, E. (2013) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infcom.2013.6567183 · Cited by 7 · see citing works
TCP with Machine Learning - Advances and Opportunities
Molia, H. K. (2019) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2019/132862019 · Cited by 3 · see citing works
A lightweight, high performance communication protocol for grid computing
Dickens, P. M. (2009) · Cluster Computing · doi:10.1007/s10586-009-0107-x · Cited by 3 · see citing works
Appropriateness of Machine Learning Techniques for TCP with MANETs
Molia, H. K., & Kothari, A. D. (2020) · Lecture notes in networks and systems · doi:10.1007/978-981-15-3325-9_39 · Cited by 3 · see citing works
Towards real-time performance monitoring for encrypted traffic
Kharrazi, M., Sen, S. B., & Spatscheck, O. (2007) · IEEE Internet Network Management Workshop · doi:10.1145/1321753.1321769 · Cited by 2 · see citing works
Identifying Network Congestion on SDN-Based Data Centers with Supervised Classification
de Oliveira, F. D. S., Pillon, M. A., Miers, C. C., & Koslovski, G. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-28451-9_20 · Cited by 2 · see citing works
Framework for Real-Time Monitoring of Packet Loss Caused by Network Congestion
He, X., He, Z., Li, W., Liu, G., & Wei, X. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3578056 · Cited by 1 · see citing works
Bayesian piggyback control for improving real-time communication quality
Xiao, W.-C., & Chen, K.-T. (2011) · IEEE International Workshop Technical Committee on Communications Quality and Reliability (CQR) · doi:10.1109/cqr.2011.5996080 · Cited by 1 · see citing works
Improving TCP Performance with Intelligent Loss Differentiation for Mobile Adhoc Networks
Molia, H. K. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/312942020 · Cited by 1 · see citing works
Short Segment Cumulative Modeling Algorithm for Markovian Model on Packet Loss
Amro, I. (2013) · International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC) · doi:10.1109/3pgcic.2013.125
Dynamic Estimation Algorithm for Markovian Model for Packet Loss
Amro, I. (2013) · EUROSIM Congress on Modelling and Simulation (EUROSIM) · doi:10.1109/eurosim.2013.106
Markovian Model for Packet Loss in EUMEDConnect Network
Amro, I. (2013) · International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN) · doi:10.1109/cicsyn.2013.54
Loss differentiation algorithms in heterogeneous networks
Su, J. (2011) · International Conference on Electric Information and Control Engineering · doi:10.1109/iceice.2011.5778119
An Adaptive Loss Differentiation Algorithm Based on Queue Management
Ye, J., Wang, J., & Liu, H. (2006) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct.2006.341917
Glisic, S., & Lorenzo, B. (2022) · Wiley eBooks · doi:10.1002/9781119790327.ch7
Methods of Congestion Control in Wired Networks with Reinforcement Learning – A Review
Lakshmi, M. J., & Arrama, M. B. (2022) · International Conference on Innovative Practices in Technology and Management (ICIPTM) · doi:10.1109/iciptm54933.2022.9753983
Genetic Improvement of TCP Congestion Avoidance
Carbognin, A., Custode, L. L., & Iacca, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-21094-5_9
- Authors
- I'onseca, N., & Crovella, M.
- Affiliations
- Boston University (US)
- ORCID
- Crovella, M.
- Venue
- Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies.
- Publisher
- IEEE
- Published
- 2005-08-24
- Volume
- 3
- Pages
- 1826-1837
- OpenAlex
- W2145246546
- Cited by
- 27
- References
- 27
- Citations by year
- 2025: 1 · 2023: 2 · 2022: 4 · 2021: 1 · 2020: 2 · 2019: 1 · 2018: 1 · 2015: 1 · 2013: 5 · 2012: 1
- FWCI
- 0.96
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Conference on Computer Communications (INFOCOM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Traffic and Congestion Control
- Physical Sciences › Computer Science › Computer Networks and Communications › Wireless Networks and Protocols
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- TCP, packet loss detection, Bayesian detection, round-trip time, detection probability, false alarm probability, fast retransmit, TCP timeout, flow control, packet retransmission, throughput, analytical performance model
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
