Smart Experts for Network State Estimation
Abstract
Several network protocols, services, and applications adjust their operation dynamically based on current network conditions. Consequently, keeping accurate estimates of the network and its performance as it fluctuates over time is critical. For example, both TCP and IEEE 802.11 periodically adapt some of their key operating parameters, namely, the retransmission timeout and the contention window size based on the average round trip time and the number of collisions, respectively. In this paper, we present a novel mechanism to estimate “near-future” network performance based on past network conditions. We call our approach to network performance estimation as smart experts for network state estimation (SENSE). SENSE uses a simple, yet effective, algorithm combining a machine learning method known as fixed-share with exponentially weighted moving average (EWMA). SENSE also introduces novel techniques that improve the predictability of the fixed-share framework without increasing computational complexity. SENSE is thus able to respond to network dynamics at different time scales, i.e., long- and medium-term fluctuations as well as short-lived variations. We evaluate SENSE's performance using synthetic and real datasets. Our experimental results show that, when compared to fixed-share and EWMA, SENSE yields higher estimation accuracy for all datasets due to its ability to more closely track data fluctuations.
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?
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 [128]
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 [128]
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 [128]
Cites
A tutorial on support vector regression
Smola, A. J., & Schölkopf, B. (2004) · Statistics and Computing · doi:10.1023/b:stco.0000035301.49549.88 · Cited by 13,482 · see citing works
Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J., & Scholkopf, B. (1998) · IEEE Intelligent Systems and their Applications · doi:10.1109/5254.708428 · Cited by 7,243 · 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
The Exponentially Weighted Moving Average
Hunter, J. S. (1986) · Journal of Quality Technology · doi:10.1080/00224065.1986.11979014 · Cited by 1,156 · see citing works
Learning in Artificial Neural Networks: A Statistical Perspective
White, H. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.425 · Cited by 920 · see citing works
Cesa‐Bianchi, N., Freund, Y., Haussler, D. H., Helmbold, D. P., Schapire, R. E., & Warmuth, M. K. (1997) · Journal of the ACM · doi:10.1145/258128.258179 · Cited by 617 · see citing works
Herbster, M., & Warmuth, M. K. (1998) · Machine Learning · doi:10.1023/a:1007424614876 · Cited by 559 · see citing works
The weighted majority algorithm
Littlestone, N., & Warmuth, M. K. (1989) · 30th Annual Symposium on Foundations of Computer Science · doi:10.1109/sfcs.1989.63487 · Cited by 295 · see citing works
Kim, M., & Noble, B. D. (2001) · Proceedings of the 28th Annual International Conference on Mobile Computing And Networking · doi:10.1145/381677.381705 · Cited by 171 · see citing works
On the predictability of large transfer TCP throughput
He, Q., Dovrolis, C., & Ammar, M. (2005) · ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM) · doi:10.1145/1080091.1080110 · Cited by 163 · see citing works
Adaptive disk spin‐down for mobile computers
Helmbold, D. P., Long, D. D. E., Sconyers, T. L., & Sherrod, B. (2000) · Mobile Networks and Applications · doi:10.1023/a:1019129116852 · Cited by 116 · 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
Characterizing and Predicting TCP Throughput on the Wide Area Network
Dong, L., Qiao, Y., Dinda, P. A., & Bustamante, F. E. (2005) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2005.17 · Cited by 75 · see citing works
On the predictability of large transfer TCP throughput
He, Q., Dovrolis, C., & Ammar, M. (2005) · ACM SIGCOMM Computer Communication Review · doi:10.1145/1090191.1080110 · Cited by 73 · see citing works
A Closer Look at Adaptive Regret
Adamskiy, D., Koolen, W. M., Chernov, A., & Vovk, V. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34106-9_24 · Cited by 53 · 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
A machine learning framework for TCP round-trip time estimation
Arouche Nunes, B. A., Veenstra, K., Ballenthin, W., Lukin, S., & Obraczka, K. (2014) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/1687-1499-2014-47 · Cited by 43 · see citing works
Self-citationGannoune, L., & Robert, S. (2005) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc.2004.1370885 · Cited by 31 · see citing works
Local Estimation of Probabilities of Direct and Staggered Collisions in 802.11 WLANs
Krishnan, M. N., Pollin, S., & Zakhor, A. (2009) · IEEE Global Telecommunications Conference (GLOBECOM) · doi:10.1109/glocom.2009.5425306 · Cited by 28 · see citing works
Throughput Improvement in 802.11 WLANs Using Collision Probability Estimates in Link Adaptation
Krishnan, M. N., & Zakhor, A. (2010) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc.2010.5506155 · Cited by 22 · see citing works
Gannoune, L., & Robert, S. (2004) · Cited by 19 · see citing works
Collision-free medium access based on traffic forecasting
Petkov, V., & Obraczka, K. (2012) · IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) · doi:10.1109/wowmom.2012.6263687 · Cited by 16 · see citing works
Self-citationNetwork State Estimation Using Smart Experts
Ahn, J.-S., Edalat, Y., & Obraczka, K. (2014) · International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous) · doi:10.4108/icst.mobiquitous.2014.257949 · Cited by 4 · see citing works
Self-citation
Flagged first, then by citations
1 of the 24 references couldn’t be matched to a known paper.
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
Bian, K., & Priyadarshi, R. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-024-10110-w · Cited by 139 · 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
SDATP: An SDN-Based Traffic-Adaptive and Service-Oriented Transmission Protocol
Chen, J., Ye, Q. J., Quan, W., Yan, S., Do, P. T., Yang, P., Zhuang, W., Shen, X., Li, X., & Rao, J. B. (2019) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2019.2963149 · Cited by 27 · see citing works
A Multiscale Algorithm for Joint Forecasting–Scheduling to Solve the Massive Access Problem of IoT
Rodoplu, V., Nakıp, M., Eliiyi, D. T., & Guzelis, C. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2992391 · Cited by 26 · see citing works
Comparative Study of Forecasting Schemes for IoT Device Traffic in Machine-to-Machine Communication
Nakıp, M., Gül, B. C., Rodoplu, V., & Guzelis, C. (2019) · International Conference on Cloud Computing and Internet of Things (CCIOT) · doi:10.1145/3361821.3361833 · Cited by 21 · see citing works
Dynamically Tuning IEEE 802.11's Contention Window Using Machine Learning
Edalat, Y., & Obraczka, K. (2019) · ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM) · doi:10.1145/3345768.3355920 · Cited by 19 · see citing works
Self-citationJoint Forecasting-Scheduling for the Internet of Things
Nakıp, M., Rodoplu, V., Guzelis, C., & Eliiyi, D. T. (2019) · doi:10.1109/gciot47977.2019.9058408 · Cited by 18 · see citing works
Diffusion Analysis Improves Scalability of IoT Networks to Mitigate the Massive Access Problem
Erol Gelenbe, A., Nakıp, M., Marek, D., & Czachórski, T. (2021) · Proceedings - International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems · doi:10.1109/mascots53633.2021.9614289 · Cited by 18 · see citing works
Multi-Channel Joint Forecasting-Scheduling for the Internet of Things
Rodoplu, V., Nakıp, M., Qorbanian, R., & Eliiyi, D. T. (2020) · IEEE Access · doi:10.1109/access.2020.3038358 · Cited by 17 · see citing works
IoT Traffic Shaping and the Massive Access Problem
Erol Gelenbe, A., & Sigman, K. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9839054 · Cited by 14 · see citing works
Wireless Lan Performance Enhancement Using Double Deep Q-Networks
Asaf, K., Khan, B., & Kim, G. (2022) · Applied Sciences · doi:10.3390/app12094145 · Cited by 13 · see citing works
Randomization of Data Generation Times Improves Performance of Predictive IoT Networks
Nakıp, M., & Erol Gelenbe, A. (2021) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot51360.2021.9595819 · Cited by 12 · see citing works
Improving Massive Access to IoT Gateways
Erol Gelenbe, A., Nakıp, M., & Czachórski, T. (2022) · Performance Evaluation · doi:10.1016/j.peva.2022.102308 · Cited by 9 · see citing works
Smart adaptive collision avoidance for IEEE 802.11
Edalat, Y., Obraczka, K., & Ahn, J.-S. (2021) · Ad Hoc Networks · doi:10.1016/j.adhoc.2021.102721 · Cited by 8 · see citing works
Self-citationA machine learning approach for dynamic control of RTS/CTS in WLANs
Edalat, Y., Obraczka, K., & Amiri, B. (2018) · EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous) · doi:10.1145/3286978.3287027 · Cited by 8 · see citing works
Self-citationNakıp, M., Gül, B. C., Rodoplu, V., & Guzelis, C. (2022) · IEEE Access · doi:10.1109/access.2022.3174126 · Cited by 6 · see citing works
A Machine Learning based Approach for Protecting Wireless Networks Against DoS Attacks
Arafat, Y., Yeaser, K. S., Rahman, A., & Dasgupta, A. (2020) · International Conference on Networking, Systems and Security (NSysS) · doi:10.1145/3428363.3428377 · Cited by 5 · see citing works
CSMA/PJ: A Protective Jamming Based MAC Protocol to Harmonize the Long and Short Links
Zhu, S., Zheng, X., Liu, L., & Ma, H. (2022) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2022.3193027 · Cited by 3 · see citing works
Mitigating massive access with Quasi-Deterministic Transmission: Experiments and stationary analysis
Bergquist, J., Erol Gelenbe, A., Nasereddin, M., & Sigman, K. (2025) · Performance Evaluation · doi:10.1016/j.peva.2025.102512 · Cited by 1 · see citing works
Lightweight AI-driven traffic forecasting and shaping for 6G LEO satellite networks
Liang, Y., Dong, M., Xu, X., Ping, D., Li, M., & Zhu, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132226 · Cited by 1 · see citing works
Optimal Rate Control for Latency-constrained High Throughput Big Data Applications
Xiao, Z., Harwood, A., & Rodriguez, M. A. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10021076 · Cited by 1 · see citing works
A Software-Defined Approach to Enabling Network Controllers for Smart Environment Digital Twins
Wu, C., Lai, C., Venkatasubramanian, N., & Hsu, C.-H. (2024) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom62794.2024.00018 · Cited by 1 · see citing works
Transport-Layer Protocol Customization for 5G Core Networks
Ye, Q. J., & Zhuang, W. (2021) · Wireless networks · doi:10.1007/978-3-030-88666-0_4 · Cited by 1 · see citing works
Neural Network based Network Traffic Predictability for IoT Environment
Dept. of Computer Science Engineering, D. U., Seok, M.-S., Dept. of Computer Science Engineering, D. U., & Um, J. (2020) · The International Journal of Internet of Things and its Applications · doi:10.21742/ijiota.2020.4.1.03
Glisic, S., & Lorenzo, B. (2022) · Wiley eBooks · doi:10.1002/9781119790327.ch7
MOSAL: A Subspace-Based Forecasting Algorithm for Throughput Maximization in IoT Networks
Nakıp, M., Helva, A., Guzelis, C., & Rodoplu, V. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3219251
- Authors
- Edalat, Y., Ahn, J.-S., & Obraczka, K.
- Affiliations
- University of California, Santa Cruz (US)
- Dongguk University (KR)
- Venue
- IEEE Transactions on Network and Service Management
- Published
- 2016-09
- Volume
- 13
- Issue
- 3
- Pages
- 622-635
- ISSN
- 1932-4537 (ISSN-L)
- OpenAlex
- W2470009164
- Cited by
- 27
- References
- 24
- Citations by year
- 2025: 2 · 2024: 2 · 2022: 8 · 2021: 5 · 2020: 4 · 2019: 4 · 2018: 2
- FWCI
- 1.89
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Network and Service Management (publishedVersion)
- Funders
- NSF
- CNS (1321151, NRF-2012R1A1A2020051)
- Basic Science Research Program through the National Research Foundation (NRF) funded by Korea’s Ministry of Education, Science and Technology
- 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
- network state estimation, network performance prediction, exponential moving average, IEEE 802.11, retransmission timeout, contention window, round-trip time, collision detection
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
