Cognitive Network Inference through Bayesian Network Analysis
Abstract
Cognitive networking deals with applying cognition to the entire network protocol stack for achieving stack-wide as well as network-wide performance goals, unlike cognitive radios that apply cognition only at the physical layer. Designing a cognitive network is challenging since learning the relationship between network protocol parameters in an automated fashion is very complex. We propose to use Bayesian Network (BN) models for creating a representation of the dependence relationships among network protocol parameters. BN is a unique tool for modeling the network protocol stack as it not only learns the probabilistic dependence of network protocol parameters but also provides an opportunity to tune some of the cognitive network parameters to achieve desired performance. To the best of our knowledge, this is the first work to explore the use of BNs for cognitive networks. Creating a BN model for network parameters involves the following steps: sampling the network protocol parameters (Observe), learning the structure of the BN and its parameters from the data (Learn), using a Bayesian Network inference engine (Plan and Decide) to make decisions, and finally effecting the decisions (Act). We have proved the feasibility of achieving a BN-based cognitive network system using the ns-3 simulation platform. From the early results obtained from our cognitive network approach, we provide interesting insights on predicting the network behavior, including the performance of the TCP throughput inference engine based on other observed parameters.
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 [371]
For a good amount of training samples (at least 1000), Quer et al.'s BN model provides a low prediction error.
“The results demonstrate that for a good amount of training samples (≥ 1000), this model provides a low prediction error.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [371]
Prediction based only on the number of MAC Transmissions achieves a comparable error, and sometimes even lower, than using the full set of features.
“Furthermore, the authors exhibit that the prediction based only on the number of MAC Transmissions (MAC-TX) achieves a comparable error-and sometimes even lower-than using the full set of features.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [371]
Cites
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033 · see citing works
Artificial intelligence: a modern approach
Kumar, D. A., Balasubramanian, S., Byeon, D. H., & Manerkar, P. G. V. (1995) · Choice Reviews Online · doi:10.5860/choice.33-1577 · Cited by 22,182 · see citing works
Pattern Recognition and Machine Learning
(2007) · Kybernetes · doi:10.1108/03684920710743466 · Cited by 8,540 · see citing works
(2009) · Cited by 6,153 · see citing works
Bayesian Networks and Decision Graphs
Jensen, F. V., & Nielsen, T. D. (2007) · Information science and statistics · doi:10.1007/978-0-387-68282-2 · Cited by 4,157 · see citing works
Cognitive Radio An Integrated Agent Architecture for Software Defined Radio
Mitola, J. (2000) · Cited by 3,509 · see citing works
Richardson, T., & Urbanke, R. L. (2008) · Cambridge University Press eBooks · doi:10.1017/cbo9780511791338 · Cited by 2,343 · see citing works
The bayes net toolbox for matlab
Murphy, K. (2001) · Cited by 1,014 · see citing works
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 636 · see citing works
Cognitive networks: adaptation and learning to achieve end-to-end performance objectives
Thomas, R. W., Friend, D. H., DaSilva, L. A., et al. (2006) · IEEE Communications Magazine · doi:10.1109/mcom.2006.273099 · Cited by 468 · see citing works
Learning Bayesian Network Model Structure from Data
Margaritis, D. (2003) · Cited by 282 · see citing works
Comparison of score metrics for Bayesian network learning
Yang, S., & Chang, K. (2002) · IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans · doi:10.1109/tsmca.2002.803772 · Cited by 84 · see citing works
CogNet: a cognitive complete knowledge network system
Manoj, B. S. B. S., Rao, R. R., & Zorzi, M. (2008) · IEEE Wireless Communications · doi:10.1109/mwc.2008.4749751 · Cited by 51 · see citing works
Self-citationExploring Simulated Annealing and Graphical Models for Optimization in Cognitive Wireless Networks
Meshkova, E., Riihijärvi, J., Achtzehn, A., et al. (2009) · IEEE Global Telecommunications Conference (GLOBECOM) · doi:10.1109/glocom.2009.5425349 · Cited by 23 · see citing works
Using Bayesian Networks for Cognitive Control of Multi-hop Wireless Networks
Quer, G., Meenakshisundaram, H., Tamma, B. R., et al. (2010) · doi:10.1109/milcom.2010.5680448 · Cited by 21 · see citing works
Self-citationAn alternative approach to measurement based on quantile functions
Lampasi, A. (2008) · Measurement · doi:10.1016/j.measurement.2008.01.009 · Cited by 16 · 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
Cognitive Call Admission Control for VoIP over IEEE 802.11 Using Bayesian Networks
Quer, G., Baldo, N., & Zorzi, M. (2011) · 2011 IEEE Global Telecommunications Conference - GLOBECOM 2011 · doi:10.1109/glocom.2011.6133955 · Cited by 10 · see citing works
Self-citation
- Authors
- Quer, G., Meenakshisundaram, H., Tamma, B., Manoj, B. S., Rao, R., & Zorzi, M.
- Affiliations
- University of Padua (IT)
- University of California San Diego (US)
- Venue
- 2010 IEEE Global Telecommunications Conference GLOBECOM 2010
- Publisher
- IEEE
- Published
- 2010-12
- Pages
- 1-6
- ISSN
- 1930-529X (ISSN-L)
- OpenAlex
- W2140100635
- Cited by
- 29
- References
- 16
- Citations by year
- 2025: 1 · 2022: 3 · 2018: 2 · 2017: 3 · 2016: 1 · 2015: 2 · 2014: 4 · 2013: 4 · 2012: 5
- FWCI
- 3.75
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Globecom (publishedVersion)
- Padua Research Archive (University of Padova) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Cognitive Radio Networks and Spectrum Sensing
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Keywords
- cognitive networks, Bayesian networks, protocol stack, Bayesian network structure learning, Bayesian network inference, network performance optimization, ns-3 simulation
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
