{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:44:50Z","timestamp":1775144690322,"version":"3.50.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T00:00:00Z","timestamp":1691020800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T00:00:00Z","timestamp":1691020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101017168"],"award-info":[{"award-number":["101017168"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101017168"],"award-info":[{"award-number":["101017168"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018960","name":"National Technical University of Athens","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018960","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Netw Syst Manage"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Networks are always evolving to meet the needs of progressing and novel applications. To this end, improved network capacity, latency and security are required. Monitoring is key to achieving these objectives. It is a cornerstone for the uninterrupted network operation and the applications\u2019 QoS management. Network tomography uses a subset of monitoring information, corresponding to partial view of the network state, to estimate wide-sense network performance metrics. In this paper, we present a novel machine learning (ML) formulation for Network Tomography. It is novel in that its features are designed under the assumption that: (i) the existence of certain links of the network is not known (e.g., due to security reasons), (ii) the routing is dynamic (non-deterministic), i.e., for the same origin\u2013destination node pair, a different route may be selected depending on the state of certain links. These assumptions are typically present in modern networks. The formulation can be used to estimate both additive and non-additive performance metrics. We evaluate our proposal using different ML algorithms: neural networks (NNs), Gaussian regression and linear regression with interactions. Our simulations indicate that our ML formulation has better estimation accuracy compared to traditional algebraic or other ML approaches that cannot or do not take into account these two hypotheses. Regarding the accuracy of the examined ML algorithms, the differences mainly depend on the additive or not nature of the network metrics.<\/jats:p>","DOI":"10.1007\/s10922-023-09763-y","type":"journal-article","created":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T08:02:29Z","timestamp":1691049749000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Network Tomography with Partial Topology Knowledge and Dynamic Routing"],"prefix":"10.1007","volume":"31","author":[{"given":"Ippokratis","family":"Sartzetakis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanouel","family":"Varvarigos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,3]]},"reference":[{"key":"9763_CR1","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1080\/01621459.1996.10476697","volume":"91","author":"Y Vardi","year":"1996","unstructured":"Vardi, Y.: Network tomography: estimating source\u2013destination traffic intensities from link data. J. Am. Stat. Assoc. 91, 365\u2013377 (1996)","journal-title":"J. Am. Stat. Assoc."},{"key":"9763_CR2","unstructured":"R\u00f8dbro, C.A.,Chou, P.A., Dogan, \u00dc.: Prediction of Bandwidth and Additive Metrics for Large Scale Network Tomography. Microsoft Research Technical Report, MSR-TR-2016-57"},{"key":"9763_CR3","unstructured":"Ma, L., Zhang, Z., Srivatsa, M.: Neural network tomography. arXiv preprint (2020). arXiv:2001.02942"},{"key":"9763_CR4","doi-asserted-by":"crossref","unstructured":"Sartzetakis, I., Varvarigos, E.: Machine learning network tomography with dynamic routing and partial topology knowledge. In: Proceedings of the IEEE Globecom Conference, Rio de Janeiro, Brazil (December 2022)","DOI":"10.1109\/GLOBECOM48099.2022.10001622"},{"issue":"7","key":"9763_CR5","doi-asserted-by":"publisher","first-page":"2462","DOI":"10.1109\/18.796384","volume":"45","author":"R C\u00e1ceres","year":"1999","unstructured":"C\u00e1ceres, R., Duffield, N.G., Horowitz, J., Towsley, D.F.: Multicast-based inference of network-internal loss characteristics. IEEE Trans. Inf. Theory 45(7), 2462\u20132480 (1999)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"9763_CR6","unstructured":"Duffield, N.G., Horowitz, J., Presti, F.L., Towsley, D.: Network delay tomography from end-to-end unicast measurements. In: Proceedings of the Thyrrhenian International Workshop on Digital Communications. Springer, Berlin (2001)"},{"key":"9763_CR7","doi-asserted-by":"crossref","unstructured":"Padmanabhan, V.N., Qiu, L., Wang, H.J.: Passive network tomography using Bayesian inference. In: Proceedings of the 2nd ACM SIGCOMM Workshop on Internet measurement, Marseille, France (November 2002)","DOI":"10.1145\/637201.637214"},{"key":"9763_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bindel, D., Katz, R.H.: Tomography-based overlay network monitoring. In: Proceedings of the 3rd ACM SIGCOMM conference on Internet measurement, Miami Beach, USA (October 2003)","DOI":"10.1145\/948205.948233"},{"issue":"12","key":"9763_CR9","doi-asserted-by":"publisher","first-page":"5373","DOI":"10.1109\/TIT.2006.885460","volume":"52","author":"N Duffield","year":"2006","unstructured":"Duffield, N.: Network tomography of binary network performance characteristics. IEEE Trans. Inf. Theory 52(12), 5373\u20135388 (2006)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"6","key":"9763_CR10","doi-asserted-by":"publisher","first-page":"2710","DOI":"10.1109\/TIT.2006.874414","volume":"52","author":"O Gurewitz","year":"2006","unstructured":"Gurewitz, O., Cidon, I., Sidi, M.: One-way delay estimation using network-wide measurements. IEEE Trans. Inf. Theory 52(6), 2710\u20132724 (2006)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"12","key":"9763_CR11","doi-asserted-by":"publisher","first-page":"6029","DOI":"10.1109\/TSP.2010.2068294","volume":"58","author":"A Chen","year":"2010","unstructured":"Chen, A., Cao, J., Bu, T.: Network tomography: identifiability and Fourier domain estimation. IEEE Trans. Signal Process. 58(12), 6029\u20136039 (2010)","journal-title":"IEEE Trans. Signal Process."},{"key":"9763_CR12","doi-asserted-by":"crossref","unstructured":"Ma, L., He, T., Leung, K.K., Towsley, D., Swami, A.: Efficient identification of additive link metrics via network tomography. In: Proceedings of the 33rd IEEE International Conference on Distributed Computing Systems, Philadelphia, USA (July 2013)","DOI":"10.1109\/ICDCS.2013.24"},{"issue":"4","key":"9763_CR13","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1109\/TNET.2014.2328668","volume":"22","author":"L Ma","year":"2014","unstructured":"Ma, L., He, T., Leung, K.K., Swami, A., Towsley, D.: Inferring link metrics from end-to-end path measurements: identifiability and monitor placement. IEEE\/ACM Trans. Network. 22(4), 1351\u20131368 (2014)","journal-title":"IEEE\/ACM Trans. Network."},{"issue":"3","key":"9763_CR14","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1214\/088342304000000422","volume":"19","author":"R Castro","year":"2004","unstructured":"Castro, R., Coates, M., Liang, G., Nowak, R., Yu, B.: Network tomography: recent developments. Stat. Sci. 19(3), 499\u2013517 (2004)","journal-title":"Stat. Sci."},{"issue":"2","key":"9763_CR15","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3390\/fi12020020","volume":"12","author":"G Kakkavas","year":"2020","unstructured":"Kakkavas, G., Gkatzioura, D., Karyotis, V., Papavassiliou, S.: A review of advanced algebraic approaches enabling network tomography for future network infrastructures. Future Internet 12(2), 20 (2020)","journal-title":"Future Internet"},{"issue":"1","key":"9763_CR16","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1109\/TNET.2016.2584544","volume":"25","author":"L Ma","year":"2017","unstructured":"Ma, L., He, T., Swami, A., Towsley, D., Leung, K.K.: Network capability in localizing node failures via end-to-end path measurements. IEEE\/ACM Trans. Network. 25(1), 434\u2013450 (2017)","journal-title":"IEEE\/ACM Trans. Network."},{"key":"9763_CR17","doi-asserted-by":"crossref","unstructured":"Bartolini, N., He, T., Khamfroush, H.: Fundamental limits of failure identifiability by Boolean network tomography. In: Proceedings of the IEEE INFOCOM Conference on Computer Communications, Atlanta, USA (May 2017)","DOI":"10.1109\/INFOCOM.2017.8057091"},{"issue":"7","key":"9763_CR18","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1587\/transcom.2020EBP3149","volume":"E104.B","author":"R Tagyo","year":"2021","unstructured":"Tagyo, R., Ikegami, D., Kawahara, R.: Network tomography using routing probability for undeterministic routing. IEICE Trans. Commun. E104.B(7), 837\u2013848 (2021)","journal-title":"IEICE Trans. Commun."},{"key":"9763_CR19","doi-asserted-by":"crossref","unstructured":"Rahali, M., Sanner, J., Rubino, G.: TOM: a self-trained tomography solution for overlay networks monitoring. In: Proceedings of the IEEE Consumer Communications and Networking Conference (CCNC), Las Vegas, USA (January 2020)","DOI":"10.1109\/CCNC46108.2020.9045301"},{"key":"9763_CR20","doi-asserted-by":"crossref","unstructured":"Ibraheem, A., Sheng, Z., Parisis, G., Tian, D.: Neural network based partial tomography for in-vehicle network monitoring. In: Proceedings of the IEEE International Conference on Communications Workshops (ICC), Virtual Conference (June 2021)","DOI":"10.1109\/ICCWorkshops50388.2021.9473498"},{"key":"9763_CR21","doi-asserted-by":"crossref","unstructured":"Rkhami, A., Hadjadj-Aoul, Y., Rubino, G., Outtagarts, A.: On the use of machine learning and network tomography for network slices monitoring. In: Proceedings of the IEEE 22nd International Conference on High Performance Switching and Routing (HPSR), Paris, France (June 2021)","DOI":"10.1109\/HPSR52026.2021.9481795"},{"key":"9763_CR22","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M., Nasrabadi, N.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)"},{"key":"9763_CR23","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001","volume-title":"Gaussian Processes for Machine Learning","author":"CE Rasmussen","year":"2005","unstructured":"Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT, Cambridge (2005)"},{"key":"9763_CR24","volume-title":"Multiple Regression: Testing and Interpreting Interactions","author":"LS Aiken","year":"1991","unstructured":"Aiken, L.S., West, S.G., Reno, R.R.: Multiple Regression: Testing and Interpreting Interactions. Sage, London (1991)"}],"container-title":["Journal of Network and Systems Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10922-023-09763-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10922-023-09763-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10922-023-09763-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T06:12:49Z","timestamp":1698300769000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10922-023-09763-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,3]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["9763"],"URL":"https:\/\/doi.org\/10.1007\/s10922-023-09763-y","relation":{},"ISSN":["1064-7570","1573-7705"],"issn-type":[{"value":"1064-7570","type":"print"},{"value":"1573-7705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,3]]},"assertion":[{"value":"27 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"73"}}