{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T12:59:47Z","timestamp":1740142787224,"version":"3.37.3"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T00:00:00Z","timestamp":1721520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072465","62172155"],"award-info":[{"award-number":["62072465","62172155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023TQ0089"],"award-info":[{"award-number":["2023TQ0089"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2022RC3061","2023RC3027"],"award-info":[{"award-number":["2022RC3061","2023RC3027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurate and current comprehension of network status is crucial for efficient network management. Nevertheless, direct network measurement strategies entail substantial traffic overhead and demand intricate coordination among network entities, making them impractical. Network tomography, an indirect measurement approach, utilizes insights garnered from measured parts to deduce characteristics of the entire network. Past studies frequently depend on acquiring challenging-to-access information, such as the complete network topology or support from specialized protocols. Unfortunately, these constraints pose challenges in non-cooperative scenarios where obtaining such information is difficult. Recent endeavors pursue emancipating tomography from dependence on copious information, striving to predict unmeasured path performance using limited data. Nevertheless, the disparity between the measured data and actual performance has hindered the accuracy. In response, we introduce an innovative tomography framework named DRL-Tomo, designed to alleviate potential biases. DRL-Tomo initiates by generating augmented data through deep reinforcement learning, gradually approximating the genuine performance of unmeasured paths. Subsequently, a neural network model is trained using this augmented data, enabling precise inferences. Our experiments, encompassing both real-world and synthetic datasets, vividly demonstrate DRL-Tomo\u2019s remarkable enhancement. Specifically, it achieves a substantial 10%\u201367% improvement in path delay prediction and an impressive 30%\u201398% enhancement in path loss rate prediction.<\/jats:p>","DOI":"10.1093\/comjnl\/bxae064","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T08:30:41Z","timestamp":1721637041000},"page":"2995-3008","source":"Crossref","is-referenced-by-count":0,"title":["DRL-Tomo: a deep reinforcement learning-based approach to augmented data generation for network tomography"],"prefix":"10.1093","volume":"67","author":[{"given":"Changsheng","family":"Hou","sequence":"first","affiliation":[{"name":"College of Computer, National University of Defense Technology , No. 109 Deya Road, Kaifu District, Changsha City, Hunan Province 410073 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingnan","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology , No. 109 Deya Road, Kaifu District, Changsha City, Hunan Province 410073 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xionglve","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology , No. 109 Deya Road, Kaifu District, Changsha City, Hunan Province 410073 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongqing","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology , No. 109 Deya Road, Kaifu District, Changsha City, Hunan Province 410073 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingwen","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology , No. 109 Deya Road, Kaifu District, Changsha City, Hunan Province 410073 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiping","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology , No. 109 Deya Road, Kaifu District, Changsha City, Hunan Province 410073 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,7,21]]},"reference":[{"volume-title":"IEEE Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref1"},{"volume-title":"IEEE International Conference on Mobile Ad Hoc and Smart Systems (MASS)","key":"2024101809313808200_ref2"},{"volume-title":"Neural network tomography","year":"2020","author":"Ma","key":"2024101809313808200_ref3"},{"key":"2024101809313808200_ref4","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1109\/TNET.2002.805026","article-title":"Multicast-based inference of network-internal delay distributions","volume":"10","author":"Lo Presti","year":"2002","journal-title":"IEEE\/ACM Trans Netw"},{"key":"2024101809313808200_ref5","doi-asserted-by":"crossref","first-page":"3383","DOI":"10.1109\/TNSE.2024.3371384","article-title":"Delay-aware routing in software-defined networks via network tomography and reinforcement learning","volume":"11","author":"Tao","year":"2024","journal-title":"IEEE Trans Netw Sci Eng"},{"key":"2024101809313808200_ref6","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1080\/01621459.1996.10476697","article-title":"Network tomography: estimating source-destination traffic intensities from link data","volume":"91","author":"Vardi","year":"1996","journal-title":"J Am Stat Assoc"},{"key":"2024101809313808200_ref7","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1145\/964725.633041","article-title":"Traffic matrix estimation: existing techniques and new directions","volume":"32","author":"Medina","year":"2002","journal-title":"ACM SIGCOMM Comput Commun Rev"},{"volume-title":"IEEE Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref8"},{"volume-title":"IEEE Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref9"},{"volume-title":"IEEE International Conference on Network Protocols (ICNP)","key":"2024101809313808200_ref10"},{"volume-title":"IEEE Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref11"},{"key":"2024101809313808200_ref12","doi-asserted-by":"crossref","first-page":"4239","DOI":"10.1109\/TSP.2022.3191807","article-title":"Simultaneous topology and loss tomography via a modified theme dictionary model","volume":"70","author":"Li","year":"2022","journal-title":"IEEE Trans Signal Process"},{"volume-title":"IEEE\/ACM International Symposium on Quality of Service (IWQOS)","key":"2024101809313808200_ref13"},{"volume-title":"IEEE Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref14"},{"key":"2024101809313808200_ref15","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/TNET.2021.3118006","article-title":"Bound inference and reinforcement learning-based path construction in bandwidth tomography","volume":"30","author":"Feng","year":"2022","journal-title":"IEEE\/ACM Trans Netw"},{"key":"2024101809313808200_ref16","first-page":"2617","article-title":"Measurement integrity attacks against network tomography: feasibility and defense","volume":"18","author":"Zhao","year":"2021","journal-title":"IEEE Trans Dependable Secure Comput"},{"volume-title":"IEEE Annual Consumer Communications and Networking Conference (CCNC)","key":"2024101809313808200_ref17"},{"volume-title":"IEEE International Conference on High Performance Switching and Routing (HPSR)","key":"2024101809313808200_ref18"},{"volume-title":"IEEE International Conference on Communications Workshops (ICC Workshops)","key":"2024101809313808200_ref19"},{"volume-title":"IEEE International Conference on Unmanned Systems (ICUS)","key":"2024101809313808200_ref20"},{"key":"2024101809313808200_ref21","doi-asserted-by":"crossref","first-page":"5","DOI":"10.23919\/comex.2023XBL0132","article-title":"Link delay estimation under undeterministic routing using neural network","volume":"13","author":"Ushizuka","year":"2024","journal-title":"IEICE Communications Express"},{"journal-title":"IEEE Global Communications Conference (GLOBECOM)","key":"2024101809313808200_ref22"},{"key":"2024101809313808200_ref23","doi-asserted-by":"crossref","DOI":"10.1007\/s10922-023-09763-y","article-title":"Network tomography with partial topology knowledge and dynamic routing","volume":"31","author":"Sartzetakis","year":"2023","journal-title":"J Network Syst Manage"},{"key":"2024101809313808200_ref24","doi-asserted-by":"crossref","first-page":"9668","DOI":"10.1109\/JIOT.2019.2930459","article-title":"A $Q$ -learning based framework for congested link identification","volume":"6","author":"Pan","year":"2019","journal-title":"IEEE Internet Things J."},{"key":"2024101809313808200_ref25","doi-asserted-by":"crossref","first-page":"36988","DOI":"10.1109\/ACCESS.2020.2975238","article-title":"Traffic measurement optimization based on reinforcement learning in large-scale its-oriented backbone networks","volume":"8","author":"Nie","year":"2020","journal-title":"IEEE Access"},{"volume-title":"IEEE International Conference on Communications (ICC)","key":"2024101809313808200_ref26"},{"volume-title":"IEEE International Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref27"},{"key":"2024101809313808200_ref28","doi-asserted-by":"crossref","first-page":"1392","DOI":"10.1109\/TNET.2015.2411691","article-title":"Scalpel: scalable preferential link tomography based on graph trimming","volume":"24","author":"Gao","year":"2016","journal-title":"IEEE\/ACM Trans Netw"},{"key":"2024101809313808200_ref29","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1109\/TNET.2016.2581176","article-title":"Optimal monitor assignment for preferential link tomography in communication networks","volume":"25","author":"Dong","year":"2017","journal-title":"IEEE\/ACM Trans Netw"},{"volume-title":"IEEE International Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref30"},{"volume-title":"IEEE Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref31"},{"key":"2024101809313808200_ref32","doi-asserted-by":"crossref","first-page":"1859","DOI":"10.1109\/TNET.2020.3000115","article-title":"Bound inference in network performance tomography with additive metrics","volume":"28","author":"Feng","year":"2020","journal-title":"IEEE\/ACM Trans Netw"},{"key":"2024101809313808200_ref33","doi-asserted-by":"crossref","first-page":"1801","DOI":"10.1109\/TNET.2019.2931047","article-title":"Preferential link tomography in dynamic networks","volume":"27","author":"Li","year":"2019","journal-title":"IEEE\/ACM Trans Netw"},{"key":"2024101809313808200_ref34","doi-asserted-by":"crossref","first-page":"1732","DOI":"10.1109\/TNET.2016.2642185","article-title":"Robust and efficient monitor placement for network tomography in dynamic networks","volume":"25","author":"He","year":"2017","journal-title":"IEEE\/ACM Trans Netw"},{"key":"2024101809313808200_ref35","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1109\/TNET.2018.2834141","article-title":"Taming both predictable and unpredictable link failures for network tomography","volume":"26","author":"Li","year":"2018","journal-title":"IEEE\/ACM Trans Netw"},{"key":"2024101809313808200_ref36","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1109\/OJCOMS.2021.3068222","article-title":"Tomography based learning for load distribution through opaque networks","volume":"2","author":"Xu","year":"2021","journal-title":"IEEE Open J Commun Soc"},{"key":"2024101809313808200_ref37","doi-asserted-by":"crossref","first-page":"5064","DOI":"10.1109\/TNNLS.2022.3207346","article-title":"Deep reinforcement learning: a survey","volume":"35","author":"Wang","year":"2024","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"2024101809313808200_ref38","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","article-title":"Deep reinforcement learning for autonomous driving: a survey","volume":"23","author":"Kiran","year":"2022","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2024101809313808200_ref39","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: a brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"2024101809313808200_ref40","doi-asserted-by":"crossref","first-page":"3133","DOI":"10.1109\/COMST.2019.2916583","article-title":"Applications of deep reinforcement learning in communications and networking: a survey","volume":"21","author":"Luong","year":"2019","journal-title":"IEEE Commun Surv Tutorials"},{"key":"2024101809313808200_ref41","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"volume-title":"Proceedings of the International Conference on Machine Learning","key":"2024101809313808200_ref42"},{"volume-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"2024101809313808200_ref43"},{"volume-title":"Rocketfuel: An isp topology mapping engine","key":"2024101809313808200_ref44"},{"key":"2024101809313808200_ref45","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1109\/JSAC.2011.111002","article-title":"The internet topology zoo","volume":"29","author":"Knight","year":"2011","journal-title":"IEEE J Sel Areas Commun"},{"key":"2024101809313808200_ref46","article-title":"Network science","volume":"371","author":"Barab\u00e1si","year":"2016","journal-title":"Philos Trans R Soc London, Ser A"},{"volume-title":"IEEE Conference on Computer Communications (INFOCOM)","key":"2024101809313808200_ref47"},{"key":"2024101809313808200_ref48","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.1109\/TNET.2021.3058230","article-title":"Stealthy DGoS attack: degrading of service under the watch of network tomography","volume":"29","author":"Chiu","year":"2021","journal-title":"IEEE\/ACM Trans Netw"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/10\/2995\/59729674\/bxae064.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/10\/2995\/59729674\/bxae064.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T09:31:59Z","timestamp":1729243919000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/67\/10\/2995\/7717689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,21]]},"references-count":48,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,7,21]]},"published-print":{"date-parts":[[2024,10,12]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxae064","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"type":"print","value":"0010-4620"},{"type":"electronic","value":"1460-2067"}],"subject":[],"published-other":{"date-parts":[[2024,10]]},"published":{"date-parts":[[2024,7,21]]}}}