Maxime MOUCHET

Poste

Doctorant

Localisation

Brest

Contact information:

Tél.

1417

Mail

maxime.mouchet@imt-atlantique.fr
Liens personnels
Les 10 dernières publications HAL
Communication dans un congrès
Mouchet Maxime, Chonavel Thierry, Vaton Sandrine
Statistical Characterization of Round-Trip Times with Nonparametric Hidden Markov Models
IFIP/IEEE IM 2019 Workshop: 4th International Workshop on Analytics for Network and Service Management (AnNet 2019), Apr 2019, Washington, DC, United States
Bibtext :
@inproceedings{mouchet:hal-02010099,
TITLE = {{Statistical Characterization of Round-Trip Times with Nonparametric Hidden Markov Models}},
AUTHOR = {Mouchet, Maxime and Chonavel, Thierry and Vaton, Sandrine},
URL = {https://hal.archives-ouvertes.fr/hal-02010099},
BOOKTITLE = {{IFIP/IEEE IM 2019 Workshop: 4th International Workshop on Analytics for Network and Service Management (AnNet 2019)}},
ADDRESS = {Washington, DC, United States},
YEAR = {2019},
MONTH = Apr,
PDF = {https://hal.archives-ouvertes.fr/hal-02010099/file/AnNet_2019.pdf},
HAL_ID = {hal-02010099},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Statistical Characterization of Round-Trip Times with Nonparametric Hidden Markov Models
%+ Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA)
%+ Département Informatique (INFO)
%+ Université Bretagne Loire (UBL)
%+ Lab-STICC_TB_CID_TOMS
%+ Département Signal et Communications (SC)
%A Mouchet, Maxime
%A Chonavel, Thierry
%A Vaton, Sandrine
%< avec comité de lecture
%B IFIP/IEEE IM 2019 Workshop: 4th International Workshop on Analytics for Network and Service Management (AnNet 2019)
%C Washington, DC, United States
%8 2019-04-08
%D 2019
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]Conference papers
%X The study of round-trip time (RTT) measurements on the Internet is of particular importance for improving real-time applications, enforcing QoS with traffic engineering, or detecting unexpected network conditions. On large timescales, from 1 hour to several days, RTT measurements exhibit characteristic patterns due to inter and intra-AS routing changes and traffic engineering, in addition to link congestion. We propose the use of a nonparametric Bayesian model, the Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), to characterize RTT timeseries. The parameters of the HMM, including the number of states, as well as the values of hidden states are estimated from delay observations by Gibbs sampling. No assumptions are made on the number of states, and a nonparametric mixture model is used to represent a wide range of delay distribution in each state for more flexibility. We validate the model through three applications: on RIPE Atlas measurements we show that 80% of the states learned on RTTs match only one AS path; on a labelled delay changepoint dataset we show that the model is competitive with state-of-the-art changepoint detection methods in terms of precision and recall; and we show that the predictive ability of the model allows us to reduce the monitoring cost by 90% in routing overlays using Markov decision processes.
%G English
%2 https://hal.archives-ouvertes.fr/hal-02010099/document
%2 https://hal.archives-ouvertes.fr/hal-02010099/file/AnNet_2019.pdf
%L hal-02010099
%U https://hal.archives-ouvertes.fr/hal-02010099
%~ CNRS
%~ UNIV-BREST
%~ UNIV-UBS
%~ INSTITUT-TELECOM
%~ IRISA_SET
%~ ENIB
%~ LAB-STICC_ENIB
%~ LAB-STICC
%~ LAB-STICC_TB
%~ CENTRALESUPELEC
%~ IRISA
%~ INRIA
%~ IMT-ATLANTIQUE
%~ LAB-STICC_IMTA_CID_TOMS
%~ LAB-STICC_IMTA
%~ INRIA-AUT
%~ IMTA_INFO
%~ IMTA_SC
%~ INSA-GROUPE
%~ UNIV-RENNES1
%~ UR1-MATH-STIC
%~ UR1-HAL
%~ UR1-UFR-ISTIC
%~ TEST-UR-CSS
%~ IRISA_IMTA
%~ UNIV-RENNES
Communication dans un congrès
Mouchet Maxime, Vaton Sandrine, Brun Olivier, Belzarena Pablo, Amigo Isabel, Prabhu Balakrishna
Optimisation conjointe de la métrologie active et du routage : une approche markovienne
Rencontres Francophones sur la Conception de Protocoles, l’Évaluation de Performance et l’Expérimentation des Réseaux de Communication, May 2018, Roscoff, France. 2018
Bibtext :
@inproceedings{mouchet:hal-01785870,
TITLE = {{Optimisation conjointe de la m{\'e}trologie active et du routage : une approche markovienne}},
AUTHOR = {Mouchet, Maxime and Vaton, Sandrine and Brun, Olivier and Belzarena, Pablo and Amigo, Isabel and Prabhu, Balakrishna},
URL = {https://hal.archives-ouvertes.fr/hal-01785870},
BOOKTITLE = {{Rencontres Francophones sur la Conception de Protocoles, l'{\'E}valuation de Performance et l'Exp{\'e}rimentation des R{\'e}seaux de Communication}},
ADDRESS = {Roscoff, France},
HAL_LOCAL_REFERENCE = {Rapport LAAS n{\textdegree} 18114},
YEAR = {2018},
MONTH = May,
KEYWORDS = {optimisation ; routage ; m{\'e}trologie ; RTT ; HMM ; MDP ; RIPE Atlas},
PDF = {https://hal.archives-ouvertes.fr/hal-01785870/file/CoRes2018.pdf},
HAL_ID = {hal-01785870},
HAL_VERSION = {v1},
}
Endnote :
%0 Conference Proceedings
%T Optimisation conjointe de la métrologie active et du routage : une approche markovienne
%+ Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA)
%+ Université Bretagne Loire (UBL)
%+ Département Informatique (INFO)
%+ Équipe Services et Architectures pour Réseaux Avancés (LAAS-SARA)
%+ UDELAR, Facultad de Ingenieria [Montevideo] (UDELAR)
%A Mouchet, Maxime
%A Vaton, Sandrine
%A Brun, Olivier
%A Belzarena, Pablo
%A Amigo, Isabel
%A Prabhu, Balakrishna
%< avec comité de lecture
%Z Rapport LAAS n° 18114
%B Rencontres Francophones sur la Conception de Protocoles, l’Évaluation de Performance et l’Expérimentation des Réseaux de Communication
%C Roscoff, France
%8 2018-05-28
%D 2018
%K optimisation
%K routage
%K métrologie
%K RTT
%K HMM
%K MDP
%K RIPE Atlas
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]Conference papers
%X Nous nous intéressons à l'optimisation des stratégies de monitoring actif dans le but d'optimiser le routage dans un ré-seau overlay. Notre approche est d'exploiter la stabilité des différentes routes en caractérisant les délais par des chaînes de Markov cachées (HMM) et de formaliser le problème comme un processus de décision markovien (MDP). Nous in-troduisons un modèle HMM pour caractériser les séries de RTT dans un réseau comme Internet. Puis nous formalisons le problème d'optimisation conjointe de la métrologie et du routage comme un MDP que nous résolvons avec une méthode de type Value Iteration. Enfin nous validons notre approche dans différents contextes. En particulier nous considérons un overlay de 30 ancres du réseau de mesure public RIPE Atlas. Nous montrons qu'en exploitant correctement la stabilité des performances des routes, il est possible de réduire le budget de mesure d'au moins 90% en ne perdant quasiment rien en termes de performance de routage.
%G French
%2 https://hal.archives-ouvertes.fr/hal-01785870/document
%2 https://hal.archives-ouvertes.fr/hal-01785870/file/CoRes2018.pdf
%L hal-01785870
%U https://hal.archives-ouvertes.fr/hal-01785870
%~ CNRS
%~ UNIV-UBS
%~ UNIV-TLSE3
%~ IRISA_SET
%~ UNIV-RENNES1
%~ CENTRALESUPELEC
%~ IRISA
%~ INRIA
%~ INSA-TOULOUSE
%~ TEST-UR-CSS
%~ UNIV-RENNES
%~ CORES2018
%~ UR1-MATH-STIC
%~ UR1-HAL
%~ UR1-UFR-ISTIC
%~ INRIA-AUT
%~ LAAS-RESEAUX-ET-COMMUNICATIONS
%~ LAAS-SARA
%~ LAAS
%~ INSA-GROUPE
%~ IMT-ATLANTIQUE
%~ IMTA_INFO
%~ IRISA_IMTA
Article dans une revue
Vaton Sandrine, Brun Olivier, Mouchet Maxime, Belzarena Pablo, Amigo Isabel, Prabhu Balakrishna, Chonavel Thierry
Joint Minimization of Monitoring Cost and Delay in Overlay Networks: Optimal Policies with a Markovian Approach
Journal of Network and Systems Management, Springer Verlag, In press, 〈10.1007/s10922-018-9464-1〉
Bibtext :
@article{vaton:hal-01857738,
TITLE = {{Joint Minimization of Monitoring Cost and Delay in Overlay Networks: Optimal Policies with a Markovian Approach}},
AUTHOR = {Vaton, Sandrine and Brun, Olivier and Mouchet, Maxime and Belzarena, Pablo and Amigo, Isabel and Prabhu, Balakrishna and Chonavel, Thierry},
URL = {https://hal.archives-ouvertes.fr/hal-01857738},
JOURNAL = {{Journal of Network and Systems Management}},
HAL_LOCAL_REFERENCE = {Rapport LAAS n{\textdegree} 18260},
PUBLISHER = {{Springer Verlag}},
YEAR = {2018},
DOI = {10.1007/s10922-018-9464-1},
KEYWORDS = {HDP-HMM ; Sparse monitoring ; RIPE Atlas ; Round trip times ; Active monitoring ; Markov chains ; Hidden Markov models ; Markov decision processes ; Routing overlays},
PDF = {https://hal.archives-ouvertes.fr/hal-01857738/file/article-journal-OptimMetro.pdf},
HAL_ID = {hal-01857738},
HAL_VERSION = {v1},
}
Endnote :
%0 Journal Article
%T Joint Minimization of Monitoring Cost and Delay in Overlay Networks: Optimal Policies with a Markovian Approach
%+ Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA)
%+ Université Bretagne Loire (UBL)
%+ Département Informatique (INFO)
%+ Équipe Services et Architectures pour Réseaux Avancés (LAAS-SARA)
%+ UDELAR, Facultad de Ingenieria [Montevideo] (UDELAR)
%+ Lab-STICC_IMTA_CID_TOMS
%+ Département Signal et Communications (SC)
%A Vaton, Sandrine
%A Brun, Olivier
%A Mouchet, Maxime
%A Belzarena, Pablo
%A Amigo, Isabel
%A Prabhu, Balakrishna
%A Chonavel, Thierry
%< avec comité de lecture
%Z Rapport LAAS n° 18260
%@ 1064-7570
%J Journal of Network and Systems Management
%I Springer Verlag
%8 2018
%D 2018
%R 10.1007/s10922-018-9464-1
%K HDP-HMM
%K Sparse monitoring
%K RIPE Atlas
%K Round trip times
%K Active monitoring
%K Markov chains
%K Hidden Markov models
%K Markov decision processes
%K Routing overlays
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]Journal articles
%X Continuous monitoring of network resources enables to make more-informed resource allocation decisions but incurs overheads. We investigate the trade-off between monitoring costs and benefits of accurate state information for a routing problem. In our approach link delays are modeled by Markov chains or hidden Markov models. The current delay information on a link can be obtained by actively monitoring this link at a fixed cost. At each time slot, the decision maker chooses to monitor a subset of links with the objective of minimizing a linear combination of long-run average delay and monitoring costs. This decision problem is modeled as a Markov decision process whose solution is computed numerically. In addition, in simple settings we prove that immediate monitoring cost and delay minimization leads to a threshold policy on a filter which sums up information from past measurements. The lightweight method as well as the optimal policy are tested on several use-cases. We demonstrate on an overlay of 30 nodes of RIPE Atlas that we obtain delay values close to the performance of the always best path with an extremely low monitoring effort when delays between nodes are modeled with hierarchical Dirichlet process hidden Markov models.
%G English
%2 https://hal.archives-ouvertes.fr/hal-01857738/document
%2 https://hal.archives-ouvertes.fr/hal-01857738/file/article-journal-OptimMetro.pdf
%L hal-01857738
%U https://hal.archives-ouvertes.fr/hal-01857738
%~ UNIV-BREST
%~ UR1-HAL
%~ UR1-MATH-STIC
%~ UR1-UFR-ISTIC
%~ TEST-UR-CSS
%~ LAB-STICC_IMTA_CID_TOMS
%~ IMTA_INFO
%~ IMTA_SC
%~ IRISA_IMTA
%~ LAB-STICC_IMTA
%~ UNIV-RENNES
%~ INRIA-AUT
%~ IMT-ATLANTIQUE
%~ LAAS-RESEAUX-ET-COMMUNICATIONS
%~ CENTRALESUPELEC
%~ LAB-STICC
%~ INSTITUT-TELECOM
%~ UNIV-TLSE3
%~ UNIV-RENNES1
%~ CNRS
%~ INRIA
%~ UNIV-UBS
%~ INSA-TOULOUSE
%~ LAAS
%~ IRISA
%~ IRISA_SET
%~ LAAS-SARA
%~ ENIB
%~ INSA-GROUPE
See all publications