Doctoral School: Mathématiques Hadamard and the Research Unit SAMOVAR - Services répartis, Architectures, Modélisation, Validation, Administration des Réseaux are presenting the "examination of a thesis" by M. Achille SALAÜN, who is expected to defend his research to obtain his PhD at l'Institut Polytechnique de Paris, prepared at Telecom SudParis in: Computer science
"Alarm prediction in networks via spatiotemporal pattern search and machine learning"
THURSDAY, JULY 8, 2021 at 2 pm,
Paris-Rennes-Nice (EIT Digital)
LINCS 23, avenue d’Italie 75013 Paris
- M. François DESBOUVRIES, Professor, Télécom SudParis, FRANCE - Supervisor
- M. Maurizio FILIPPONE, Professor, EURECOM, FRANCE - Rapporteur
- M. Matthieu LATAPY, Research supervisor, CNRS (LIP6), FRANCE - Rapporteur
- Mme Anne BOUILLARD, Research Engineer, Huawei Technologies France, FRANCE - Thesis co-supervisor
- Mme Johanne COHEN, Research supervisor, CNRS (LISN), FRANCE - Examiner
- M. Erwan LE PENNEC, Professor, Ecole Polytechnique (CMAP), FRANCE - Examiner
Nowadays, telecommunication networks occupy a central position in our world. Indeed, they allow to share worldwide a huge amount of information. Networks are however complex systems, both in size and technological diversity.
Therefore, it makes their management and reparation more difficult. In order to limit the negative impact of such failures, some tools have to be developed to detect a failure whenever it occurs, analyse its root causes to solve it efficiently, or even predict this failure as prevention is better than cure.
In this thesis, we mainly focus on these two last problems. To do so, we use files, called alarm logs, storing all the alarms that have been emitted by the system. However, these files are generally noisy and verbose: an operator managing a network needs tools able to extract and handle in an interpretable manner the causal relationships inside a log. In this thesis, we followed two directions.
First, we have inspired from pattern matching techniques: similarly to the Ukkonen’s algorithm, we build online a structure, called DIG-DAG, that stores all the potential causal relationships between the events of a log. Moreover, we introduce a query system to exploit our DIG-DAG structure. Finally, we show how our solution can be used for root cause analysis.
The second approach is a generative approach for the prediction of time series. In particular, we compare two well-known models for this task: recurrent neural nets on the one hand, hidden Markov models on the other hand. Here, we compare analytically the expressivity of these models by encompassing them into a probabilistic model, called GUM.