Simone Porcino
Real-time flow monitoring based on time-space probabilistic data structures.
Rel. Paolo Giaccone, Alessandro Cornacchia. Politecnico di Torino, Corso di laurea magistrale in Communications And Computer Networks Engineering (Ingegneria Telematica E Delle Comunicazioni), 2023
|
Preview |
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview |
Abstract
Network monitoring is essential to ensure network performance, integrity and security. However, with the growth of link rates and simultaneous number of flows, real-time traffic monitoring is challenging because it requires network devices that perform operations on a time scale very reduced and, possibly, with a small amount of memory to store measurement data. Among the available metrics to asses network performance, this thesis refers to the round-trip time (RTT) of data flows, i.e. packets sharing the same flowID. To comply with the aforementioned constraints, the measurement device should be equipped with a very efficient data structure both for recording the time each outgoing packet enters the system and for querying it at the reception of its response to calculate their RTT.
For this purpose, we propose a probabilistic data structure composed of a set of Bloom filter that are evenly spaced temporally
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
URI
![]() |
Modifica (riservato agli operatori) |
