Characterization and Prediction of Mobile-App Traffic Using Markov Modeling
| Autor: | Antonio Pescape, Valerio Persico, Antonio Montieri, Giuseppe Aceto, Giampaolo Bovenzi, Domenico Ciuonzo |
|---|---|
| Přispěvatelé: | Aceto, G., Bovenzi, G., Ciuonzo, D., Montieri, A., Persico, V., Pescape, A. |
| Rok vydání: | 2021 |
| Předmět: |
Computer Networks and Communications
Computer science Markov process 02 engineering and technology Markov model Machine learning computer.software_genre Android app Data modeling symbols.namesake mobile app 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering traffic prediction Hidden Markov model traffic modeling Markov chain Network packet business.industry 020206 networking & telecommunications Networking hardware traffic characterization Network planning and design symbols Artificial intelligence encrypted traffic business computer |
| Zdroj: | IEEE Transactions on Network and Service Management. 18:907-925 |
| ISSN: | 2373-7379 |
| Popis: | Modeling network traffic is an endeavor actively carried on since early digital communications, supporting a number of practical applications, that range from network planning and provisioning to security. Accordingly, many theoretical and empirical approaches have been proposed in this long-standing research, most notably, Machine Learning (ML) ones. Indeed, recent interest from network equipment vendors is sparking around the evaluation of solid information-theoretical modeling approaches complementary to ML ones, especially applied to new network traffic profiles stemming from the massive diffusion of mobile apps. To cater to these needs, we analyze mobile-app traffic available in the public dataset MIRAGE-2019 adopting two related modeling approaches based on the well-known methodological toolset of Markov models (namely, Markov Chains and Hidden Markov Models ). We propose a novel heuristic to reconstruct application-layer messages in the common case of encrypted traffic. We discuss and experimentally evaluate the suitability of the provided modeling approaches for different tasks: characterization of network traffic (at different granularities, such as application, application category, and application version), and prediction of network traffic at both packet and message level. We also compare the results with several ML approaches, showing performance comparable to a state-of-the-art ML predictor (Random Forest Regressor). Also, with this work we provide a viable and theoretically sound traffic-analysis toolset to help improving ML evaluation (and possibly its design), and a sensible and interpretable baseline. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|