Multivariate Time Series Characterization and Forecasting of VoIP Traffic in Real Mobile Networks

MD Mauro; G Galatro; F Postiglione; W Song; Antonio Liotta

doi:10.1109/TNSM.2023.3295748

Multivariate Time Series Characterization and Forecasting of VoIP Traffic in Real Mobile Networks

MD Mauro, G Galatro, F Postiglione, W Song Antonio Liotta

IEEE Transactions on Network and Service Management

2023

: https://doi.org/10.1109/TNSM.2023.3295748

https://hdl.handle.net/10863/37651

Data-driven Artificial Intelligence (D2AI)

VoIP traffic characterization

mobility scenarios

machine learning for time series forecasting

multivariate time series forecasting

Predicting the behavior of real-time traffic (e.g., VoIP) in mobility scenarios could help the operators to better plan their network infrastructures and to optimize the allocation of resources. Accordingly, in this work the authors propose a forecasting analysis of crucial QoS/QoE descriptors (some of which neglected in the technical literature) of VoIP traffic in a real mobile environment. The problem is formulated in terms of a multivariate time series analysis. Such a formalization allows to discover and model the temporal relationships among various descriptors and to forecast their behaviors for future periods. Techniques such as Vector Autoregressive models and machine learning (deep-based and tree-based) approaches are employed and compared in terms of performance and time complexity, by reframing the multivariate time series problem into a supervised learning one. Moreover, a series of auxiliary analyses (stationarity, orthogonal impulse responses, etc.) are performed to discover the analytical structure of the time series and to provide deep insights about their relationships. The whole theoretical analysis has an experimental counterpart since a set of trials across a real-world LTE-Advanced environment has been performed to collect, post-process and analyze about 600,000 voice packets, organized per flow and differentiated per codec.

(1)

url

https://doi.org/10.1109/TNSM.2023.3295748

: Multivariate Time Series Characterization and Forecasting of VoIP Traffic in Real Mobile Networks
: MD Mauro
G Galatro - IBM
F Postiglione - University of Salerno
W Song - Shanghai Ocean University
Antonio Liotta - Free University of Bozen-Bolzano
: IEEE Transactions on Network and Service Management
: 1932-4537
: 1932-4537
: Institute of Electrical and Electronics Engineers Inc.
: (UNIBZ)69345375
991006680198301241
: 2-s2.0-85164783612
: Faculty of Computer Science
: English
: Journal article
: Mauro MD, Galatro G, Postiglione F, Song W, Liotta A
: unibz-area: Data-driven Artificial Intelligence (D2AI)
MIURSSD: Informatica;Sistemi di elaborazione delle informazioni
MIURSSDCODE: INF/01;ING-INF/05

See more details