Traffic matrices are used for many network management operations, from planning to repairing. Despite years of research on the topic, their estimation and inference on the Internet are still challenging and error-prone. For example, missing values are unavoidable due to flaws in the measurement systems and possible failure in data collection systems. It is thus helpful for many network operators to recover the missing data from the partial direct measurements. Some existing matrix completion methods do not fully consider network traffic behavior and hidden traffic characteristics, showing the inability to adapt to multiple scenarios. Others instead make assumptions on the matrix structure that may be invalid or impractical, curtailing the applicability. In this paper, we propose Hide & Seek, a novel matrix completion and prediction algorithm based on a combination of generative autoencoders and Hidden Markov Models. We demonstrate with an extensive experimental evaluation on real-world datasets how our algorithm can accurately reconstruct missing values while predicting their short-term evolution.

Hide & Seek: Traffic Matrix Completion and Inference Using Hidden Information / Sacco, Alessio; Esposito, Flavio; Marchetto, Guido. - ELETTRONICO. - (2023), pp. 529-534. (Intervento presentato al convegno 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC) tenutosi a Las Vegas, NV, USA nel 08-11 January 2023) [10.1109/CCNC51644.2023.10060329].

Hide & Seek: Traffic Matrix Completion and Inference Using Hidden Information

Alessio Sacco;Guido Marchetto
2023

Abstract

Traffic matrices are used for many network management operations, from planning to repairing. Despite years of research on the topic, their estimation and inference on the Internet are still challenging and error-prone. For example, missing values are unavoidable due to flaws in the measurement systems and possible failure in data collection systems. It is thus helpful for many network operators to recover the missing data from the partial direct measurements. Some existing matrix completion methods do not fully consider network traffic behavior and hidden traffic characteristics, showing the inability to adapt to multiple scenarios. Others instead make assumptions on the matrix structure that may be invalid or impractical, curtailing the applicability. In this paper, we propose Hide & Seek, a novel matrix completion and prediction algorithm based on a combination of generative autoencoders and Hidden Markov Models. We demonstrate with an extensive experimental evaluation on real-world datasets how our algorithm can accurately reconstruct missing values while predicting their short-term evolution.
2023
978-1-6654-9734-3
File in questo prodotto:
File Dimensione Formato  
Hide_amp_Seek_Traffic_Matrix_Completion_and_Inference_Using_Hidden_Information.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 395.15 kB
Formato Adobe PDF
395.15 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
CCNC_2023___TM_estimation___short_version__camera_ready_.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 332.5 kB
Formato Adobe PDF
332.5 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2978361