faaShark: An End-to-End Network Traffic Analysis System Atop Serverless Computing

The prosperity of the Internet has made network traffic analysis increasingly indispensable in network operation. With the development of machine learning, more researchers and engineers are using deep learning models for network traffic analysis. However, the rapidly growing data size and model com...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on network science and engineering Ročník 11; číslo 3; s. 2473 - 2484
Hlavní autoři: Zhao, Hongyu, Pan, Shanxing, Cai, Zinuo, Chen, Xinglei, Jin, Lingxiao, Gao, Honghao, Wan, Shaohua, Ma, Ruhui, Guan, Haibing
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.05.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Analytical models
Cloud computing
cold start
Communications traffic
Computational modeling
Deep learning
Design optimization
distributed training
Load modeling
Machine learning
Network analysis
Network traffic analysis
Optimization algorithms
Resource scheduling
Serverless computing
Telecommunication traffic
Traffic analysis
Traffic models
Training
ISSN:2327-4697, 2334-329X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The prosperity of the Internet has made network traffic analysis increasingly indispensable in network operation. With the development of machine learning, more researchers and engineers are using deep learning models for network traffic analysis. However, the rapidly growing data size and model complexity make resource scheduling a serious limitation, which is why cloud computing services are typically required for network analysis. To leverage the advantages of serverless platforms, we propose faaShark , an end-to-end network traffic analysis system based on a serverless computing platform. faaShark adapts distributed training to fully utilize the flexibility of serverless platforms. Additionally, we design a cold start optimization algorithm to reduce the hit rate of cold start when serving pretrained models to handle network analysis requests. Our extensive experiments evaluate the impact of several parameters of distributed training and confirm the effectiveness of our cold start optimization algorithm when building such a network analysis system atop serverless computing frameworks.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2327-4697
2334-329X
DOI:10.1109/TNSE.2023.3294406