Source-linked AI summary
Machine Learning for Networking: Workflow, Advances and Opportunities
Mowei Wang, Yong Cui, Xin Wang, Shihan Xiao, Junchen Jiang
TL;DR
Networking’s diversity, dynamism, and complexity make efficient algorithms difficult, while conventional traffic classification also faces port instability, privacy concerns, and encryption. This article presents an MLN workflow and selective survey, reporting that machine-learning approaches can match heuristic scheduling performance and outperform prediction-based systems in cited applications.
Problem
Networking’s diverse, dynamic scenarios make efficient algorithms challenging, while traditional traffic-classification methods face ineffective port assignments, privacy concerns, and encrypted traffic.
Method
The paper summarizes an MLN workflow and selectively surveys recent machine-learning advances across networking fields, explaining their design principles and workflow stages.
Results
Surveyed advances include DeepRM matching state-of-the-art heuristic scheduling with less cost and Pytheas outperforming prediction-based systems by reducing prediction bias and delayed response.
Takeaways & Limitations
The synthesis provides a practical starting guideline for MLN research and identifies opportunities for networking design and community building.
Takeaways & Limitations
Real-world MLN methods still require robustness, generalization under changing traffic distributions, and interpretable behavior under hard networking constraints.
Abstract
from arXiv · showhide
Recently, machine learning has been used in every possible field to leverage its amazing power. For a long time, the net-working and distributed computing system is the key infrastructure to provide efficient computational resource for machine learning. Networking itself can also benefit from this promising technology. This article focuses on the application of Machine Learning techniques for Networking (MLN), which can not only help solve the intractable old network questions but also stimulate new network applications. In this article, we summarize the basic workflow to explain how to apply the machine learning technology in the networking domain. Then we provide a selective survey of the latest representative advances with explanations on their design principles and benefits. These advances are divided into several network design objectives and the detailed information of how they perform in each step of MLN workflow is presented. Finally, we shed light on the new opportunities on networking design and community building of this new inter-discipline. Our goal is to provide a broad research guideline on networking with machine learning to help and motivate researchers to develop innovative algorithms, standards and frameworks.
Conclusions · Biographies
The biographies describe Mowei Wang’s academic training and research interests, alongside Yong Cui’s academic career, publication record, standards contributions, and research interests.
- Biographies: Mowei Wang earned a B.Eng. in communication engineering from Beijing University of Posts and Telecommunications in 2017.
- Biographies: Mowei Wang is pursuing a Ph.D. in computer science and technology at Tsinghua University.
- Biographies: Mowei Wang researches data center networks and machine learning.
- Biographies: Yong Cui earned computer science and engineering degrees from Tsinghua University in 1999 and 2004.
- Biographies: Yong Cui is a full professor in Tsinghua University’s Computer Science Department.
- Biographies: Yong Cui has published over 100 refereed conference and journal papers and received several Best Paper Awards.
- Biographies: Yong Cui co-authored seven Internet standard documents for his IPv6 technology proposal.
- Biographies: Yong Cui’s major research interests include mobile technologies.