Electronics Science Technology and Application

  • Home
  • About
    • About the Journal
    • Contact
  • Article
    • Current
    • Archives
  • Submissions
  • Editorial Team
  • Announcements
Register Login

ISSN

2424-8460(Online)

2251-2608(Print)

Article Processing Charges (APCs)

US$800

Publication Frequency

Quarterly

Download Full Text PDF

Published

2026-07-21

Issue

Vol 13 No 2 (2026): Published

Section

Articles

Research on intelligent network traffic classification and dynamic scheduling mechanism based on deep learning

Ming Tang

Communication University of China, Nanjing

Wenting Ding

Communication University of China, Nanjing

Hongxiu Duan

Communication University of China, Nanjing


DOI: https://doi.org/10.59429/esta.v13i2.14560


Keywords: deep learning; network traffic classification; attention mechanism; dynamic scheduling; feature extraction


Abstract

The explosive growth of network traffic and increasing complexity of service types have rendered traditional classification and scheduling methods inadequate for meeting efficient transmission demands. By leveraging convolutional neural networks and long short-term memory networks as core architectures, combined with attention mechanisms, this study proposes an intelligent traffic classification model that automatically extracts spatiotemporal traffic features, enabling precise identification of encrypted and complex traffic patterns. A dynamic scheduling mechanism is designed based on classification results to optimize resource allocation and transmission efficiency. Experimental results demonstrate that this approach significantly improves classification accuracy and network throughput, providing robust technical support for intelligent network management and security protection.


References

[1] Zhang X, Yin J. Optimized extreme learning machines with deep learning for high-performance network traffic classification[J]. Scientific Reports, 2025, 15(1): 33199.

[2] Agurto N D, Fuertes W, Marrone L, et al. A Novel Traffic Classification Approach by Employing Deep Learning on Software-Defined Networking[J]. Future Internet, 2024, 16(5): 153-.

[3] Gaba S, Budhiraja I, Kumar V, et al. Advancements in enhancing cyber-physical system security: Practical deep learning solutions for network traffic classification and integration with security technologies.[J]. Mathematical biosciences and engineering: MBE, 2024, 21(1): 1527-1553.

[4] Liu Youbang, Deng Yongzan. Computer Network Traffic Classification and Analysis Based on Deep Learning [J]. Information Recording Materials, 2025, 26(08): 28-30.

[5] He Erlu, Wu Xiangbo, Liu Lizhe, et al. Deep learning-based network baseline and encrypted traffic classification technology [J]. Journal of Cyberspace Security Science, 2024, 2(02): 76-85.



ISSN: 2424-8460
21 Woodlands Close #02-10 Primz Bizhub Singapore 737854

Email:editorial_office@as-pub.com