Title: A traffic classification-based traffic engineering framework in software-defined networking

Authors: Chih-Yu Lin; Chien-Cheng Wu; Hong-Yi Huang

Addresses: Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung, 202301, Taiwan ' Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung, 202301, Taiwan ' Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung, 202301, Taiwan

Abstract: Traffic engineering is used to optimise network performance. Due to the dynamic nature of the network environment, devising an efficient traffic engineering approach attracts more attention in next-generation networks. However, network performance optimisation is challenging due to stringent requirements and the need for global observation within the dynamic network environment. Fortunately, software-defined networking (SDN) can provide an abstract global view of the complete network environment, so we are motivated to leverage the SDN framework to construct next-generation networks. In this study, we propose a traffic engineering framework for SDN. Our proposed framework optimises transmission paths by employing traffic classification techniques. In addition, we divide this framework into three modules that can operate independently. Therefore, compared with conventional methods, our proposed framework shows greater flexibility. The superiority of our approach has been verified through rigorous testing on the Mininet simulator and the Ryu controller. Finally, we firmly believe that our contribution opens new avenues for more efficient and optimised network management.

Keywords: network performance optimisation; SDN; software-defined networking; traffic classification; traffic engineering; Mininet; Ryu.

DOI: 10.1504/IJCNDS.2026.150916

International Journal of Communication Networks and Distributed Systems, 2026 Vol.32 No.1, pp.33 - 57

Received: 20 Apr 2024
Accepted: 22 Dec 2024

Published online: 05 Jan 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article