Open Access

ARTICLE

DRL-AMIR: Intelligent Flow Scheduling for Software-Defined Zero Trust Networks

Wenlong Ke^1,2,*, Zilong Li¹, Peiyu Chen¹, Benfeng Chen¹, Jinglin Lv¹, Qiang Wang², Ziyi Jia², Shigen Shen¹

1 School of Information Engineering, Huzhou University, Huzhou, 313000, China
2 National Key Laboratory of Advanced Communication Networks, Shijiazhuang, 050050, China

* Corresponding Author: Wenlong Ke. Email:

Computers, Materials & Continua 2025, 84(2), 3305-3319. https://doi.org/10.32604/cmc.2025.065665

Received 19 March 2025; Accepted 14 May 2025; Issue published 03 July 2025

Abstract

Zero Trust Network (ZTN) enhances network security through strict authentication and access control. However, in the ZTN, optimizing flow control to improve the quality of service is still facing challenges. Software Defined Network (SDN) provides solutions through centralized control and dynamic resource allocation, but the existing scheduling methods based on Deep Reinforcement Learning (DRL) are insufficient in terms of convergence speed and dynamic optimization capability. To solve these problems, this paper proposes DRL-AMIR, which is an efficient flow scheduling method for software defined ZTN. This method constructs a flow scheduling optimization model that comprehensively considers service delay, bandwidth occupation, and path hops. Additionally, it balances the differentiated requirements of delay-critical K-flows, bandwidth-intensive D-flows, and background B-flows through adaptive weighting. The proposed framework employs a customized state space comprising node labels, link bandwidth, delay metrics, and path length. It incorporates an action space derived from node weights and a hybrid reward function that integrates both single-step and multi-step excitation mechanisms. Based on these components, a hierarchical architecture is designed, effectively integrating the data plane, control plane, and knowledge plane. In particular, the adaptive expert mechanism is introduced, which triggers the shortest path algorithm in the training process to accelerate convergence, reduce trial and error costs, and maintain stability. Experiments across diverse real-world network topologies demonstrate that DRL-AMIR achieves a 15–20% reduction in K-flow transmission delays, a 10–15% improvement in link bandwidth utilization compared to SPR, QoSR, and DRSIR, and a 30% faster convergence speed via adaptive expert mechanisms.

---

Keywords

---