Next Article in Journal
Elasticsearch-Based Threat Hunting to Detect Privilege Escalation Using Registry Modification and Process Injection Attacks
Previous Article in Journal
Hybrid B5G-DTN Architecture with Federated Learning for Contextual Communication Offloading
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

RS-MADDPG: Routing Strategy Based on Multi-Agent Deep Deterministic Policy Gradient for Differentiated QoS Services

1
Transmission Operation and Inspection Center, State Grid Zhengzhou Electric Power Supply Company, Zhengzhou 450007, China
2
DC Branch, State Grid Henan Electric Power Company, Zhengzhou 450052, China
3
College of Big Data and Artificial Intelligence, Zhengzhou University of Economics and Business, Zhengzhou 450099, China
4
College of Electronics and Communication Engineering, Shenzhen Polytechnic University, Shenzhen 518005, China
5
College of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou 450007, China
*
Author to whom correspondence should be addressed.
Future Internet 2025, 17(9), 393; https://doi.org/10.3390/fi17090393
Submission received: 31 July 2025 / Revised: 24 August 2025 / Accepted: 27 August 2025 / Published: 29 August 2025

Abstract

As network environments become increasingly dynamic and users’ Quality of Service (QoS) demands grow more diverse, efficient and adaptive routing strategies are urgently needed. However, traditional routing strategies suffer from limitations such as poor adaptability to fluctuating traffic, lack of differentiated service handling, and slow convergence in complex network scenarios. To this end, we propose a routing strategy based on multi-agent deep deterministic policy gradient for differentiated QoS services (RS-MADDPG) in a software-defined networking (SDN) environment. First, network state information is collected in real time and transmitted to the control layer for processing. Then, the processed information is forwarded to the intelligent layer. In this layer, multiple agents cooperate during training to learn routing policies that adapt to dynamic network conditions. Finally, the learned policies enable agents to perform adaptive routing decisions that explicitly address differentiated QoS requirements by incorporating a custom reward structure that dynamically balances throughput, delay, and packet loss according to traffic type. Simulation results demonstrate that RS-MADDPG achieves convergence approximately 30 training cycles earlier than baseline methods, while improving average throughput by 3%, reducing latency by 7%, and lowering packet loss rate by 2%.
Keywords: quality of service; routing strategy; multi-agent deep deterministic policy gradient; software-defined networking quality of service; routing strategy; multi-agent deep deterministic policy gradient; software-defined networking

Share and Cite

MDPI and ACS Style

Kuang, S.; Zheng, J.; Liang, S.; Li, Y.; Liang, S.; Huang, W. RS-MADDPG: Routing Strategy Based on Multi-Agent Deep Deterministic Policy Gradient for Differentiated QoS Services. Future Internet 2025, 17, 393. https://doi.org/10.3390/fi17090393

AMA Style

Kuang S, Zheng J, Liang S, Li Y, Liang S, Huang W. RS-MADDPG: Routing Strategy Based on Multi-Agent Deep Deterministic Policy Gradient for Differentiated QoS Services. Future Internet. 2025; 17(9):393. https://doi.org/10.3390/fi17090393

Chicago/Turabian Style

Kuang, Shi, Jinyu Zheng, Shilin Liang, Yingying Li, Siyuan Liang, and Wanwei Huang. 2025. "RS-MADDPG: Routing Strategy Based on Multi-Agent Deep Deterministic Policy Gradient for Differentiated QoS Services" Future Internet 17, no. 9: 393. https://doi.org/10.3390/fi17090393

APA Style

Kuang, S., Zheng, J., Liang, S., Li, Y., Liang, S., & Huang, W. (2025). RS-MADDPG: Routing Strategy Based on Multi-Agent Deep Deterministic Policy Gradient for Differentiated QoS Services. Future Internet, 17(9), 393. https://doi.org/10.3390/fi17090393

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop