Automatic Network Traffic Scheduling Algorithm Based on Hierarchical Reinforcement Learning

This paper proposes an intelligent network traffic scheduling algorithm based on deep reinforcement learning and graph neural network (GNN) to solve traffic scheduling problems in large-scale dynamic network environments. The algorithm combines the decision-making ability of deep reinforcement learning and the advantage of GNNs in processing graph structure data. Through hierarchical reinforcement learning framework, it realizes efficient decision-making process from macro-strategy formulation to micro-operation execution. Experimental results show that compared with traditional algorithms, the proposed algorithm has significant advantages in key performance indicators such as average delay time, throughput and resource utilization. The algorithm not only surpasses Dijkstra, Shortest Path First (SPF) and Weighted Round Robin (WRR) algorithms under standard test conditions, but also shows excellent robustness and generalization ability under complex scenarios such as different traffic demand intensity, link failure and network topology change. Experimental results show that the proposed traffic scheduling algorithm based on deep reinforcement learning and graph neural network has significant advantages in multiple key performance indicators. Specifically, in a large-scale network environment (including 100,000 traffic flows and 3,000 links, each with a bandwidth of 1 Gbps), compared with the Dijkstra algorithm, the shortest path first (SPF) algorithm, and the weighted round-robin (WRR) algorithm, the proposed algorithm achieves lower average latency (10.5 milliseconds vs. 16.2 milliseconds), higher throughput (9800 Mbps vs. 8900 Mbps), and better resource utilization (92% vs. 85%). In addition, the algorithm also shows good adaptability, maintaining low latency under different traffic demand intensities while improving overall network performance. In addition, through model optimization and parameter adjustment, the convergence speed and learning efficiency of the algorithm are significantly improved when dealing with large-scale networks, which provides strong technical support for automatic network traffic management. © 2024 Slovene Society Informatika. All rights reserved.