What type of study is this?

This is a Quantitative Study study.

October 2, 2025MATEC Web of ConferencesOpen Access

A deep reinforcement learning approach for flexible multipath routing using graph neural networks

View Full Paper

Ask AI

Bookmark

Authors

A new multipath routing model optimizes bandwidth allocation using deep reinforcement learning and graph neural networks, enhancing load balancing.

The proposed method improves total allocated bandwidth by 9.76% compared to traditional single-path models, demonstrating its efficiency.
Simulation experiments on realistic network topologies validate the effectiveness of a flexible routing strategy that uses deep reinforcement learning and graph neural networks.
The approach features a multi-path decision-making mechanism that optimally distributes traffic across selected paths to enhance network throughput.
A dynamic traffic allocation strategy aids in load balancing and alleviates congestion by responding to real-time capacities of selected paths.

Geng et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

A new multipath routing model optimizes bandwidth allocation using deep reinforcement learning and graph neural networks, enhancing load balancing.