FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation

TL;DR

FlagVNE introduces a flexible, bidirectional RL framework with hierarchical and meta-learning components to improve virtual network embedding, achieving better exploration, efficiency, and generalization over existing methods.

Contribution

The paper presents a novel RL framework with bidirectional actions, hierarchical decoding, and meta-learning for VNE, enhancing flexibility and generalization.

Findings

Outperforms existing RL-based VNE methods on key metrics

Demonstrates improved exploration and training efficiency

Achieves better generalization across VNR sizes

Abstract

Virtual network embedding (VNE) is an essential resource allocation task in network virtualization, aiming to map virtual network requests (VNRs) onto physical infrastructure. Reinforcement learning (RL) has recently emerged as a promising solution to this problem. However, existing RL-based VNE methods are limited by the unidirectional action design and one-size-fits-all training strategy, resulting in restricted searchability and generalizability. In this paper, we propose a FLexible And Generalizable RL framework for VNE, named FlagVNE. Specifically, we design a bidirectional action-based Markov decision process model that enables the joint selection of virtual and physical nodes, thus improving the exploration flexibility of solution space. To tackle the expansive and dynamic action space, we design a hierarchical decoder to generate adaptive action probability distributions and ensure high training efficiency. Furthermore, to overcome the generalization issue for varying VNR sizes, we propose a meta-RL-based training method with a curriculum scheduling strategy, facilitating specialized policy training for each VNR size. Finally, extensive experimental results show the effectiveness of FlagVNE across multiple key metrics. Our code is available at GitHub (https://github.com/GeminiLight/flag-vne).