DNFS-VNE: Deep Neuro Fuzzy System Driven Virtual Network Embedding

TL;DR

This work tackles interpretable virtual network embedding (VNE) by marrying deep neuro fuzzy systems (DNFS) with reinforcement learning to form DNFS-VNE, a five-block architecture that uses CNNs as fuzzy implication operators and Mamdani-type rules for interpretability. A five-block DNFS-based policy network drives DRL-based embedding decisions, while the fuzzy rule base is learned and cached within the network weights, enabling transparent reasoning about substrate-node embeddings. The approach demonstrates improvements over baselines in long-term revenue, revenue-cost efficiency, and acceptance rates, with explicit generated rules that reveal how resource levels influence embedding outcomes. The framework thus provides a practical, interpretable avenue for dynamic, multi-domain VNE with potential extensions to additional resource dimensions.

Abstract

By decoupling substrate resources, network virtualization (NV) is a promising solution for meeting diverse demands and ensuring differentiated quality of service (QoS). In particular, virtual network embedding (VNE) is a critical enabling technology that enhances the flexibility and scalability of network deployment by addressing the coupling of Internet processes and services. However, in the existing deep neural networks (DNNs)-based works, the black-box nature DNNs limits the analysis, development, and improvement of systems. For example, in the industrial Internet of Things (IIoT), there is a conflict between decision interpretability and the opacity of DNN-based methods. In recent times, interpretable deep learning (DL) represented by deep neuro fuzzy systems (DNFS) combined with fuzzy inference has shown promising interpretability to further exploit the hidden value in the data. Motivated by this, we propose a DNFS-based VNE algorithm that aims to provide an interpretable NV scheme. Specifically, data-driven convolutional neural networks (CNNs) are used as fuzzy implication operators to compute the embedding probabilities of candidate substrate nodes through entailment operations. And, the identified fuzzy rule patterns are cached into the weights by forward computation and gradient back-propagation (BP). Moreover, the fuzzy rule base is constructed based on Mamdani-type linguistic rules using linguistic labels. In addition, the DNFS-driven five-block structure-based policy network serves as the agent for deep reinforcement learning (DRL), which optimizes VNE decision-making through interaction with the environment. Finally, the effectiveness of evaluation indicators and fuzzy rules is verified by simulation experiments.

Figures (11)

• Figure 1: Schematic diagram of the VNE process that the VNRs of two users are embedded into the substrate network, where the numbers indicate the relevant network metrics.
• Figure 2: Schematic diagram of the corresponding relationship between substrate resources and virtual resources.
• Figure 3: The five-layer feed-forward network structure of DNFS.
• Figure 4: The policy network diagram of the proposed DNFS-VNE algorithm.
• Figure 5: Eq. \ref{['eq5']} in the training process.