VNE solution for network differentiated QoS and security requirements: from the perspective of deep reinforcement learning

Wang, Chao; Batth, Ranbir Singh; Zhang, Peiying; Aujla, Gagangeet Singh; Duan, Youxiang; Liu, Ren

doi:10.1007/s00607-020-00883-w

Cited by 23 publications

(6 citation statements)

References 50 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RL agent collects the historical mapping data of the virtual network and optimizes the VNE mapping strategy using the policy gradient descent method. The VNE algorithm proposed by Yao et al [30] and Dolati et al [31] combines deep learning (DL) and RL, which also provides some inspirations for solving VNE problems. At present, VNE solutions based on machine learning mainly adopt DL, RL or graph theory [32,33,34].…”

Section: Vne Algorithm Based On Machine Learningmentioning

confidence: 99%

DVNE-DRL: Dynamic virtual network embedding algorithm based on deep reinforcement learning

Xiao¹

2023

Preprint

View full text Add to dashboard Cite

Virtual Network Embedding (VNE), as the key challenge of network resource management technology, lies in the contradiction between online embedding decision and pursuing long-term average revenue goals. Most of the previous work ignored the dynamics in Virtual Network (VN) modeling, or could not automatically detect the complex and time-varying network state to provide a reasonable network embedding scheme. In view of this, we model a network embedding framework where the topology and resource allocation change dynamically with the number of network users and workload, and then introduce a deep reinforcement learning method to solve the VNE problem. Further, a dynamic virtual network embedding algorithm based on Deep Reinforcement Learning (DRL), named DVNE-DRL, is proposed. In DVNE-DRL, VNE is modeled as Markov Decision Process (MDP), and Reinforcement Learning Agent (RLA) is used to periodically detect the state of network environment and provide a more reasonable network embedding scheme in real time. Different from the previous methods based on DRL algorithm to solve VNE problem, this paper improves the method of feature extraction and matrix optimization, and considers the characteristics of virtual network and physical network together to alleviate the problem of redundancy and slow convergence. The simulation results show that compared with the existing advanced algorithms, the acceptance rate and average revenue of DVNE-DRL are increased by about 25% and 35%, respectively. K E Y W O R D S VNE, DRL, embedding framework, DRL-DVNE，MDP，feature extraction

show abstract

Section: Vne Algorithm Based On Machine Learningmentioning

confidence: 99%

DVNE-DRL: Dynamic virtual network embedding algorithm based on deep reinforcement learning

Xiao¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors of [28] and [29] also combined DL and RL, and their deep reinforcement learning (DRL) based VNE algorithm also provided new ideas for solving this problem.…”

Section: B Vne Solution Based On MLmentioning

confidence: 99%

Dynamic Virtual Network Embedding Algorithm based on Graph Convolution Neural Network and Reinforcement Learning

Zhang¹,

Wang²,

Kumar³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Network virtualization (NV) is a technology with broad application prospects. Virtual network embedding (VNE) is the core orientation of VN, which aims to provide more flexible underlying physical resource allocation for user function requests. The classical VNE problem is usually solved by heuristic method, but this method often limits the flexibility of the algorithm and ignores the time limit. In addition, the partition autonomy of physical domain and the dynamic characteristics of virtual network request (VNR) also increase the difficulty of VNE. This paper proposed a new type of VNE algorithm, which applied reinforcement learning (RL) and graph neural network (GNN) theory to the algorithm, especially the combination of graph convolutional neural network (GCNN) and RL algorithm. Based on a self-defined fitness matrix and fitness value, we set up the objective function of the algorithm implementation, realized an efficient dynamic VNE algorithm, and effectively reduced the degree of resource fragmentation. Finally, we used comparison algorithms to evaluate the proposed method. Simulation experiments verified that the dynamic VNE algorithm based on RL and GCNN has good basic VNE characteristics. By changing the resource attributes of physical network and virtual network, it can be proved that the algorithm has good flexibility.

show abstract

“…Wireless network is a physical infrastructure that allows computers, mobile phones, printers, and other devices to communicate with each other via a router. Ad hoc sensor networks are being organized in numerous areas such as the military, health care, and defence as a result of technical advancements [1].…”

Section: Introductionmentioning

confidence: 99%

Vampire Attack Mitigation and Network Performance Improvement Using Probabilistic Fuzzy Chain Set with Authentication Routing Protocol and Hybrid Clustering-Based Optimization in Wireless Sensor Network

Alkwai

Aledaily

Almansour

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The most effective threat for wireless sensor networks (WSN) is Vampire attacks on sensor nodes as they can stretch the network connectivity among them and influence the network’s energy, which can drain the network. Vampire attack has particular malicious nature of sensor nodes in which they can widely exploit features of combined routing protocol. Fuzzy rules and fuzzy sets are highly optimal techniques in mitigating the vampire attacks of the network, which can quantify the uncertain behaviour of sensor nodes. This study aims to propose a novel technique using a probabilistic fuzzy chain set with authentication-based routing protocol and hybrid clustering technique for data optimization of the network. The suggested approach here employs a fuzzy-based chain rule set to combat growing types of vampire assaults using probability formulas. The authentication routing protocol has increased network routing security. The proposed technique (PFCS-ARP_HC) has optimized the energy consumption of network. Simulation for this technique has been carried out using NS2 and experimental results show the performance of the proposed model in terms of throughput of 98%, packet delivery ratio of 89%, energy consumption of 67%, latency of 46% control overhead of 53%, and attack detection ratio of 87.9%.

show abstract

VNE solution for network differentiated QoS and security requirements: from the perspective of deep reinforcement learning

Cited by 23 publications

References 50 publications

DVNE-DRL: Dynamic virtual network embedding algorithm based on deep reinforcement learning

DVNE-DRL: Dynamic virtual network embedding algorithm based on deep reinforcement learning

Dynamic Virtual Network Embedding Algorithm based on Graph Convolution Neural Network and Reinforcement Learning

Vampire Attack Mitigation and Network Performance Improvement Using Probabilistic Fuzzy Chain Set with Authentication Routing Protocol and Hybrid Clustering-Based Optimization in Wireless Sensor Network

Contact Info

Product

Resources

About