A dynamic and resource sharing virtual network mapping algorithm

Xiao, Xiancui; Zheng, Xiangwei; Bian, Ji; Ji, Cun; Cui, Xinchun

doi:10.1016/j.dcan.2022.06.011

Cited by 3 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concept of the complex network matured in the late 1990s, developing from topology theory, which primarily manifests in a strong diversity of network nodes and connections, a complex network structure, and an evident cluster effect [49].The analysis of complex networks mainly focuses on the network structure characteristics and the discovery of key nodes [50]. In recent years, the theory of complex networks has developed rapidly and has been widely used in research into trade networks [51][52][53], transportation networks [54,55], and virtual resource trading networks with good results [56][57][58]. Rural migrants embody the population mobility relationship between different regions, and this is an appropriate topic for the application of complex network analysis.…”

Section: Complex Network Analysis Methodsmentioning

confidence: 99%

Dynamic Characteristics and Evolution Analysis of China’s Rural Population Migration Networks from 2000 to 2020 Based on the Perspective of Regional Differences

Zhou

Fang

2023

Systems

View full text Add to dashboard Cite

The large-scale cross-regional migration of rural migrants is a significant feature of the current social system in China, affecting the sustainability of social and economic development. Using China National Census data and socio-economic panel data, we applied the complex network analysis method to construct a rural population migration network and analyze its characteristics, evolution, and mechanisms of network formation and changes. The research findings are as follows: (1) From 2000 to 2020, the rural population migration network developed rapidly, the network scope expanded continuously, regional participation gradually grew, and the inter-regional rural population migration relationship became increasingly complex. The overall network gradually evolved from an early segmented and loose structure to a monolithic and solid structure. (2) The in-degree centralization of the network remained higher than the out-degree centralization. The inbound migration pattern of the rural population was more compact than the outbound migration pattern, and the internal network displayed aggregated inbound population migration and dispersed outbound population migration flow characteristics. (3) The network had a distinctive “core–edge” character, with the core areas and the main migration flows in the network demonstrating high similarity across different periods. The overall network gradually developed around the core areas where the rural population moved in and out. (4) The influence mechanism between the later migration network and the geographical differences was more complex than in the early period. Differences in the regional development levels and geographical factors continued to influence the mobility choices of the rural population, whereas differences in income levels, cost of living, employment opportunities, and education funding only affected the rural migration network during specific periods. Based on these findings, reasonable migration policies should be formulated to ensure sustainable urban and rural development.

show abstract

Section: Complex Network Analysis Methodsmentioning

confidence: 99%

Dynamic Characteristics and Evolution Analysis of China’s Rural Population Migration Networks from 2000 to 2020 Based on the Perspective of Regional Differences

Zhou

Fang

2023

Systems

View full text Add to dashboard Cite

show abstract

“…One is service provider (SP), whose task is to create customized virtual networks (VNS) to provide end-to-end network services for users. The other is a physical network provider whose function is to maintain infrastructure (InP) equipment so that the former SP can adopt them to host their services at an acceptable business cost [5,6]. It turns out that good coordination between these two roles can improve the practicality and commercial value of physical network devices.…”

Section: Introductionmentioning

confidence: 99%

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

Xiao¹

2023

Preprint

Self Cite

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

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

Xiao

2023

Sci Rep

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 a Markov Decision Process (MDP), and then deep learning is introduced to perceive the current network state through historical data and embedded knowledge, while utilizing reinforcement learning decision-making capabilities to implement the network embedding process. In addition, we improve the method of feature extraction and matrix optimization, and consider 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.

show abstract

A dynamic and resource sharing virtual network mapping algorithm

Cited by 3 publications

References 27 publications

Dynamic Characteristics and Evolution Analysis of China’s Rural Population Migration Networks from 2000 to 2020 Based on the Perspective of Regional Differences

Dynamic Characteristics and Evolution Analysis of China’s Rural Population Migration Networks from 2000 to 2020 Based on the Perspective of Regional Differences

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

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

Contact Info

Product

Resources

About