Virtual Network Embedding Research Articles

Spectral graph theory-based virtual network embedding for vehicular fog computing: A deep reinforcement learning architecture

In the intelligent transportation system (ITS), the vehicular fog computing network (VFCN) can effectively alleviate the bottleneck existing in the cloud computing framework, such as high latency-sensitive applications, through edge computing offloading. It uses vehicles as the infrastructure, and fog nodes can communicate, perceive and share resources, so resource orchestration has become an essential issue of VFCN. To reduce the communication transportation cost and improve the resource utilization of VFCN, we propose a spectral graph theory-based resource orchestration algorithm by combining Virtual Network Embedding (VNE) and Deep Reinforcement Learning (DRL). Specifically, we propose a four-layer strategy network based on Graph Convolutional Networks (GCNs) for computing node embedding probability, where fog nodes fully mine spatial structure information by fusing themselves with neighborhood information to compensate for the lack of traditional heuristic VNE. Moreover, fog link embedding is performed by breadth-first search (BFS). Finally, the effectiveness of the proposed strategy is scientifically and rigorously proved in terms of long-term average revenue, long-term average revenue-cost ratio, and VNR acceptance rate through simulation cases, which can reasonably arrange the resources of VFCN.

A robust control-theory-based exploration strategy in deep reinforcement learning for virtual network embedding

Network slice management and, more generally, resource orchestration should be fully automated in 6G networks, as envisioned by the ETSI ENI. In this context, artificial intelligence (AI) and context-aware policies are certainly major options to move in this direction and to adapt service delivery to changing user needs, environmental conditions and business objectives. In this paper, we step towards this objective by addressing the problem of optimal placement of dynamic virtual networks through a self-adaptive learning-based strategy. These constantly evolving networks present, however, several challenges, mainly due to their stochastic nature, and the high dimensionality of the state and the action spaces. This curse of dimensionality requires, indeed, a broader exploration, which is not always compatible with a real-time execution in an operational network. Thus, we propose DQMC, a new strategy for virtual network embedding in mobile networks combining a Deep Reinforcement Learning (DRL) strategy, namely a Deep Q-Network (DQN), and Monte Carlo (MC). As learning is costly in time and computing resources, and sensitive to changes in the network, we suggest a control-theory-based techniques to dynamically leverage exploration in DQMC. This leads to fast, efficient, and sober learning compared to a Monte Carlo-based strategy. This also ensures a reliable solution even in the case of a change in the requests’ sizes or a node’s failure, showing promising perspectives for solutions combining control-theory and machine learning.

Dynamic Reliability-Aware Virtual Network Embedding for Airborne Tactical Networks

Airborne tactical networks (ATNs) built on network virtualization (NV) can enable efficient information sharing for network-centric warfare by breaking the tight coupling between applications and network infrastructure and thus solving the network ossification problem. With dynamic changes during military missions, the application of virtualization is challenged by the changing demands on network resources when instantiating multiple virtual networks (VNs) on a shared substrate network (SN), known as virtual network embedding (VNE). However, existing dynamic VNE algorithms, mostly designed for wired networks, focus on the dynamic changes of single VN and do not consider the dynamic changes of different VNs. The proper processing of changes of different VNs is beneficial to improve the embedding profits of VNs. On these backgrounds, we investigate the dynamic wireless VNE that processes the dynamic changes of different VNs in the wireless environment of ATNs. A relationship matrix-based dynamic wireless VNE (DWVNE-RM) algorithm is proposed in order to maximize the acceptance ratio of VN requests. The dynamic changes of different VNs are classified into negative changes (requiring resource) and positive changes (releasing resource). Then, the relationship matrix between negative and positive changes is constructed to properly process the resource relationship among different changes in order to improve the acceptance ratio. In addition, the complex interference of ATNs is considered in the mapping or remapping of virtual nodes and links to improve the reliability. Through extensive simulation, DWVNE-RM is compared with multiple existing dynamic algorithms and outperforms over others.

Edge computing network resource allocation based on virtual network embedding

SummaryIt is expected that the demand for quality of service (QoS) and quality of experience (QoE) in future 6G scenarios will continue to increase, and edge computing (EC) will continue to receive widespread attention. However, the highly dynamic and connectivity complexity of edge computing networks (ECNs) pose severe challenges to its resource allocation issues. In addition, network virtualization (NV) is widely applied to increase the flexibility of network architectures. Based on the above inspirations, we adopt virtual network embedding (VNE) to make decisions on the resource allocation of ECN. Specifically, we deploy a deep reinforcement learning (DRL)‐based multi‐layer policy network, which is applied to extract environmental information, calculate the available resources of edge nodes, and screen candidate edge nodes that satisfy resource allocation conditions. Second, the resources of edge links are allocated according to the shortest path algorithm. Finally, we build a simulation environment to demonstrate the advantages of the proposed policy network through rich experiments.

Application of Meta-Heuristics in 5G Network Slicing: A Systematic Review of the Literature.

Network slicing is a vital component of the 5G system to support diverse network scenarios, creating virtual networks (slices) by mapping virtual network requests to real networks. The mapping is an arduous computing process, mathematically studied and known as the Virtual Network Embedding (VNE) problem, and its complexity is NP-Hard. The mapping process is oriented to respect the QoS demands from the virtual network requests and the available resources in the physical-substrate infrastructure. Meta-heuristic approaches are a suitable way to solve the VNE problems because of their capacity to escape from the local optimum and adapt the solution search to complex networks; these abilities are essential in 5G networks scenarios. This article presents a systematic review of meta-heuristics organized by application, development and problem-solving approaches to VNE. It also provides the standard parameters to model the infrastructure and virtual network requests to simulate network slicing as a service. Finally, our work proposes some future research based on the discovered gaps.

Shared Protection-Based Virtual Network Embedding Over Elastic Optical Networks

This paper proposes a survivable virtual network embedding model over elastic optical networks considering shared protection against any single substrate node or link failure. A virtual network request is embedded in the substrate network with allocating the primary and backup resources which are node-disjoint. Modulation selection and spectrum allocation with constraints from elastic optical networks are considered in the embedding procedure. We consider the backup computing and transmission resource sharing to reduce the required backup resources. We formulate the proposed model as an integer linear programming problem to minimize the rejection ratio for a given set of virtual network requests. We introduce a greedy-based approach that promotes resource sharing to handle the larger-size problem in a practical time. In order to further improve the performance on the objective value, a deep reinforcement learning-based approach with polynomial time complexity in each episode is developed to solve the problem in multiple stages. We design a dedicated learning agent for each stage considering the problem property. We analyze the usages of different approaches based on performance evaluation. The numerical results show that, compared to a conventional model that adopts dedicated protection, the proposed model with shared protection reduces the rejection ratio by 15% on average in our examined cases.

Wireless Virtual Network Embedding Algorithm Based on Deep Reinforcement Learning

Wireless network virtualization is widely used to solve the ossification problem of networks, such as 5G and the Internet of Things. The most crucial method of wireless network virtualization is virtual network embedding, which allows virtual networks to share the substrate network resources. However, in wireless networks, link interference is an inherent problem while mapping virtual networks because of the characteristics of wireless channels. To distribute resources efficiently and address the problem of interference, a dynamic embedding algorithm with deep reinforcement learning is proposed. During the training stage, we take resource use and interference from substrate networks as observations to train the agent, and then the agent generates a resource allocation strategy. Aiming at realizing load balance, we reshape the reward function considering the execution ratio and residual ratio of substrate network resources as well as the cost consumed by current virtual network request. Numerical tests show that our embedding approach increases the acceptance ratio and maintains better robustness. Moreover, the results also illustrate that our algorithm maintains a high acceptance ratio while producing less interference and lower cost.

A Heuristic Fuzzy Based 5G Network Orchestration Framework for Dynamic Virtual Network Embedding

Network slicing has become an unavoidable requirement for allocating 5G mobile network resources when sharing resources among devices that have varying needs. As a result, the virtual network slices get resources from the shared physical infrastructure that matches their needs. In order to maximize the use of shared resources, it is critical to provide an efficient virtual network embedding strategy for mapping each user’s requests to a physical infrastructure. Virtual network embedding primarily deals with the two most important network parameters—node mapping and link mapping. This paper proposes the heuristic fuzzy algorithm for node mapping and Dijikstra’s algorithm for link mapping. The proposed fuzzy based multi-criteria decision making technique uses membership functions for node parameters to prepare node mapping. By determining the shortest path, Dijikstra’s algorithm is used to provide link mapping. The proposed strategy is tested under dynamic physical infrastructure conditions for validation. The average acceptance ratio, costrevenue ratio, and average utilization of node capacity and link bandwidth are used to evaluate the performance of the proposed strategy. In addition, the obtained results are compared to the literature to show that the proposed strategy is effective.

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

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 the 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 article 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.

Conflict-Based Search for the Virtual Network Embedding Problem

In emerging network virtualization architectures, service providers will be able to create many heterogeneous virtual networks and offer customized end-to-end services by leasing shared resources from infrastructure providers. The Virtual Network Embedding (VNE) problem is central to such technology. It involves the proper allocation of CPU and bandwidth resources available in a physical substrate network to meet the demands of multiple virtual networks. Combinatorially, the VNE problem is a problem in resource management that is NP-hard to solve. In this paper, we present a novel version of the Conflict-Based Search (CBS) algorithm for solving the VNE problem. Our approach, called VNE-CBS, is inspired by the success of the CBS framework in the Multi-Agent Path Finding domain. We successfully address the unique challenges in applying the CBS framework to the VNE problem, and, in doing so, we pave the way for overcoming a crucial issue in Internet ossification via heuristic search methods. On the theoretical front, we show that, unlike many existing algorithms, our algorithm is complete and optimal. On the experimental front, we show that our algorithm significantly outperforms other state-of-the-art methods on various benchmark instances for both the offline and online versions of the VNE problem.

Survivable virtual network embedding algorithm considering multiple node failure in IIoT environment

The Industrial Internet of Things is a new ecology formed by the deep integration of the Internet of Things and the industrial environment. Network is one of the core technologies of industrial Internet of things. However, in the face of billions of industrial Internet of Things applications, the traditional network architecture cannot meet the needs of these applications for network resources. Network virtualization technology can effectively solve the above problems by decoupling network services from the underlying network. However, the existing heuristic virtual network embedding algorithm is easy to fall into the local optimum, such as the virtual network embedding algorithm based on particle swarm optimization. Therefore, in order to solve the above problems, a virtual network embedding strategy based on the hybrid whale optimization algorithm is proposed. This strategy can avoid the introduction of the population into the local optimum while reducing the amount of calculation. Secondly, a node importance measurement strategy based on weighted aggregation coefficient and traffic prediction is introduced. This strategy can conduct a more reasonable and effective assessment of the importance of nodes. Thirdly, to reduce resource occupation and improve network security and stability, we propose a multi-node failure recovery strategy. It depends on the construction of candidate nodes and the selection of recovery points. Simulation results show that compared with other algorithms, the proposed algorithm reduces the cost and maintains a high success rate of fault recovery. In addition, its request acceptance rate is twice that of other algorithms.

Resource Fragmentation-Aware Embedding in Dynamic Network Virtualization Environments

In network virtualization environments, with random arrival and departure of virtual network requests, there exist some resources (i.e., link resources and node resources) isolated from others in substrate networks. This phenomenon is referred to as resource fragmentation. In this paper, we attempt to improve the resource utilization efficiency by avoiding resource fragmentation in substrate networks. First and most importantly, we define a new metric called resource fragmentation degree (RFD) to quantitatively measure the status of resource fragmentation at substrate nodes and links. The basic idea of RFD is that the resource availability of a node (or a link) is determined by the residual link and node resources around the node (or the link). Based on the definition of RFD, we formulate the virtual network embedding (VNE) problem as a mixed integer programming problem with consideration of the cost of resource fragmentation. Then, an online VNE algorithm with consideration of RFD (VNERFD) is proposed to solve the problem, which is performed according to the current resource status of substrate networks and virtual network requests. To reduce accumulated fragmented resources produced by dynamic arrival and departure of virtual network requests, a heuristic virtual network reconfiguration algorithm based on RFD (VNR-RFD) is proposed. Simulation results show that VNE-RFD and VNR-RFD can effectively reduce fragmented resources and thus embed more virtual networks into substrate networks.

Secure Virtual Network Embedding Algorithms for a Software-Defined Network Considering Differences in Resource Value

Software-defined networking (SDN) and network virtualization (NV) are key technologies for future networks, which allow telecommunication service providers (TSPs) to share network resources with users in a flexible manner. Since TSPs have limited virtualized network resources, it is critical to develop effective virtual network embedding (VNE) algorithms for an SDN network to improve resource utilization. However, most existing VNE algorithms ignore the security issues of SDN networks, which may be subject to malicious attacks due to their openness feature. Therefore, it is necessary to develop secure VNE (SVNE) for SDN networks. In this paper, we researched the relationship between resource value and node security-level, and we found that there are differences in the resource value of different nodes. Based on this analysis, we define the evaluation indicators considering differences in resource value for the SVNE problem. Then, we present a mixed-integer linear program (MILP) model to minimize the cost of SVNE. As the formulated optimization problem cannot be solved conveniently, we design two node-ranking approaches to rank physical and virtual nodes, respectively, and we propose two novel SVNE algorithms based on the node ranking approaches. Finally, simulation results reveal that our proposed algorithm is superior to other typical algorithms.

RKD-VNE: Virtual network embedding algorithm assisted by resource knowledge description and deep reinforcement learning in IIoT scenario

In the era of Industry 4.0, the Industrial Internet of Things (IIoT) is developing rapidly, various IIoT applications pose new challenges to the existing network architecture. On the one hand, these applications put forward higher requirements for the efficient use of network resources. On the other hand, these applications generate massive amounts of information, and they pursue a more secure network environment. Therefore, in order to ensure security while effectively allocating network resources, this paper puts forward a virtual network embedding (VNE) algorithm assisted by resource knowledge description (RKD) and deep reinforcement learning (DRL). First, we use social attribute perception to measure the security of each physical node and regard it as one of the attributes of the physical node. Then, RKD is used to standardize resource constraints before the virtual network is embedded. Finally, the DRL agent derives the probability of the physical node being embedded according to the physical network attributes, and embeds the virtual node according to the probability. Simulation experiments show that compared with the BaseLine algorithm, the RKD-VNE algorithm proposed in this paper has obvious advantages in the general performance of VNE, especially in terms of long-term revenue consumption rate increased by 24.3%.

Space-Air-Ground Integrated Multi-Domain Network Resource Orchestration Based on Virtual Network Architecture: A DRL Method

Traditional ground wireless communication networks cannot provide high-quality services for artificial intelligence (AI) applications such as intelligent transportation systems (ITS) due to deployment, coverage and capacity issues. The space-air-ground integrated network (SAGIN) has become a research focus in the industry. Compared with traditional wireless communication networks, SAGIN is more flexible and reliable, and it has wider coverage and higher quality of seamless connection. However, due to its inherent heterogeneity, time-varying and self-organizing characteristics, the deployment and use of SAGIN still faces huge challenges, among which the orchestration of heterogeneous resources is a key issue. Based on virtual network architecture and deep reinforcement learning (DRL), we model SAGIN’s heterogeneous resource orchestration as a multi-domain virtual network embedding (VNE) problem, and propose a SAGIN cross-domain VNE algorithm. We model the different network segments of SAGIN, and set the network attributes according to the actual situation of SAGIN and user needs. In DRL, the agent is acted by a five-layer policy network. We build a feature matrix based on network attributes extracted from SAGIN and use it as the agent training environment. Through training, the probability of each underlying node being embedded can be derived. In test phase, we complete the embedding process of virtual nodes and links in turn based on this probability. Finally, we verify the effectiveness of the algorithm from both training and testing.

Admission Control and Virtual Network Embedding in 5G Networks: A Deep Reinforcement-Learning Approach

Fifth-generation (5G) networks are already available in major urban areas and are expected to bring a major transformation to citizens’ lives. 5G services, such as enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLLC), and massive machine-type communications (mMTC), require a network infrastructure capable of supporting stringent requirements in terms of latency and bandwidth demands; as such, it must be highly dynamic and flexible. Network slicing is a key enabler technology that can provide dynamic and flexible characteristics to 5G network architecture. A network slice (NS) can be defined as a partition of network and IT resources, that is, network links and nodes capacity dedicated to a specific set of service demands. As a result, different NSs can coexist over the same physical infrastructure network and can be used to dynamically and flexibly deploy the aforementioned 5G services. However, to efficiently implement NSs with different requirements, communication service providers (CSPs) that own the physical infrastructure network must adopt sophisticated techniques for admission control and resource allocation of NSs. In this paper, we present a novel framework for admission control and resource allocation of 5G NSs in metro-core networks. Specifically, our framework is based on a deep reinforcement learning (DRL) algorithm called Advantage Actor Critic (A2C), which performs admission control, i.e. it is capable of learning which slice to admit based on the availability of the physical network resources. Then, given the diversity of requirements for each 5G service, we propose different resource allocation algorithms based on integer linear programming (ILP) and heuristics to treat each service accordingly. Results show that our proposed framework can increase the number of admitted NSs with respect to the case in which the admission control is disabled by improving the resource allocation performance.

Monkey Business: Reinforcement Learning Meets Neighborhood Search for Virtual Network Embedding}

Monkey Business: Reinforcement Learning Meets Neighborhood Search for Virtual Network Embedding}

Fault-Tolerant Embedding Algorithm for Node Failure in Airborne Tactical Network Virtualization

Airborne tactical networks (ATNs) are driving the promising development of Internet of Battle things by enabling efficient information sharing, which is impeded by the network ossification problem that is deep-rooted in the tightly coupled network architecture. As a solution, network virtualization (NV) can break the tight coupling between applications and network infrastructure, providing a more flexible and scalable architecture for ATNs. With complex interference and malicious attacks, the application of NV is challenged by network failures when instantiating multiple virtual networks on a shared substrate network, which is known as survivable virtual network embedding (SVNE). However, existing SVNE algorithms, mostly designed for wired networks, are not necessarily optimal for the virtualization of ATNs due to the complex wireless interference. To this end, a fault-tolerant SVNE algorithm, termed SVNE-FT, is proposed to recover virtual networks from single node failure (end or switching node failure) under the wireless interference. To end node failure, SVNE-FT firstly adopts a novel node ranking approach to select reliable substrate nodes for virtual nodes and then remaps the failed virtual nodes, affected by node failure, by releasing part of the substrate paths to improve the resource utilization. In addition, to switching node failure, it adopts the improved pre-configured cycle (p-Cycle) technology to augment the reliable link mapping with differentiated p-Cycles that protect switching node from node failure and reduce the resource consumption of backups. Numerical simulation results reveal that SVNE-FT outperforms typical and latest heuristic SVNE algorithms under the complex interference of ATNs. For instance, average acceptance ratio of virtual networks improves at least 12%.

Dynamic and highly energy-efficient virtual network embedding method based on elastic optical networks

Network virtualization has been considered one of the promising paradigms for future network architecture, which can satisfy the diversified and personalized requirements of different applications by sharing physical network infrastructure. One of the major challenges in virtualization is how to map virtual networks efficiently onto the substrate network considering different constraints. We aim at solving the problem of high energy consumption of virtual network embedding in respect of the orthogonal frequency division multiplexing using elastic optical networks (EONs). First, we comprehensively consider and design an energy consumption model of network components, which denotes the key part of virtual optical network embedding (VONE). Then, a dynamic heuristic energy-efficient virtual optical network embedding (DEE-VONE) algorithm is proposed to achieve high energy efficiency and resource scalability. Simulation experiments have proven that, compared with the two benchmark algorithms, namely, the FFK-VONE and LRCK-VONE, the proposed method can maximize the network energy consumption saving at the cost of increasing the blocking probability. As the traffic load increases, the DEE-VONE method achieves higher energy-saving efficiency because optical switching energy saving plays an essential role.

Virtual optical network embedding of time-varying traffic in elastic optical networks

Network virtualization can enhance the flexibility of Internet infrastructure resources and the scalability of the substrate elastic optical networks (EONs) through the coexistence of multiple virtual optical networks supporting different services. Traditional virtual optical network embedding mostly assumed fixed embedding, that is, once a virtual optical network (VON) is embedded, the network resources allocated to it are almost unchanged during its lifetime. However, the actual traffic demand on a VON usually changes over time. To address the problems of high bandwidth blocking probability and low spectrum utilization caused by the mismatch between the resources allocated and the required resources during the virtual optical network embedding of the time-varying traffic in the elastic optical networks (EONs), we propose a virtual optical network embedding algorithm of the time-varying traffic (TVT-VONE). Firstly, in the node embedding stage, a node weight value measurement is designed based on the attributes of virtual nodes and physical nodes. Secondly, in the virtual optical link embedding stage, a measurement formula for path spectrum resource richness is designed to decrease link embedding failure due to insufficient spectrum resources on the path. Finally, in order to adapt to the characteristics of dynamic changes in bandwidth requirements of time-varying traffic, we design a resource-aware virtual network reconfiguration strategy when the spectrum resources of traffic required do not match the resources allocated to the changed traffic. Simulation results show that the proposed algorithm can effectively reduce the bandwidth blocking probability of VON requests and improve spectrum utilization of EONs.