Design of an Efficient Method for Identifying Virtual Machines Compatible with Service Chain in a Virtual Network Environment

Hyeonseok Oh,Daeun Yu,Yoon-Ho Choi,Namgi Kim 보안공학연구지원센터 2014 International Journal of Multimedia and Ubiquitous Vol.9 No.11

With advancements in network technologies, network virtualization has been proposed to efficiently provide a large number of services and flexible management by utilizing limited resources over existing networks as much as possible. Network virtualization has been proposed as a new paradigm for networks, as it simplifies complicated network configurations for convenient maintenance through the maximum utilization of limited network resources. However, problems have arisen due to network virtualization, such as how to assign real network components that are compatible with virtual network components over a large number of virtual machines existing in a network. In particular, the service-chaining concept—where a network flow only passes through needed services—has been newly introduced by combining the recently highlighted Software-Defined Network with a virtualization concept called Network Function Virtualization. As a result, studies on which virtual machines are selected and how to connect them have increased ever more. Accordingly, this paper aims to identify virtual machines that are compatible with service chaining in a virtual network environment where virtual machines are dispersed, and it proposes a method of how to create a path by connecting virtual machines.

기계학습 기반의 가상 네트워크 기능 자원 수요 예측 방법

김희곤,이도영,유재형,홍원기 한국통신학회 2018 KNOM Review Vol.21 No.2

네트워크 가상화 (Network virtualization)는 물리 네트워크상에서 각 사용자 별로 독립된 가상의 네트워크 환경을 생성하는 기술을 지칭한다. 네트워크 가상화 기술은 물리 네트워크 자원을 공유하여 사용자 별로 네트워크를 구축하는 데 필요한 비용을 절감할 수 있으며, 네트워크 관리자가 요구사항에 따라 동적으로 네트워크를 관리할 수 있도록 돕는다. 하지만 동적으로 네트워크 관리를 수행할 수 있다는 장점에도 불구하고, 관리자가 여전히 직접 판단을 내리고 관리 기능을 실행하는 과정은 동일하다. 네트워크 관리 기능 실행 전까지 관리자에 의해 네트워크 상황을 파악하고 결정을 내리는 과정에는 많은 시간이 소요될 수 있기 때문에 네트워크 가상화로 얻을 수 있는 동적 네트워크 관리라는 장점을 최대화 하지 못하고 있다. 본 논문에서는 기계학습 (Machine Learning) 기술을 도입하여 사람의 도움 없이 네트워크가 스스로 학습하여 동적으로 네트워크 관리를 수행하는 방법을 제안한다. 제안하는 방법은 가상 네트워크 관리에서 핵심적이고 필수적인 문제인 자원관리 최적화 문제를 서비스 펑션 체인 (Service Function Chaining) 문제로 정의하고, VNF의 자원 수요를 예측하여 적절한 자원을 동적으로 할당해 서비스 중단이 일어나는 것을 방지하면서 네트워크 운용비용을 절감하는 것을 목표로 한다. Network virtualization refers to a technology creating independent virtual network environment on a physical network. Network virtualization technology can share the physical network resources to reduce the cost of establishing the network for each user and enables the network administrator to dynamically change the network configuration according to the purpose. Although the network management can be handled dynamically, the management is manual, and it does not maximize the profit of network virtualization. In this paper, we propose Machine-Learning technology to allow the network to learn by itself and manage its management dynamically. The proposed approach is to dynamically allocate appropriate resources by predicting resource demand of VNF in service function chaining, which is a core and essential problem in virtual network management. Our goal is to predict the resource demand of the VNF and dynamically allocate the appropriate resources to reduce the cost of network operation while preventing service interruption.

Q-learning based Service Function Chaining using VNF Resource-aware Reward Model

Doyoung Lee,Jae-Hyoung Yoo,James Won-Ki Hong 한국통신학회 2020 한국통신학회 APNOMS Vol.2020 No.09

With the advent of the 5G network era, it is required to flexibly build and manage networks to meet rapidly changing service requirements. Software-defined networking (SDN) and network function virtualization (NFV) are key technologies that enable flexible network management by transforming networks into software-based networks. Besides, NFV has the advantage of virtualizing network functions, operating those on commercial (COTS) servers, and managing the network functions dynamically. However, the numerous virtual networks and resources created by NFV can cause problems complicating network management. To solve the problems, research on managing complex NFV environments using artificial intelligence (AI) has recently attracted attention. In particular, service function chaining (SFC) is one of the essential NFV technologies, and it is required to create an efficient SFC path in dynamic networks. In this paper, we propose a method of finding optimal SFC path considering the resource utilization of virtual network function (VNF) and VNF placement by using Q-learning, one of the reinforcement learning (RL) algorithms.

Security challenges with network functions virtualization

Daghmehchi Firoozjaei, M.,Jeong, J.(.,Ko, H.,Kim, H. North-Holland 2017 Future generation computer systems Vol.67 No.-

<P>The advent of network functions virtualization (NFV) has revolutionized numerous network-based applications due to its several benefits such as flexibility, manageability, scalability, and security. By the software-based virtualization of network functions on a single infrastructure, NFV provides users with a framework that dynamically provisions various network services in a flexible manner. However, NFV faces several security challenges (e.g., multi-tenancy and live migration) which make it vulnerable to some cybersecurity attacks (e.g., side-channel attacks and shared resource misuse attacks). In this paper, we provide an overview of NFV, discuss potentially serious security threats on NFV and introduce effective countermeasures to mitigate those threats. Finally, we suggest some practical solutions to provide a trustworthy platform for NFV. (C) 2016 Elsevier B.V. All rights reserved.</P>

SDN 기반 네트워크에서의 유해트래픽 검출을 위한 테스트베드 구축

김정윤 한국지식정보기술학회 2017 한국지식정보기술학회 논문지 Vol.12 No.3

SDN-based networks have many advantages over existing networks. SDN is different from existing network configuration It is a method of delivering packets based on software functions in network equipment, which has many advantages in terms of cost and operation over existing network structure. However, since it is built around OpenFlow, which is the most widely known interface in SDN, it is also vulnerable to security. So SDN tried to solve this by providing virtualized security function based on NFV(Network Function Virtualization). The advantage of NFV is that it is possible to apply security only to the place where security is needed by using controller without need to set up like existing equipment. In this paper, I tried to investigate a method to filter harmful traffic without the ACL(Access Control List), ZFW(Zone-Based Firewall) and other functions set in the security device in the NFV that operates for security in the SDN environment. The hardware-based security technologies currently used are inevitably subject to delays and can not be used to prevent security attacks that are executed in various ways by changing port numbers. Therefore, the purpose of this paper is to improve the security performance of SDN based on NFV by analyzing traffic pattern and filtering harmful traffic and nontoxic traffic. For this study, a test network based on actual SDN was constructed and the pattern - based harmful traffic detection technology was proved.

SDN/NFV-based Scalable Mobile Service Integration for Gradual Network Evolution

경연웅,박성호,박진우 한국통신학회 2017 Journal of communications and networks Vol.19 No.6

The coexistence of heterogeneous networks is becomingincreasingly more common with the evolution towards 5G, increasingthe complexity and cost of deploying and managing these networks. Network operators consequently need to find efficient waysof flexibly constructing and operating networks within a heterogeneousnetwork environment in order to reduce operational expenditure(OPEX) and capital expenditure (CAPEX). One possibleway to meet this requirement is the accommodation of previouslegacy network services in the newly-deployed network while graduallyreducing the reliance on physical legacy networks. Softwaredefinedtransitional network (SDTN) architecture is a strong candidateto achieve this. In the SDTN, SDN/NFV plays a key role inintegrating legacy network services into the newly-deploying network. This paper proposes an SDTN architecture and presentsan example of its deployment in a mobile network evolution scenarioin which 3G mobile services are integrated into a 4G network. The unified mobility management, in which 3G mobile servicesare integrated into a 4G access networks based on SDN/NFVis described. The network nodes for legacy mobility managementservices are virtualized at the control plane and accommodated intothe SDTN architecture. As a result, the mobility management is interoperablebetween the virtualized legacy network service functionsand the underlying 4G network. In order to support variousheterogeneous services integration into the 4G mobile network,scalable edge switches are proposed for protocol mapping betweenincoming heterogeneous service traffic and 4G data. The proposedSDTN approach can be applied to the future deployment of 5Gnetworks by accommodating various pre-existing legacy servicesin newly-deploying networks.

A Mechanism for Configurable Network Service Chaining and Its Implementation

( Gang Xiong ),( Yuxiang Hu ),( Julong Lan ),( Guozhen Cheng ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.8

Recently Service Function Chaining (SFC) is promising to innovate the network service mode in modern networks. However, a feasible implementation of SFC is still difficult due to the need to achieve functional equivalence with traditional modes without sacrificing performance or increasing network complexity. In this paper, we present a configurable network service chaining (CNSC) mechanism to provide services for network traffics in a flexible and optimal way. Firstly, we formulate the problem of network service chaining and design an effective service chain construction framework based on integrating software-defined networking (SDN) with network functions virtualization (NFV). Then, we model the service path computation problem as an integer liner optimization problem and propose an algorithm named SPCM to cooperatively combine service function instances with a network utility maximum policy. In the procedure of SPCM, we achieve the service node mapping by defining a service capacity matrix for substrate nodes, and work out the optimal link mapping policies with segment routing. Finally, the simulation results indicate that the average request acceptance ratio and resources utilization ratio can reach above 85% and 75% by our SPCM algorithm, respectively. Upon the prototype system, it is demonstrated that CNSC outperforms other approaches and can provide flexible and scalable network services.

Graph Neural Network-based Virtual Network Function Management

Doyoung Lee,Dongnyeong Heo,Heeyoul Choi,Jae-Hyoung Yoo,James Won-Ki Hong,Hee-Gon Kim,Suhyun Park,Stanislav Lange 한국통신학회 2020 한국통신학회 APNOMS Vol.2020 No.09

Software-Defined Networking (SDN) and Network Function Virtualization (NFV) help reduce OPEX and CAPEX as well as increase network flexibility and agility. But at the same time, operators have to cope with the increased complexity of managing virtual networks and machines, which are more dynamic and heterogeneous than before. Since this complexity is paired with strict time requirements for making management decisions, traditional mechanisms that rely on, e.g., Integer Linear Programming (ILP) models are no longer feasible. Machine learning has emerged as a possible solution to address network management problems to get near-optimal solutions in a short time. In this paper, we propose a Graph Neural Network (GNN) based algorithm to manage VNFs. The proposed model solves the complex VNF management problem in a short time and gets near-optimal solutions.

An Optimized Deployment Mechanism for Virtual Middleboxes in NFV- and SDN-Enabling Network

( Gang Xiong ),( Penghao Sun ),( Yuxiang Hu ),( Julong Lan ),( Kan Li ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.8

Network Function Virtualization (NFV) and Software Defined Networking (SDN) are recently considered as very promising drivers of the evolution of existing middlebox services, which play intrinsic and fundamental roles in today`s networks. To address the virtual service deployment issues that caused by introducing NFV or SDN to networks, this paper proposes an optimal solution by combining quantum genetic algorithm with cooperative game theory. Specifically, we first state the concrete content of the service deployment problem and describe the system framework based on the architecture of SDN. Second, for the service location placement sub-problem, an integer linear programming model is built, which aims at minimizing the network transport delay by selecting suitable service locations, and then a heuristic solution is designed based on the improved quantum genetic algorithm. Third, for the service amount placement sub-problem, we apply the rigorous cooperative game-theoretic approach to build the mathematical model, and implement a distributed algorithm corresponding to Nash bargaining solution. Finally, experimental results show that our proposed method can calculate automatically the optimized placement locations, which reduces 30% of the average traffic delay compared to that of the random placement scheme. Meanwhile, the service amount placement approach can achieve the performance that the average metric values of satisfaction degree and fairness index reach above 90%. And evaluation results demonstrate that our proposed mechanism has a comprehensive advantage for network application.

Service Traffic Engineering: avoiding Link Overloads in Service Chains

Khalil Mebarkia,Zoltán Zsóka 한국통신학회 2019 Journal of communications and networks Vol.21 No.1

Emerging technologies such as software defined networks(SDN) and network function virtualization (NFV) enable flexibilityin operation and a significant reduction of the costly hardware deploymentin networks and improve service agility too. Virtual networkfunctions (VNF) are running as virtual machines on servers,and are organized in chains using service function chaining (SFC). Though many SFC algorithms were introduced, they mostly neglectthe state of the underlying networking layers and infrastructure,considering static costs for the connections among the VNFs. In this paper, we apply a model that considers also the topology andcurrent load information of the IP layer below. We formulate theproblem using an integer linear program (ILP) and propose also aheuristic algorithm with the objective of avoiding link overloads inthe networking layer. Thus, we solve the stated VNF-SFC problemsimilar to the basic traffic engineering (TE) problem in networks. We define different architectures to classify the solutions accordingto the amount of networking layer information applied in VNFSFCsolutions. We analyze the operation of the proposed solutionsand show their benefits and drawbacks by numerical results of acase study.