Service function chain orchestration across multiple clouds

Zhong, Xuxia; Wang, Ying; Qiu, Xuesong

doi:10.1109/cc.2018.8485473

Cited by 16 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, VNF embedding and VNF scheduling have attracted significant attention from both academia and industry [4], [5]. However, most researchers focus on either VNF embedding [6]- [11] or VNF scheduling [12]- [15]. Few researchers concentrate on solving both VNF embedding and scheduling in a coordinated manner.…”

Section: Introductionmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: Dynamic Embedding and Scheduling of Service Function Chains for Future SDN/NFV-Enabled Networks

2019

View full text Add to dashboard Cite

Currently, software-defined networking (SDN) and network function virtualization (NFV) are the two most promising approaches for implementing network virtualization (NV). Traditional TCP/IPbased networks (e.g. Internet) will be transformed into SDN/NFV-enabled networks in the foreseeable future. Through virtualization, the slicing of heterogeneous underlying resources will provide an agile and customized virtual network (VN) services to end users. Hence, the virtual network function (VNF) embedding and scheduling are crucial to the VN service deployment in the SDN/NFV-enabled networks. In this paper, the dynamic VNF embedding and scheduling are jointly researched for enhancing the VN service provisioning. At first, the VNF embedding and scheduling are formulated by using the mixed integer linear programming (MILP) model, having the goals of minimizing the consumed underlying resources and providing QoS-guaranteed VN service. Subsequently, to remove the NP-hardness of the MILP model, a dynamic VNF embedding and scheduling algorithm is proposed. For instance, when a new VN service is requested, the VNFs, constituting the service function chain (SFC) of the VN service, will be embedded and scheduled by the proposed algorithm. If the resource and QoS requirements of the VNFs are not satisfied, a re-embedding and rescheduling scheme will be triggered in order to optimize certain existing VNFs. The dynamic embedding and scheduling algorithm has flexible network function placement and improves the underlying resource utilization. Finally, the simulation results are illustrated to validate the proposed algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: Dynamic Embedding and Scheduling of Service Function Chains for Future SDN/NFV-Enabled Networks

2019

View full text Add to dashboard Cite

show abstract

“…Although they increased SFC acceptance rate and the service capacity, yet more optimization targets are needed, including transmission delay, load balancing and so on. Zhong et al orchestrated SFCs across multiple data centers and proposed an ILP model to minimize the total cost [ 7 ]. They reduced the overall cost, however, the optimization result is too simple to apply in most cases.…”

Section: Related Workmentioning

confidence: 99%

“…In view of the dynamic and reliable deployment of the service function chain, the existing deployment methods have some shortcomings. Previously, most SFC deployment models only solve the problem which is determining deployment location or achieving optimization targets [ 6 , 7 , 8 , 9 ]. However, the reliability requirements have increased with the development of NFV and increasing of SFC requests.…”

Section: Introductionmentioning

confidence: 99%

Reliable Service Function Chain Deployment Method Based on Deep Reinforcement Learning

Wang

Zhao

2021

Sensors

View full text Add to dashboard Cite

Network function virtualization (NFV) is a key technology to decouple hardware device and software function. Several virtual network functions (VNFs) combine into a function sequence in a certain order, that is defined as service function chain (SFC). A significant challenge is guaranteeing reliability. First, deployment server is selected to place VNF, then, backup server is determined to place the VNF as a backup which is running when deployment server is failed. Moreover, how to determine the accurate locations dynamically with machine learning is challenging. This paper focuses on resource requirements of SFC to measure its priority meanwhile calculates node priority by current resource capacity and node degree, then, a novel priority-awareness deep reinforcement learning (PA-DRL) algorithm is proposed to implement reliable SFC dynamically. PA-DRL determines the backup scheme of each VNF, then, the model jointly utilizes delay, load balancing of network as feedback factors to optimize the quality of service. In the experimental results, resource efficient utilization, survival rate, and load balancing of PA-DRL were improved by 36.7%, 35.1%, and 78.9% on average compared with benchmark algorithm respectively, average delay was reduced by 14.9%. Therefore, PA-DRL can effectively improve reliability and optimization targets compared with other benchmark methods.

show abstract

“…Zhong et al [23] orchestrated SFCs across multiple datacenters, with a goal to minimize the overall cost. An integer linear programming model was formulated and solved with a metaheuristic algorithm named GBAO that contained three modules.…”

Section: A Sfc Deployment For Optimizing Resource Consumptionmentioning

confidence: 99%

“…Formula (23) represents the maximum load rate of the nodes in the physical network. As shown in the formula, the maximum node load rate is equal to the maximum load rate of all nodes in the physical network.…”

Section: One Of Our Goals Is To Minimize V…v (2) Bandwidth Resourcementioning

confidence: 99%

Low-Latency and Resource-Efficient Service Function Chaining Orchestration in Network Function Virtualization

Sun

Zhu

et al. 2020

IEEE Internet Things J.

121

View full text Add to dashboard Cite

Recently, network function virtualization (NFV) has been proposed to solve the dilemma faced by traditional networks and to improve network performance through hardware and software decoupling. The deployment of the service function chain (SFC) is a key technology that affects the performance of virtual network function (VNF). The key issue in the deployment of SFCs is proposing effective algorithms to achieve efficient use of resources. In this paper, we propose a service function chain deployment optimization (SFCDO) algorithm based on a breadth-first search (BFS). The algorithm first uses a BFS based algorithm to find the shortest path between the source node and the destination node. Then, based on the shortest path, the path with the fewest hops is preferentially chosen to implement the SFC deployment. Finally, we compare the performances with the greedy and simulated annealing (G-SA) algorithm. The experiment results show that the proposed algorithm is optimized in terms of end-to-end delay and bandwidth resource consumption. In addition, we also consider the load rate of the nodes to achieve network load balancing.

show abstract

Service function chain orchestration across multiple clouds

Cited by 16 publications

References 14 publications

Notice of Violation of IEEE Publication Principles: Dynamic Embedding and Scheduling of Service Function Chains for Future SDN/NFV-Enabled Networks

Notice of Violation of IEEE Publication Principles: Dynamic Embedding and Scheduling of Service Function Chains for Future SDN/NFV-Enabled Networks

Reliable Service Function Chain Deployment Method Based on Deep Reinforcement Learning

Low-Latency and Resource-Efficient Service Function Chaining Orchestration in Network Function Virtualization

Contact Info

Product

Resources

About