VNF-EQ: dynamic placement of virtual network functions for energy efficiency and QoS guarantee in NFV

Kim, Sanghyeok; Park, Sungyoung; Kim, Young-Jae; Kim, Siri; Lee, Kwonyong

doi:10.1007/s10586-017-1004-3

Cited by 44 publications

(27 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows substantially improved performance at the price of a loss of the genericity of the NSGA-II algorithm. While the authors, in [22] and [24], consider modifications that leave the choice of the VNFs mapping random, ensuring a good exploration of the space of solutions, other approaches have chosen to steer the mapping to accelerate the convergence. In fact, in [23], the authors proposed a greedy version of the non-dominated sorting genetic algorithm (NSGA-II), in which nodes with higher residual resources have a higher priority to be mapped; while for link mapping, shorter paths are prioritized.…”

Section: Metaheuristics-based Approachesmentioning

confidence: 99%

A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding

Quang

Hadjadj‐Aoul

Outtagarts

2019

IEEE Trans. Netw. Serv. Manage.

121

View full text Add to dashboard Cite

Network Function Virtualization (NFV) and service orchestration simplify the deployment and management of network and telecommunication services. The deployment of these services requires, typically, the allocation of Virtual Network Function -Forwarding Graph (VNF-FG), which implies not only the fulfillment of the service's requirements in terms of Quality of Service (QoS), but also considering the constraints of the underlying infrastructure. This topic has been well-studied in existing literature, however, its complexity and uncertainty of available information unveil challenges for researchers and engineers. In this paper, we explore the potential of reinforcement learning techniques for the placement of VNF-FGs. However, it turns out that even the most well-known learning technique is ineffective in the context of a large-scale action space. In this respect, we propose approaches to find out feasible solutions while improving significantly the exploration of the action space. The simulation results clearly show the effectiveness of the proposed learning approach for this category of problems. Moreover, thanks to the deep learning process, the performance of the proposed approach is improved over time.

show abstract

Section: Metaheuristics-based Approachesmentioning

confidence: 99%

A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding

Quang

Hadjadj‐Aoul

Outtagarts

2019

IEEE Trans. Netw. Serv. Manage.

121

View full text Add to dashboard Cite

show abstract

“…Regarding related work about delay and NFV, the authors in [16] proposed a VNF placement algorithm that allows users to meet their service latency requirements while minimizing the power consumption at the same time. In the proposed algorithm, a shortest path between a source and a destination is first computed, using Dijkstra algorithm based on the service latency requirements from the users.…”

Section: Related Workmentioning

confidence: 99%

Offline and online power aware resource allocation algorithms with migration and delay constraints

Hejja

Hesselbach

2019

Computer Networks

View full text Add to dashboard Cite

In order to handle advanced mobile broadband services and Internet of Things (IoT), future Internet and 5G networks are expected to leverage the use of network virtualization, be much faster, have greater capacities, provide lower latencies, and significantly be power efficient than current mobile technologies. Therefore, this paper proposes three power aware algorithms for offline, online, and migration applications, solving the resource allocation problem within the frameworks of network function virtualization (NFV) environments in fractions of a second. The proposed algorithms target minimizing the total costs and power consumptions in the physical network through sufficiently allocating the least physical resources to host the demands of the virtual network services, and put into saving mode all other not utilized physical components. Simulations and evaluations of the offline algorithm compared to the state-of-art resulted on lower total costs by 32%. In addition to that, the online algorithm was tested through four different experiments, and the results argued that the overall power consumption of the physical network was highly dependent on the demands' lifetimes, and the strictness of the required end-to-end delay. Regarding migrations during online, the results concluded that the proposed algorithms would be most effective when applied for maintenance and emergency conditions.

show abstract

“…We mathematically formulate this problem as a multiobjective optimization model with two different goals of minimizing total resource consumption cost and operating cost, respectively. Similar to most existing works, [10][11][12][13][14]16,[19][20][21][22][23][24][25][26][31][32][33] we transform the multiobjective optimization problem into a single objective optimization problem and base on Dijkstra algorithm to design a heuristic service deployment approach to solve it.…”

Section: Related Workmentioning

confidence: 99%

“…The static proposals may lead to network performance degradation. 17,18 Although a large number of research works [19][20][21][22][23][24][25][26][27][28][29][30] have tried to tackle the problem of dynamic network SFCs deployment, they did not consider the dynamic network service chains deployment across multiple SDN domains. Thus, an efficient dynamic cross-domain SDN network service deployment scheme is urgently required to adapt to dynamic service demands from end users.…”

Section: Introductionmentioning

confidence: 99%

Dynamic network service deployment across multiple SDN domains

Zhang

Wang

Dong

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The integration of software defined networking (SDN) and network function virtualization (NFV) is a promising approach to support flexible service deployment and provisioning. In particular, NFV enables a network service to be represented as one network service function chain, which is composed of several virtual network functions in a specific order. However, with regard to service provisioning in multidomain SDN networks, virtual network functions are deployed in several different SDN domains due to limited resource capacity of each SDN domain. It results in the network service deployment complexity increase and causes additional operating cost. On the other hand, most current network service deployment proposals are limited to static user request scenarios. How to effectively deploy network service across multiple SDN domains to satisfy dynamic service demands of end users is a challenging problem. To address the aforementioned challenge, in this paper, we study the problem of dynamic network service deployment across multiple SDN domains. Specifically, we first design a novel service deployment framework to support dynamic deployment and optimization of virtual network function in multidomain SDN networks. Then, we formulate the problem as a multiobjective optimization problem with the target of jointly minimizing resource consumption cost and operating cost. Furthermore, we transform the multiobjective optimization problem into a single objective optimization model and present an efficient heuristic service deployment approach to solve it by leveraging Dijkstra algorithm. The simulation results demonstrate that the proposed service deployment method is efficient and outperforms comparison methods in terms of service rejection ratio, resource cost, and operating cost.

show abstract

VNF-EQ: dynamic placement of virtual network functions for energy efficiency and QoS guarantee in NFV

Cited by 44 publications

References 12 publications

A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding

A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding

Offline and online power aware resource allocation algorithms with migration and delay constraints

Dynamic network service deployment across multiple SDN domains

Contact Info

Product

Resources

About