NNIRSS: neural network-based intelligent routing scheme for SDN

Zhang, Chuangchuang; Wang, Xingwei; Li, Fuliang; Huang, Min

doi:10.1007/s00521-018-3427-z

Cited by 15 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Energy efficiency and routing schemes are interlinked with each other. Using neural network [58] developed a routing scheme that makes the controller work centralized to the data flow. In this technique, the data flow path can also be predicted, which helps to fulfil QoS requirements.…”

Section: A Core Network 1) Software Defined Networking (Sdn)mentioning

confidence: 99%

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

et al. 2020

View full text Add to dashboard Cite

As the world pushes toward the use of greener technology and minimizes energy waste, energy efficiency in the wireless network has become more critical than ever. The next-generation networks, such as 5G, are being designed to improve energy efficiency and thus constitute a critical aspect of research and network design. The 5G network is expected to deliver a wide range of services that includes enhanced mobile broadband, massive machine-type communication and ultra-reliability, and low latency. To realize such a diverse set of requirement, 5G network has evolved as a multi-layer network that uses various technological advances to offer an extensive range of wireless services. Several technologies, such as software-defined networking, network function virtualization, edge computing, cloud computing, and small cells, are being integrated into the 5G networks to fulfill the need for diverse requirements. Such a complex network design is going to result in increased power consumption; therefore, energy efficiency becomes of utmost importance. To assist in the task of achieving energy efficiency in the network machine learning technique could play a significant role and hence gained significant interest from the research community. In this paper, we review the state-of-art application of machine learning techniques in the 5G network to enable energy efficiency at the access, edge, and core network. Based on the review, we present a taxonomy of machine learning applications in 5G networks for improving energy efficiency. We discuss several issues that can be solved using machine learning regarding energy efficiency in 5G networks. Finally, we discuss various challenges that need to be addressed to realize the full potential of machine learning to improve energy efficiency in the 5G networks. The survey presents a broad range of ideas related to machine learning in 5G that addresses the issue of energy efficiency in virtualization, resource optimization, power allocation, and incorporating enabling technologies of 5G can enhance energy efficiency.

show abstract

Section: A Core Network 1) Software Defined Networking (Sdn)mentioning

confidence: 99%

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

et al. 2020

View full text Add to dashboard Cite

show abstract

“…And we use Di(x, y, z) to represent the network resource capability of the ith SDN domain. For example, D2 (6,5,3) represents that the SDN domain D2 has six units of CPU resource, five units of storage resource, and three units of memory resource. From Figure 2, we can see that in FIGURE 2 An example of network service chains (NSCs) deployment (scheme 1)…”

Section: Figure 1 System Modelmentioning

confidence: 99%

“…2,3 On one hand, different from the conventional architectures, the control plane is decoupled from the data plane and a logically centralized controller is adopted in SDN. 4,5,6,7 What is more, the control plane is programmable to support the flexible deployment of new network services. These distinguished features enable SDN to simplify the service deployment and provisioning.…”

mentioning

confidence: 99%

Network service chains deployment across multiple SDN domains

Zhang

Wang

et al. 2018

Int J Communication

Self Cite

View full text Add to dashboard Cite

The integration of software-defined networking (SDN) and network function virtualization (NFV) enables the flexible deployment of network services and significant reduction in service provisioning cost. In particular, SDN, as a new networking paradigm, supports the flexible provisioning of new network services. Meanwhile, in NFV, the service request from end user can be represented as the service function chain (SFC). However, with the continuously increasing of network users and constant enlargement in network scale, the deployment of network services in the large-scale SDN network, which is composed of multiple SDN domains, becomes more challenging since these SDN domains are managed and maintained by different network operators and service providers. To address the above challenge, in this paper, we study the problem of how to deploy network services across multiple SDN domains optimally. Specifically, we first formulate this problem as an optimization problem by jointly minimizing the total number of SDN domains occupied by SFCs and the corresponding network resource consumption cost. We propose a novel heuristic deployment algorithm to solve this optimization problem. The simulation results demonstrate that the proposed heuristic deployment algorithm is effective and outperforms the comparison algorithms in terms of the total service cost. KEYWORDS multidomain network, network service deployment, SDN, SFC Int J Commun Syst. 2018;31:e3826.wileyonlinelibrary.com/journal/dac

show abstract

“…In recent years, software defined networking (SDN) as an emerging networking paradigm has received great attention. The SDN decouples control plane from data plane and transfers the computing intelligence into control plane . These distinguished features in SDN architecture enable efficient service provisioning for end users.…”

Section: Introductionmentioning

confidence: 99%

“…The SDN decouples control plane from data plane and transfers the computing intelligence into control plane. 1,2 These distinguished features in SDN architecture enable efficient service provisioning for end users. On the other hand, network function virtualization (NFV) technology decouples network functions from hardware and implements them in software.…”

Section: Introductionmentioning

confidence: 99%

Dynamic network service deployment across multiple SDN domains

Zhang

Wang

Dong

et al. 2019

Trans Emerging Tel Tech

Self Cite

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

NNIRSS: neural network-based intelligent routing scheme for SDN

Cited by 15 publications

References 26 publications

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

Network service chains deployment across multiple SDN domains

Dynamic network service deployment across multiple SDN domains

Contact Info

Product

Resources

About