Bidirectional Matching Strategy for Multi-Controller Deployment in Distributed Software Defined Networking

Hu, Tao; Peng, Yi; Guo, Zehua; Lan, Julong; Zhang, Jianhui

doi:10.1109/access.2018.2798665

Cited by 30 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-controller data plane 1) Controller deployment: Controller deployment is an important issue in multi-controller research. In WANs, the propagation latency is the critical part of the total latency [25] [26], and some works aim to minimize the propagation latency among controllers and switches [50] [51].…”

Section: Related Workmentioning

confidence: 99%

Joint Switch Upgrade and Controller Deployment in Hybrid Software-Defined Networks

Guo

Chen

Liu

et al. 2019

IEEE J. Select. Areas Commun.

Self Cite

View full text Add to dashboard Cite

To improve traffic management ability, Internet Service Providers (ISPs) are gradually upgrading legacy network devices to programmable devices that support Software-Defined Networking (SDN). The coexistence of legacy and SDN devices gives rise to a hybrid SDN. Existing hybrid SDNs do not consider the potential performance issues introduced by a centralized SDN controller: flow requests processed by a highly loaded controller may experience long tail processing delay; inappropriate multi-controller deployment could increase the propagation delay of flow requests.In this paper, we propose to jointly consider the deployment of SDN switches and their controllers for hybrid SDNs. We formulate the joint problem as an optimization problem that maximizes the number of flows that can be controlled and managed by the SDN and minimizes the propagation delay of flow requests between SDN controllers and switches under a given upgrade budget constraint. We show this problem is NP-hard. To efficiently solve the problem, we propose some techniques (e.g., strengthening the constraints and adding additional valid inequalities) to accelerate the global optimization solver for solving the problem for small networks and an efficient heuristic algorithm for solving it for large networks. The simulation results from real network topologies illustrate the effectiveness of the proposed techniques and show that our proposed heuristic algorithm uses a small number of controllers to manage a high amount of flows with good performance. Z. Guo and Z.-L. Complexity analysis, controller deployment, heuristic algorithm, hybrid SDN, switch upgrade, upgrade budget I. INTRODUCTION Software-Defined Networking (SDN) has been widely studied and gradually adapted for campus networks [1], data center networks [2], Wide Area Networks (WANs) [3], enterprise networks [4], and Internet exchange points [5]. Due to the cost and operational considerations, SDN technology is usually deployed in an incremental fashion. In particular, at each time of network upgrade, only a set of selected legacy network devices (i.e., layer-3 routers and layer-2 switches) are upgraded to SDN switches. AT&T converted 34% of its network to SDN by the end of 2016 and virtualized 55% of its network to software by the end 2017. Its final goal is to reach 75% softwarization of its network by 2020 [6]. Therefore, the legacy network devices and SDN switches may coexist for a long time. In this paper, we will refer to such a network as a hybrid SDN.A WAN usually consists of many network devices at geo-distributed locations. A straightforward method to upgrade legacy network devices in WANs to SDN switches is based on the locations of network devices, for example, upgrade a part of WAN with network devices in proximity. The partial upgraded network can enjoy the benefit of SDN, but the performance improvement of the entire network is limited. An efficient solution for network providers is to spread the benefit of upgraded SDNs in the entire network. Based on this consideration, existing ...

show abstract

Section: Related Workmentioning

confidence: 99%

Joint Switch Upgrade and Controller Deployment in Hybrid Software-Defined Networks

Guo

Chen

Liu

et al. 2019

IEEE J. Select. Areas Commun.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, to elevate the propagation latency and bottlenecks in controller deployment in such a high densified 5G based SDN network. Many proposed methods such as Kandoo in [20] and [21] gave a promising solution to the above problems.…”

Section: Related Workmentioning

confidence: 99%

An architecture of 5G based on SDN NV wireless network

Ibrahim

Hashim

2019

IJEECS

View full text Add to dashboard Cite

<span>The unexpected increase demand growth of broadband traffic, rapid advancement in networking and internet technology led to the growth in Internet-connected devices to sensor networks, and machine type communication devices. These increases bring more challenges in network capacity and connectivity. The use of the new 5G technology continues to address these challenges by providing high data rates, low latency, and more mobility with highly and densified HetNe deploment. This densified network brings new challenges to service provisioning in future networks based on the recent network paradigm innovations, Network Virtualization and Software Defined Networking to cope with massive broadband connectivity and enhancement of capacity, flexibility, and scalability. This study sets out to present the key features and requirements for 5G HetNet, SDN and NFV. The results of this study generally justify the challenges and how to integrate them into future wireless networks through a proposed 5G-based SDN-NV wireless network architecture to enable best network performance and resource management.</span>

show abstract

“…Bidirectional matching strategy (BMS) has addressed the problems of controller's load distribution and single point of failure using centralized SDN controller architecture. BMS uses hops, delay, and traffic parameters to create matching list between controller and switches, which in turn ensures the processing speed of packet.…”

Section: Related Workmentioning

confidence: 99%

Traffic pattern–based load‐balancing algorithm in software‐defined network using distributed controllers

Gasmelseed

Ramalakshmi

2018

Int J Communication

View full text Add to dashboard Cite

Programmability and decoupling of the data plane and control plane in software-defined networking (SDN) make the enterprise's network to focus on this new paradigm and to deploy their applications on it. Furthermore, supporting of distributed controllers in SDN opens the opportunities to address the limitations of centralized controller's architecture, which in turn improves the overall performance of the network. This study proposes a new loadbalancing algorithm to handle the load based on the traffic pattern specifically transmission control protocol (TCP) and user datagram protocol (UDP) traffic.Additionally, this study uses a distributed SDN controller's architecture to host the load balancer application. This study also employs a failover mechanism on the distributed architecture to achieve high-availability environment and to ensure the redundancy and reliability of the network. The obtained results prove the effectiveness of the proposed algorithm in terms of availability, which is increased by 11%, response time is reduced by 98%, transaction rate is also increased by 258%, throughput is increased by 206%, concurrency is reduced by 63%, and packet loss is reduced by 86% while comparing with random, round-robin, and weighted round-robin algorithms in addition to ease the integration and deployment in distributed controllers.

show abstract

Bidirectional Matching Strategy for Multi-Controller Deployment in Distributed Software Defined Networking

Cited by 30 publications

References 11 publications

Joint Switch Upgrade and Controller Deployment in Hybrid Software-Defined Networks

Joint Switch Upgrade and Controller Deployment in Hybrid Software-Defined Networks

An architecture of 5G based on SDN NV wireless network

Traffic pattern–based load‐balancing algorithm in software‐defined network using distributed controllers

Contact Info

Product

Resources

About