An Effective Load Balanced Controller Placement Approach in Software-Defined WANs

Wide Area Networks (WANs) are widely used in various fields such as business, education, government and military. The traditional network management of WANs has been difficult to meet the requirements of network development. Software-Defined Networking (SDN), a new network architecture with the concept of the separation between control and forwarding and centralized management, provides a practical solution for the efficient management of WANs. A Software-Defined WAN (SD-WAN) is usually deployed with multiple controllers due to the requirements of delay, scalability and reliability. The controller placement is a significant issue in a SD-WAN. In the literature, many approaches focus on reducing the delay between switches and controllers. However, these approaches may lead to load imbalance among controllers, which would have a negative impact on the performance and reliability of the network. In this paper, we define the load balanced controller placement problem, whose objective is to reduce the average delay between switches and controllers while maintaining load balance among controllers. And we propose an effective controller placement approach based on topological potential and minimum-cost flow to solve this problem. Extensive simulations on various real WAN topologies verify that our controller placement approach can effectively reduce the delay between switches and controllers and maintain good load balance among controllers. Our approach can also reduce the number of required controllers to avoid overload.

[1]  Matthew Roughan,et al.  The Internet Topology Zoo , 2011, IEEE Journal on Selected Areas in Communications.

[2]  Rob Sherwood,et al.  The controller placement problem , 2012, HotSDN '12.

[3]  Wolfgang Kellerer,et al.  Controller placement strategies for a resilient SDN control plane , 2016, 2016 8th International Workshop on Resilient Networks Design and Modeling (RNDM).

[4]  Marc St-Hilaire,et al.  Optimal Model for the Controller Placement Problem in Software Defined Networks , 2015, IEEE Communications Letters.

[5]  Tao Luo,et al.  The Energy-Aware Controller Placement Problem in Software Defined Networks , 2017, IEEE Communications Letters.

[6]  Cristina Cervello-Pastor,et al.  On the controller placement for designing a distributed SDN control layer , 2014, 2014 IFIP Networking Conference.

[7]  Shanfei Li,et al.  An Improved Approximation Algorithm for the Hard Uniform Capacitated k-median Problem , 2014, APPROX-RANDOM.

[8]  Deyi Li,et al.  Artificial Intelligence with Uncertainty , 2004, CIT.

[9]  Dijiang Huang,et al.  Fault Tolerant Controller Placement in Distributed SDN Environments , 2018, 2018 IEEE International Conference on Communications (ICC).

[10]  Jun Huang,et al.  An Effective Approach to Controller Placement in Software Defined Wide Area Networks , 2018, IEEE Transactions on Network and Service Management.

[11]  Jun Li,et al.  A K-means-based network partition algorithm for controller placement in software defined network , 2016, 2016 IEEE International Conference on Communications (ICC).