Intelligent Software-Defined Mesh Networks With Link-Failure Adaptive Traffic Balancing

In the software defined networking (SDN)-based wireless mesh network (WMN) architecture (SD-WMN), the network is monitored and managed in a centralized manner. Although the use of SDN simplifies the WMN management, it is still not clear whether the SDN architecture, which was originally designed for wired links, can effectively handle the dynamic topology of WMNs. This paper addresses the traffic balancing issue introduced by node mobility. To reduce the response time of SDN controller for dynamic network topology, a two-layer supervised learning model is proposed that helps the controller to predict the node mobility and link failure probability. Then, an alternative route selection scheme is proposed, which achieves optimal traffic balancing while minimizing the control plane overhead. Efficiency of the proposed SD-WMN architecture is validated in the widely used network simulator-ns-3. Our results demonstrate the network throughput enhancement achieved by the proposed SD-WMN architecture with link-failure adaptive traffic control.