Preferential Multi-Attribute Rank based Forwarding Node Selection in Software Defined Networks

摘要

Today's networks provide a plethora of applications with heterogeneous characteristics. The network generates a huge volume of traffic because of its distributed nature and requires preferential treatment for controlling them. The existing traditional system lacks efficiency because of the diverse nature of the network and the need for the high-performance network is imminent. However, one of the predominant issues that demand high attention is traffic flow management. This paper explores the various traffic management approaches and analyses the significant role played by the next hop neighbor node selection in improving the performance of the network. To address this issue, the emerging software defined networking paradigm (SDN) is introduced to enable flexible traffic flow control. A novel method for traffic flow management by adopting the Simple Multi-Attribute Rating Technique (SMART) ranking method has been proposed for selecting the best next hop neighbor for forwarding the flows. A flow scheduling algorithm has been adopted for minimizing the maximum link utilization and provide improved performance. Simulation result shows that the proposed algorithm performs better in terms of throughput and latency.