Research on SDN-based data center network traffic management and optimization
Shuanglong Pang, Desheng Zeng, Xiaodan Chen · 2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA) · 2022
Under the traditional network architecture, due to the close binding relationship between network management and network physical topology, network equipment increases, network complexity inevitably increases, and network management becomes more and more difficult, which seriously restricts the improvement of network service quality. This paper designs a multi-tenant oriented network resource allocation and management platform based on SDN (Software Defined Network), which provides different view interfaces for different tenant networks, and realizes the tenant resource allocation function and traffic isolation function. At the same time, the SDN-based bandwidth-aware energy-saving routing scheme focuses traffic on as few links as possible by sleeping suitable switches and links, thus achieving the energy-saving goal, balancing the network load and avoiding network congestion. Experimental results show that under different traffic models, compared with different algorithms, the proposed algorithm improves link bandwidth utilization and throughput, and reduces the average round-trip delay of traffic, thus improving the overall network performance of the data center.