Transmission Quality Optimization in Inter-Datacenter WAN

Yadong Liu · 2020

Inter-datacenter wide area network provides high bandwidth and low delay connections for data center nodes in different regions. However, different cross data center traffic has different requirements for the network. It is very important for network operators to understand the requirements of upper applications and improve the network quality of services. Some existing traffic engineering schemes are devoted to improving the utilization of network bandwidth. However, they fail to consider the impact on transmission quality caused by failure to complete within the deadline when making scheduling schemes. In this paper, we aim to improve the overall transmission quality of the network, i.e. make full use of network bandwidth resources to improve the acceptance ratio and completion ratio of large transfer tasks without affecting the completion time of interactive flow. In order to achieve the above goals, we formulate the problem of transmission quality optimization and transforms the piecewise and discontinuous optimization objectives of the original problem into a form that is easy to solve. In addition, we propose a progressive approximation algorithm (PAA) to find an approximate solution for the problem in a feasible time range. Finally, based on the real Inter-datacenter WAN topology and different traffic patterns, a large-scale simulation experiment is carried out, which proves that the algorithm proposed in this paper can effectively improve the transmission quality of large transfer in Inter-Datacenter WAN.

Read the paper · More papers on PaperTik