Subflow scheduling strategy for multipath transmission in SDN-based spatial network

The spatial network has numerous nodes and complex links, which makes it more suitable for the Multipath Transmission Control Protocol (MPTCP). As an extension of the traditional TCP protocol, this protocol can aggregate the bandwidth of multiple paths to improve transmission performance. However, the traditional network architecture has limited support for MPTCP, making it impossible to select a good transmission path for the subflow according to the current global network status, so it is easy to cause subflow collision. By separating the control plane and data plane, the Software Defined Network (SDN) architecture can obtain the global network status and better manage the network. The introduction of SDN can solve the problem that traditional networks cannot optimize subflow transmission based on the global network status. However, the existing SDN-based solutions mainly optimize the terrestrial network and take the available bandwidth of the network as the key reference factor, which is not suitable for the network environment with a large scale of time and space such as the spatial network. Besides, due to the high-speed movement of satellite nodes, frequent link switching will cause the selected path to fail and affect the subflow transmission on the path. For this reason, a dynamic subflow allocation strategy for multi-path transmission in SDN-based spatial networks is proposed in this paper, which uses the SDN controller to monitor and analyze the network status, and selects multiple optimal and disjoint transmission paths for the subflow based on the delay and bandwidth of the path to improve the link utilization and load balancing. Then, the strategy uses the predictable characteristics of the spatial network topology to predict the link to be disconnected, reselects the optimal path for the subflow, and solves the problem that the subflow cannot be continuously transmitted due to link switching. The experimental results show that the strategy in this paper is more suitable for the spatial network, because the selected path has lower delay and higher bandwidth. It solves the collision problem of subflows, and makes the subflow transmission have better stability in the highly dynamic spatial network.