With the current trend towards low Earth orbit mega-constellations with inter-satellite links, efficient routing in such highly dynamic space-borne networks is becoming increasingly important. Due to the distinct network topology, specifically tailored solutions are required. Firstly, the relative movement of the constellation causes frequent handover events between the satellites and the terminals on ground. Furthermore, unevenly distributed traffic demands lead to geographical hot spots. The physical size of the network also implies significant propagation delays. Therefore, monitoring the dynamic topology changes and link loads on a network-wide basis for routing purposes is typically impractical with massive signaling overhead. To address these issues, we propose a distributed load-balanced routing scheme based on Software Defined Networking. The approach divides the large-scale network into sub-sections, called clusters. In order to minimize signaling overhead, packets are forwarded between these clusters according to geographical heuristics. Within each cluster active Quality of Service-aware load-balancing is applied. The responsible on-board network controller forwards routing instructions based on the network state information in its cluster. We also analyze specific design choices for the clusters and the interfaces between them. The protocol has been implemented in a system-level simulator and compared to a source-routed benchmark solution.
翻译:随着目前低地球轨道超星星系与卫星之间连接的趋势,在这种高度动态的空基网络中高效的航线正在变得越来越重要。由于不同的网络地形,需要专门设计的解决办法。首先,星座的相对移动导致卫星和地面终端之间频繁交接事件。此外,交通需求分布不均导致地理热点。网络的物理规模也意味着显著的传播延迟。因此,在全网络基础上监测动态的地形变化和连接路由负荷通常不切实际,因为有大量的间接信号。为了解决这些问题,我们提议了一个基于软件定义网络的分布式负载平衡路由计划。该方法将大型网络分成若干小区,称为集群。为了最大限度地减少信号间接点,这些集群之间会发生交通量分配不均的情况。在每个集群中,都应用了服务认知式负载平衡的积极质量。负责在机载网络上控制基于网络状态信息的前向指令。为了解决这些问题,我们提议了基于软件定义网络联网的分布式平衡路由方案。我们还分析了大型网络分为几个小区段,称为集群的分段。为了尽量减少集,我们还分析了具体设计路径选择了它们之间的界面,比较了它们之间的基准级。我们还比较了一个系统。