Congestion-Aware Scheduling for Software-Defined SAG Networks
Congestion-Aware Scheduling for Software-Defined SAG Networks
复制标题
软件定义 SAG 网络的拥塞感知调度
DOI：
10.1109/tnse.2021.3055372
复制
发表时间：
2021
影响因子：
6.6
通讯作者：
Li Keqiu
中科院分区：
文献类型：
--
作者：
Tao Xiaoyi;Ota Kaoru;Dong Mianxiong;Qi Heng;Li Keqiu
作为一种成功的全球通信解决方案，天空地(SAG)网络受到了广泛的关注。卫星作为一种空间通信方式，受到地理特征的影响。由于交通拥堵可能发生在人口稠密的城市，导致严重的延迟和吞吐量崩溃。为了解决这一问题，我们首先将软件定义网络(SDN)引入到卫星中，然后提出了一种负载均衡方法来提高通信性能。然而，SDN空地网络需要一个协同的通信过程，我们将此问题归结为一个支持SDN的路由器放置问题，这样我们就可以决定哪些传统路由器正在升级，以确保混合网络的健壮性。基于空间-空中-地面混合网络，我们设计了一种负载均衡策略来优化网络之间的流量分配，从而使总的拥塞链路最小化。为了提高空-空-地网络的性能，我们提出了一种弹性拥塞估计方案。绕行附近卫星周围的流量以优化流量负载是基于网络条件的决策。仿真结果表明，该方法比传统的卫星网络方法分别提高了6.5%和4.4%的丢包率，提高了11.6%和8.3%的吞吐量。
As a successful solution for global communications, Space-Air-Ground (SAG) networks, have drawn extensive attention. Satellites are influenced by geographical features as a way of space communications. Since the traffic congestion may occur in densely populated cities, leading to serious latency and throughput collapses. To solve this problem, we first introduce Software Defined Networks (SDN) into satellites and then propose a load balancing approach to improve communication performances. However, the SDN Space-Air-Ground networks need a cooperative communication process, we consider this problem as an SDN-enabled routers placement problem, so that we can decide the exactly traditional routers are upgrading to ensure the robustness of hybrid networks. Based on the hybrid Space-Air-Ground networks, we design a load balancing strategy to distribute traffic among networks optimally, so that the total congested links are minimized in our proposed model. For better performance in Space-Air-Ground networks, we propose a resilient congestion estimate scheme. Detouring traffic around the nearby satellites to optimize traffic load is a decision based on the network condition. Simulation results illustrate that our proposed method outperforms traditional satellite network methods by improving 6.5% and 4.4% packet loss rate, and 11.6% and 8.3% higher throughput respectively.