面向大规模航空集群组网的控制器部署方法

Research on Controller Deployment Method for Large-Scale Aviation Swarm Networks

软件定义网络(SDN)使得控制平面与数据平面解耦,可用来优化航空集群网络体系结构。针对航空集群网络大规模组网需求,设计了一种面向大规模航空集群网络的控制器部署优化算法,将多控制器部署转化为集群划分和子群部署两个阶段,首先基于负载均衡将集群划分为不同子群,然后以全网性能最优为目标于各子群内进行多目标寻优,获得Pareto前沿解。仿真实验评估了所提算法在负载均衡指数、全网平均传播时延、平均失连概率等方面的性能。实验结果表明:与现有算法相比,所提算法有效地提升了全网性能,同时具有较低的时间复杂度,适用于解决大规模动态场景下的航空集群网络控制器部署问题。

The software-defined networks(SDN)not only enable the control plane to be coupled with the data plane,further can be also used to optimize the aviation swarm network architecture.In view of satisfying the demand of large-scale aviation swarm networking,a controller deployment optimization algorithm for large-scale aviation swarm networks(ASNs)is designed.The proposed algorithm transforms the deployment of multiple controllers into two phases,i.e.,the swarm division and sub-swarm deployment.First,the swarm is divided into sub-swarms according to the load balance,and then the multiple-objectives optimization is performed in each sub-swarm based on the global optimum to obtain the Pareto frontier solutions.The simulation experiment evaluates the performance of the proposed algorithm in terms of the load balance index,average propagation delay and average disconnection probability of the entire network.The experimental result shows that compared with the existing algorithms,the proposed algorithm effectively enhances the performance of the entire network,and has lower time complexity.And the proposed algorithm is available for addressing the controller deployment issue in large-scale and dynamic ASNs.