面向预警监视任务的雷达组网智能化资源调度

Intelligent resource scheduling of radar network for early-warning and surveillance tasks

针对当前预警监视任务中雷达组网资源调度方法难以与太空目标数量井喷式增长、太空武器多样化发展的趋势相适应,而资源调度具有场景复杂、计算量大、精度要求高等特点的问题,在对反导预警与空间目标监视2类任务中资源调度原则分析的基础上,引入层次分析法与人工智能算法对资源调度问题进行求解,在任务和雷达2个层面实现了面向预警监视任务的雷达组网智能化资源调度。在任务层面,基于层次分析法对任务优先级进行了划分,为面临多个任务冲突时的任务优先选取提供了解决途径;在雷达层面,通过构建2类任务场景下的资源调度模型,在模拟退火算法和粒子群算法的基础上进行改进,提出了面向目标分配排序作业的模拟退火混合离散粒子群算法,对资源调度方案优化中的计算时间、资源节省率、算法合格率等3个指标进行了提升,有效提高了预警监视任务中雷达组网的探测效能。

The resource scheduling method of radar network in the current missile early-warning and space surveillance tasks is difficult to adapt to the trend of blowout growth of space targets and the diversified development trend of space weapons.In addition,resource scheduling has the characteristics of complex scenes,large amounts of computation and high accuracy requirements.For the above matters,this paper introduces Analytic Hierarchy Process(AHP) and artificial intelligence algorithm to solve the resource scheduling problem based on the analysis of the resource scheduling principles in missile early-warning and space surveillance tasks.Intelligent resource scheduling of radar network for missile early-warning and space surveillance tasks is implemented at both task and radar levels.At the task level,the task priority is divided based on AHP,which provides a solution for task priority selection in the face of multi-task conflicts.At the radar level,by constructing resource scheduling models in two types of task scenarios,and on the basis of Simulated Annealing(SA) algorithm and Particle Swarm Optimization(PSO),an Improved Simulated Annealing and Binary Particle Swarm Optimization(ISABPSO) algorithm for target assignment and sequencing operation is proposed,which improves the calculation time,resource saving rate and algorithm qualification rate in resource scheduling scheme optimization.The detection efficiency of the radar network in missile early-warning and space surveillance tasks is improved effectively.