支持向量回归在地面站资源评价模型中的应用

Support Vector Regression in Application of Ground Station Resources Evaluation Model

针对多遥感卫星地面站资源配置问题涉及的因素众多,而且仿真求解过程需要对不同场景的资源进行配置、调度,导致求解过程复杂、耗费时间较长的问题,提出了基于支持向量回归(Support Vector Regression,SVR)的资源评价模型。选取评价模型的评价指标,采用层次分析法(Analytic Hierarchy Process,AHP)与灰色关联理论并通过仿真得到评价值,将仿真数据随机分为训练样本和测试样本,求解二次规划问题,并采用遗传算法对模型进行参数寻优。试验表明,该方法求解迅速,模型具有较好的拟合和泛化能力。

There were many factors affecting multiple satellite ground station resources allocation. The resources need to be allocated and scheduled in the different scenes during simulation. The problem was too complex to be solved and it costs too much time. So the paper proposed a resource assessment model based on Support Vector Regression （Support Vector Regression）. Firstly, the evaluation indexes of evaluation model were selected based on a simulation which combines AHP （Analytic Hierarchy Process） and grey correlation. Secondly, the simulation data were randomly divided into training samples and testing samples, then the quadratic programming problem was solved. Furthermore, the genetic algorithm optimization was used to find the best SVM parameters. Experimental results show that the proposed method solved the problem quickly and the model had good fitting and generalization ability.