多目标情景树算法研究及应用  

Optimized Algorithm of Multi-objective Scenario Tree and Its Application

作　　者：张惠秋[1] 包振强[1] 杨雨露[1] 李宁川[2] 任晓青[1] 

机构地区：[1]扬州大学信息工程学院,江苏扬州225009 [2]扬州大学体育学院,江苏扬州225009

出　　处：《无线电工程》2015年第11期9-12,共4页Radio Engineering

基　　金：扬州市科技攻关项目基金资助(YZ2011101)

摘　　要：针对传统情景树只能产生单一优化解的缺点,提出了一种多目标情景树算法。运用Pareto进行多目标排序,并从历史复杂情景中找到与问题情景相似的非支配解集,从而避免了传统单组权值计算产生的单一优化。相对于传统情景树算法,该方法得出的非支配解集更接近问题情景,更满足实际需求。通过居民健康管理系统的应用实例,充分验证了该算法的有效性和实用性。Anoptimized algorithm of multi-objective scenario tree is put forward. It finds the non-dominated solution set by using Pareto for sorting multiple objectives,which is similar with the historical complex scenes.The problem of the traditional single optimized way is avoided which calculates similarityby a single weighted set,so the non-dominated solution setgained from the proposed algorithmis closer to the actual demand.Finally,the application exampleof the resident health-management system validates the effectiveness and practicability of the algorithm.

关 键 词：多目标 情景树 相似度 非支配解集 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]