任务优先满足和绩效奖励的重叠联盟效用分配  

Payoff distribution of overlapping coalitions for task priority satisfaction and performance rewards

作　　者：桂海霞[1] 赵邦磊 张国富[2] 苏兆品[2] 蒋建国[2] Gui Haixia;Zhao Banglei;Zhang Guofu;Su Zhaopin;Jiang Jianguo(School of Economics and Management,Anhui University of Science and Technology,Huainan 232001,China;School of Computer and Information Science,Hefei University of Technology,Hefei 230009,China)

机构地区：[1]安徽理工大学经济与管理学院,安徽淮南232001 [2]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《系统工程学报》2021年第3期302-313,共12页Journal of Systems Engineering

基　　金：国家自然科学基金资助项目(61703005);安徽省自然科学基金资助项目(1808085MG221);安徽理工大学硕博基金资助项目(12059).

摘　　要：效用分配是联盟形成中的一个难点问题,合理的效用划分方式有利于联盟的形成与稳定.针对重叠联盟中一个Agent可以参与多个任务的复杂情形,提出了任务优先满足的任务分派方法.当新的Agent成员加入到联盟中时,任务分派时对原有联盟成员给予绩效奖励,然后根据任务分派情况进行效用划分,最后通过实例与已有的效用分配策略进行了对比分析.结果表明,本文所提策略能更好的满足效用非减,充分体现各Agent对联盟贡献的差异性,同时满足时效性、稳定性和动态性等特征.Payoff distribution is a difficult problem in coalition formation,and a reasonable payoff division is conducive to the formation and stability of coalition.Considering the complex situation that one agent can participate in multiple tasks in the overlapping coalition,this paper proposes a task assignment method for task priority satisfaction.when a new agent member joins the coalition,the original coalition members are given performance rewards during task assignments,and then the payoff is divided according to task assignment.Finally,a case study is carried out to compare with the existing payoff distribution strategies.The results show that the strategy proposed in this paper can better meet the non-diminishing condition of utility and fully reflect the differences of the contributions of each agent member of the coalition.At the same time,it can also satisfy the characteristics of timeliness,stability and dynamic.

关 键 词：重叠联盟 任务分派 绩效奖励 效用分配 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]