分布式场景下基于拍卖算法的边缘智能节点任务分配  

Task Assignment of Edge Intelligent Nodes Based on Auction Algorithm in Distributed Scenarios

作　　者：李浩 陈迪 李林 王莉 LI Hao;CHEN Di;LI Lin;WANG Li(Unit 63892,Luoyang 471003,China)

机构地区：[1]63892部队,河南洛阳471003

出　　处：《移动通信》2022年第9期24-29,共6页Mobile Communications

摘　　要：针对分布式场景下的边缘智能节点任务分配问题,构建了多类型的任务分配模型用于描述边缘智能节点与任务之间的关系,提出了一种基于拍卖算法的任务分配方法。智能边缘节点以动态拍卖的方式获取各自任务。基于拍卖算法的任务分配,智能边缘节点分为拍卖节点和竞标节点。在拍卖过程中,拍卖节点不仅仅考虑竞标节点的任务出价,还考虑竞标节点的资源能力。为了激励边缘节点出价的合理性,提出了激励机制用于促进边缘智能节点提供真实出价。仿真结果表明了所提算法的有效性和合理性。Aiming at the task assignment of edge intelligent nodes in distributed scenarios,a multi-type task assignment model is constructed to describe the relationship between edge intelligent nodes and tasks,and a task assignment method based on the auction algorithm is proposed.Specifically,intelligent edge nodes acquire their tasks by dynamic auction,where intelligent edge nodes are divided into auction nodes and bidding nodes.In the auction process,the auction node not only considers the task bid of the bidding node,but also considers its resource capacity.In order to motivate the rationality of edge node bidding,an incentive mechanism is proposed to promote edge intelligent nodes to provide real bids.Simulation results show the effectiveness and rationality of the proposed algorithm.

关 键 词：任务分配 网络效益 拍卖算法 激励机制 

分 类 号：TN929[电子电信—通信与信息系统]