支持边缘端—云端协同工作的群组命令传输算法  

Group command transfer algorithm for edge-cloud cooperative work

作　　者：颜晓莲 邱晓红 Yan Xiaolian;Qiu Xiaohong(School of Software Engineering,Nanchang Campus of Jiangxi University of Science&Technology,Nanchang 330013,China)

机构地区：[1]江西理工大学软件工程学院(南昌),南昌330013

出　　处：《计算机应用研究》2021年第4期1154-1157,共4页Application Research of Computers

基　　金：江西省教育厅科技项目(GJJ170571)。

摘　　要：Internet是连接云端与分布在不同区域边缘端的重要传输载体,其尽力而为的服务模式在支持群组控制命令传输时,会造成快速消耗网络资源及路径竞争等问题。首先,把Internet群组控制命令传输问题转换为不相交带约束的多Steiner树问题(constrainted multi-Steiner trees with disjoint problem,CMSTDP),并提出一种改进型遗传算法。该算法聚焦于提升全局搜索能力和缓解路径竞争两个方面。实验从群组命令传输成功率、收敛延时比及解误差率三个方面验证,该算法适合应用于边缘端—云端之间的群组命令传输。Internet as an important carrier connected cloud and edge distributed in different areas,its best-effort service mode will cause problems such as fast consumption of network resources and path competition when supporting group control commands transfer.First,this paper transformed group control command transfer problem into constrained multi-Steiner trees with disjoint problem,and proposed a kind of improved genetic algorithm.The algorithm focused on improving the global search abi-lity and alleviating the path competition.The experiment verifies by transfer success rate,convergence delay rate and solutions error rate shows that the algorithm is suitable for group command transfer between edge and cloud.

关 键 词：群组命令传输 边缘端—云端协同工作 STEINER树 遗传算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]