基于多Agent的通航运力资源协同调度  

Collaborative Schedule of General Aviation Resource Based on Multi-Agent

作　　者：张红颖 周子林 李彪 ZHANG Hong-ying;ZHOU Zi-lin;LI Biao(College of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300,China;College of Aviation Engineering,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学电子信息与自动化学院,天津300300 [2]中国民航大学航空工程学院,天津300300

出　　处：《交通运输系统工程与信息》2020年第1期214-221,共8页Journal of Transportation Systems Engineering and Information Technology

基　　金：国网通航2018年科技项目(52950017000G)~~

摘　　要：针对并行式多任务条件下的通航运力资源调度效率较低问题,提出一种基于多Agent协商的通航运力资源协同调度方法.构建多Agent通航资源协同调度框架,建立基于招投标机制的运力资源匹配性模型以提升并行任务处理能力,在匹配性结果基础上设计资源调度策略,最后使用实际运行数据验证本文提出方法的可行性.仿真结果表明:该方法资源调度速率受并行任务数量影响较小,满足实时性需求;相比常用Agent算法所得调度结果,单机日利用率平均提升0.19 h/d,作业时长均方差平均降低0.03 h,能够快速有效地调度通航运力资源.Aiming at the low efficiency of resource scheduling in the condition of parallel tasks,a collaborative schedule method based on multi-Agent negotiation is proposed for general aviation.Firstly,the collaborative scheduling framework is established,and the matching model based on bidding mechanism is created to improve the processing ability of parallel tasks.Then the scheduling strategy is designed refer to the matching result.Finally,the actual data is applied to verify the effectiveness of the method.The simulation results demonstrate that the method is hardly affected by the number of parallel tasks,and the calculating time can meet requirements.Compared with the results obtained by Agent algorithms,the average daily utilization rate of single plane increases 0.19 h/d,the average variance is reduced by 0.03 h,which proves that the method can effectively schedule resources in a fast rate.

关 键 词：航空运输 协同调度 多AGENT协商 运力资源匹配 通航 

分 类 号：U8[交通运输工程] V2-9[航空宇航科学技术]