摘要
针对当前机场终端区空中交通中存在的航班着陆成本过大,飞机延误率过高,调度成本过大等问题,提出利用深度强化学习算法结合终端区调度算法的一系列新调度算法,重点在于解决机场终端区空中交通中待着陆飞机的安全时间间隔与着陆成本的矛盾,使飞机在安全着陆的前提下尽量减少着陆成本.实验结果表明,新调度算法在着陆成本上明显低于传统调度算法先来先服务算法.
Aiming at the problems of excessive aircraft landing costs,excessive aircraft delay rates,and excessive scheduling costs in the current air traffic in the terminal area of the airport,a series of new scheduling algorithms using deep reinforcement learning algorithms combined with terminal area scheduling algorithms are proposed.The focus is to resolve the contradiction between the safety time interval of the aircraft to be landed and the landing cost in air traffic in the terminal area of the airport,so that the aircraft can minimize the landing cost under the premise of safe landing.The results show that the new scheduling algorithm is significantly lower in landing cost than the traditional sched uling algorithm.
作者
卢锐轩
LU Rui-xuan(National Key Laboratory of Fundamental Science on Synthetic Vision,Sichuan University,Chengdu 610065)
出处
《现代计算机》
2020年第8期8-11,36,共5页
Modern Computer
关键词
机场终端区
空中交通
航班着陆调度
深度强化学习
Airport Terminal Area
Air Traffic
Aircraft Landing Scheduling
Deep Reinforcement Learning