基于改进的DDPG机场机位分配算法研究
首发时间:2021-03-31
摘要:停机位是机场的重要资源,机位分配方案是机场运行安全和效率的关键因素。现在机位分配过程主要还是依赖于人工操作,人工智能算法的应用能够减少工作人员的工作量并提高分配效率,这是具有重要意义的。本文综合考虑机场的多个约束条件后,以最大进港靠桥的航班数作为优化目标建立相应的数学模型,并将其转化成马尔可夫决策过程模型。设计环境的状态空间和智能体的动作空间,将大规模的离散动作空间通过构建特征的方式转变为连续动作空间,提出基于KNN的DDPG机位分配模型。以乌鲁木齐地窝堡国际机场的实际航班数据进行仿真实验,验证模型的有效性,能够提高机位资源的利用率。在对比实验中,DDPG_KNN的效果要优于遗传算法。
For information in English, please click here
Research on Airport Gate Assignment Based on Improved DDPG Algorithm
Abstract:gate is an important resource of an airport, and the assignment of the airport gate is a key factor for the safety and efficiency of airport operation.At present, the gate assignment process is mainly dependent on manual operation. The application of artificial intelligence algorithm can reduce the workload of staff and improve the allocation efficiency, which is of great significance.In this paper, a mathematical model is established by taking the maximum number of flights approaching the airport as the optimization objective, and the model is transformed into a Markov decision process model.The state space of the environment and the action space of the agent are designed, and the large-scale discrete action space is transformed into a continuous action space by the way of constructing features. A DDPG gate assignment model based on KNN is proposed.The actual flight data of Urumqi Diwopu International Airport is used for simulation experiments to verify the effectiveness of the model, which can improve the utilization rate of flight resources.In the comparison experiment, the effect of DDPG_KNN is better than that of genetic algorithm.
Keywords: Airport gate assignment Deep Reinforcement learning DDPG Genetic algorithm
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于改进的DDPG机场机位分配算法研究
评论
全部评论0/1000