Dynamic airspace configuration method based on a weighted graph model

This paper proposes a new method for dynamic airspace configuration based on a weighted graph model. The method begins with the construction of an undirected graph for the given airspace, where the vertices represent those key points such as airports, waypoints, and the edges represent those air routes. Those vertices are used as the sites of Voronoi diagram, which divides the airspace into units called as cells. Then, aircraft counts of both each cell and of each air-route are computed. Thus, by assigning both the vertices and the edges with those aircraft counts, a weighted graph model comes into being. Accordingly the airspace configuration problem is described as a weighted graph partitioning problem. Then, the problem is solved by a graph partitioning algorithm, which is a mixture of general weighted graph cuts algorithm, an optimal dynamic load balancing algorithm and a heuristic algorithm. After the cuts algorithm partitions the model into sub-graphs, the load balancing algorithm together with the heuristic algorithm transfers aircraft counts to balance workload among sub-graphs. Lastly, airspace configuration is completed by determining the sector boundaries. The simulation result shows that the designed sectors satisfy not only workload balancing condition, but also the constraints such as convexity, connectivity, as well as minimum distance constraint.     

Locally generalised multi-agent reinforcement learning for demand and capacity balancing with customised neural networks

Reinforcement Learning (RL) techniques are being studied to solve the Demand and Capacity Balancing (DCB) problems to fully exploit their computational performance. A locally generalised Multi-Agent Reinforcement Learning (MARL) for real-world DCB problems is proposed. The proposed method can deploy trained agents directly to unseen scenarios in a specific Air Traffic Flow Management (ATFM) region to quickly obtain a satisfactory solution. In this method, agents of all flights in a scenario form a multi-agent decision-making system based on partial observation. The trained agent with the customised neural network can be deployed directly on the corresponding flight, allowing it to solve the DCB problem jointly. A cooperation coefficient is introduced in the reward function, which is used to adjust the agent’s cooperation preference in a multi-agent system, thereby controlling the distribution of flight delay time allocation. A multi-iteration mechanism is designed for the DCB decision-making framework to deal with problems arising from non-stationarity in MARL and to ensure that all hotspots are eliminated. Experiments based on large-scale high-complexity real-world scenarios are conducted to verify the effectiveness and efficiency of the method. From a statistical point of view, it is proven that the proposed method is generalised within the scope of the flights and sectors of interest, and its optimisation performance outperforms the standard computer-assisted slot allocation and state-of-the-art RL-based DCB methods. The sensitivity analysis preliminarily reveals the effect of the cooperation coefficient on delay time allocation.     

空中交通复杂性研究进展

空中交通复杂性是空中交通态势的本质属性，是空中交通管制工作负荷的主要驱动因素。空中交通复杂性的科学评价是实现空中交通精细化管理的关键，也是当前空管领域研究热点。本文介绍了国内外空中交通复杂性的研究团队，梳理了空中交通复杂性与工作负荷、安全水平等相互之间的区别和联系，并详细分析了现有研究的具体研究路线。在分析新一代空中交通管理系统特征的基础上，对空中交通复杂性的未来研究趋势和方向进行了展望。