A Data-Driven Heuristic Method for Irregular Flight Recovery

In this study, we develop a data-driven heuristic method to solve the irregular flight recovery problem. Based on operational data from China South Airlines, Beijing, China, evaluate importance of in network and influence delay its subsequent flights. Then, classify historical states into three scenarios according their reasons investigate patterns for each scenario. Inspired by results analysis, algorithm that imitates dispatcher actions. The is based two basic operations: swapping tail numbers flights resetting departure times. can provide multiple plans real time different scenarios, continue refine validate more robust general solutions through cost analysis. Finally, test efficiency effectiveness schedule, with simulated delays, compare it other methods actions dispatchers.