Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Distributionally Robust Ground Delay Programs with Learning-Driven Airport Capacity Predictions

Haochen Wu, Xinting Zhu, Shuchang Li, Ying Zhou, Lishuai Li, Max Z. Li

Abstract

Strategic Traffic Management Initiatives (TMIs) such as Ground Delay Programs (GDPs) play a crucial role in mitigating operational costs associated with demand-capacity imbalances. However, GDPs can only be planned (e.g., duration, delay assignments) with confidence if the future capacities at constrained resources (i.e., airports) are predictable. In reality, such future capacities are uncertain, and predictive models may provide forecasts that are vulnerable to errors and distribution shifts. Motivated by the goal of planning optimal GDPs that are \emph{distributionally robust} against airport capacity prediction errors, we study a fully integrated learning-driven optimization framework. We design a deep learning-based prediction model capable of forecasting arrival and departure capacity distributions across a network of airports. We then integrate the forecasts into a distributionally robust formulation of the multi-airport ground holding problem (\textsc{dr-MAGHP}). We show how \textsc{dr-MAGHP} can outperform stochastic optimization when distribution shifts occur, and conclude with future research directions to improve both the learning and optimization stages.

Distributionally Robust Ground Delay Programs with Learning-Driven Airport Capacity Predictions

Abstract

Strategic Traffic Management Initiatives (TMIs) such as Ground Delay Programs (GDPs) play a crucial role in mitigating operational costs associated with demand-capacity imbalances. However, GDPs can only be planned (e.g., duration, delay assignments) with confidence if the future capacities at constrained resources (i.e., airports) are predictable. In reality, such future capacities are uncertain, and predictive models may provide forecasts that are vulnerable to errors and distribution shifts. Motivated by the goal of planning optimal GDPs that are \emph{distributionally robust} against airport capacity prediction errors, we study a fully integrated learning-driven optimization framework. We design a deep learning-based prediction model capable of forecasting arrival and departure capacity distributions across a network of airports. We then integrate the forecasts into a distributionally robust formulation of the multi-airport ground holding problem (\textsc{dr-MAGHP}). We show how \textsc{dr-MAGHP} can outperform stochastic optimization when distribution shifts occur, and conclude with future research directions to improve both the learning and optimization stages.
Paper Structure (20 sections, 5 equations, 6 figures, 3 tables, 1 algorithm)

This paper contains 20 sections, 5 equations, 6 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Motivation and research problem
  3. Background and prior works
  4. Contributions
  5. Methodology
  6. Airport capacity distribution prediction
  7. Deriving actual capacities from throughput
  8. Probabilistic capacity prediction
  9. Distributionally robust MAGHP (dr-MAGHP)
  10. Scenario reduction and dr-MAGHP reformulation
  11. Experimental results and discussion
  12. Capacity distribution prediction
  13. Data description
  14. Prediction experimental setup and results
  15. Capacity distribution prediction results
  16. ...and 5 more sections

Figures (6)

  • Figure 1: Learning-driven airport capacity distribution prediction and distributionally robust GDP optimization framework.
  • Figure 2: Distributions in the Wasserstein ambiguity set.
  • Figure 3: Predicted departure capacity distributions for LAX on December 31, 2019. Blue area from 9:00-21:00 is the 12-hour solution window of the dr-MAGHP.
  • Figure 4: In-sample performance of sp-MAGHP and dr-MAGHP based on predicted capacity distributions
  • Figure 5: Percent increase in delayed flights under dr-MAGHP versus sp-MAGHP with (a) $\epsilon = 0.1$, (c) $\epsilon = 0.5$; Percent decrease in delayed flights under dr-MAGHP versus sp-MAGHP with (b) $\epsilon = 0.1$, (d) $\epsilon = 0.5$.
  • ...and 1 more figures