Airline Inline Recovery Using SMS Coordination Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing airline operations face challenges in optimizing inline recovery due to complex network dependencies, localized and manual decision-making leading to sub-optimal solutions, and the inability to consider global effects of local actions, which results in unpredictable and inefficient flight operations.
Innovation Solution
A Stochastic Minplus with State (SMS) agent-based approach that utilizes a digital twin of the airline network to iteratively process flight states, minimizing an objective function that includes costs per missed passenger, departure delay, and intervention actions, while considering resource and delay propagation constraints, using a state-dependent cost function and stochastic optimization to recommend optimized action vectors for inline recovery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated decision support is implemented for global inline recovery, then global efficiency and optimization are improved, but system complexity and computational requirements increase
Solution Approach 1:
The patent segments the complex airline network into multiple coordination graphs, where each graph represents a subset of flights and their interdependencies. This segmentation allows the automated system to process global recovery problems in manageable chunks while maintaining overall optimization, thus improving reliability without overwhelming system complexity.
Solution Approach 2:
The system dynamically adjusts the coordination graph structure and optimization parameters based on real-time network state. This dynamic approach enables the automated decision support to adapt to changing conditions, improving global efficiency while managing computational complexity through adaptive rather than static processing.
2Speed
If manual localized decision making is used for inline recovery, then decision speed is improved, but optimization quality and global efficiency deteriorate
Solution Approach 1:
The patent introduces an automated decision support system as an intermediary between manual localized decisions and global optimization goals. This intermediary processes local decisions through coordination graphs that capture global network effects, thereby maintaining the speed of localized decision-making while improving optimization quality through automated global perspective.
Solution Approach 2:
The system applies local quality by allowing different parts of the network to be processed with different levels of automation and detail. High-impact decisions are processed through full automated optimization, while lower-impact decisions maintain manual processing, thus balancing decision speed with optimization quality across different local contexts.
3Reliability
If comprehensive global optimization is implemented, then recovery effectiveness is improved, but computational time and processing requirements increase
Solution Approach 1:
By segmenting the airline network into coordination graphs based on flight interdependencies, the system computes localized optimizations that collectively achieve global recovery effectiveness. This segmentation dramatically reduces computational time compared to processing the entire network as a single optimization problem, while maintaining recovery effectiveness through the coordinated interaction of local solutions.
Solution Approach 2:
The system implements partial optimization by focusing computational resources on the most critical flights and coordination graphs that have the greatest impact on overall recovery. Rather than attempting to optimize every flight simultaneously, the system applies optimization selectively to high-impact areas, achieving effective recovery with reduced computational time.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
Addressing automated global inline recovery is challenging using state of the art approaches as it is non-trivial due to the complex dependencies between local actions and global effects. A method and system disclosed herein models inline recovery for intelligent airline operations as a stochastic optimization problem via Stochastic Minplus with State (SMS) agent that captures higher-order network-wide effects of airport-level local recovery actions. The system exploits domain knowledge encoded as a coordination graph to achieve scale for real-time decision making. contribution: The MaxPlus algorithm from literature is modified to handle state-based coordination graphs with stochasticity and resource constraints. The heuristic for inline recovery targets aircraft delay and missed passenger (PAX) connections. Quick turn-around and flight delay is used as recovery actions. Heuristics are combined with simulation to incorporate uncertainty.