Airline Inline Recovery Using SMS Coordination Graph Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for airline inline recovery are sub-optimal due to localized decision-making, inability to consider network-wide effects, and lack of handling uncertainty, leading to inefficient flight delay management and missed passenger connections.
Innovation Solution
A Stochastic Minplus with State (SMS) agent-based approach that models airline operations as a stochastic optimization problem, using a coordination graph to capture network-wide effects and incorporate uncertainty through state-dependent cost functions, iteratively optimizing flight recovery actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If localized manual decision-making is used for inline recovery, then decision speed is improved, but global optimality deteriorates
Solution Approach 1:
The airline network is segmented into multiple coordination graphs, where each graph represents a subset of flights and their interdependencies. This segmentation allows distributed decision-making that maintains global optimality while enabling faster local computations, resolving the contradiction between decision speed and global optimality.
Solution Approach 2:
An automated recovery system acts as an intermediary between localized manual decisions and global network optimization. The system processes flight delay information, evaluates recovery options using optimization algorithms, and recommends actions that balance local decision speed with global optimality, eliminating the need for manual intervention while maintaining both speed and optimality.
2Reliability
If automated decision support is implemented for global inline recovery, then global optimality is improved, but decision speed deteriorates
Solution Approach 1:
The optimization problem is segmented into smaller coordination graphs that can be processed independently and in parallel. This reduces the computational burden of automated decision-making while maintaining global optimality through coordinated solutions across segments, thus improving decision speed without sacrificing optimality.
Solution Approach 2:
The system implements partial automation by focusing computational resources on critical flight segments and recovery actions that have the most significant impact. Rather than optimizing every possible action across the entire network, the system identifies and addresses the most important decisions, achieving good global optimality faster than comprehensive optimization would allow.
3Reliability
If comprehensive network-wide recovery optimization is performed, then recovery effectiveness is improved, but computational complexity deteriorates
Solution Approach 1:
The comprehensive network-wide optimization problem is divided into smaller coordination graphs representing subsets of flights. Each sub-problem is computationally tractable and can be solved independently, then integrated to achieve overall network-wide recovery effectiveness without the exponential complexity of solving the entire problem at once.
Solution Approach 2:
The optimization approach transitions from a monolithic high-dimensional problem to a structured hierarchy of lower-dimensional sub-problems organized in coordination graphs. This dimensional decomposition reduces computational complexity while maintaining recovery effectiveness through the coordinated interaction of sub-solutions.
Data Source
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.