Adaptive Digital Twin for Optimizing Repositioning, Routing, and Matching in Private Floating Fleets

Private charter fleets are valuable mobile assets that, when efficiently managed, can generate substantial revenue for operators and owners. A key factor in maximizing profitability is achieving a high asset utilization rate. We propose the development of a large-scale adaptive digital twin for supporting private floating fleet repositioning, routing and matching decisions. The digital twin is designed to connect thousands of charter aircraft and passengers in real time in a virtual private air travel network. Metaheuristic repositioning/routing/matching algorithms will be designed to optimize floating fleet assignments. These algorithms will account for various operational constraints and costs, including regulatory compliance, insurance, fuel surcharges, crew fees, and airport charges.
The digital twin will employ a microservice-enabled multi-agent system architecture to model key components—operators, passengers, aircraft, airports, and more. This back-end infrastructure will enable the industrial partner to monitor dynamic supply and demand, optimize routing and repositioning decisions, evaluate and validate a wide range of strategic, operational, and pricing scenarios. It will also be designed to be integrated with the industrial partner’s existing software systems. Additionally, the proposed platform can support the development of advanced market mechanisms such as empty-leg auctions, group bidding, and revenue-sharing models among collaborating charter operators.

Faculty Supervisor:

Chun Wang

Student:

Partner:

Airble

Discipline:

Engineering

Sector:

Transportation and warehousing

University:

Concordia University

Program: