Adaptive Ant Colony Optimization Algorithm Based on Real-Time Logistics Features for Instant Delivery

Area of Science:

• Operations Research
• Computer Science
• Logistics Management

Background:

• Ant Colony Optimization (ACO) is utilized for instant delivery scheduling due to its distributed nature.
• Current ACO methods face challenges in maintaining delivery efficiency with dynamic logistics statuses.

Purpose of the Study:

• To enhance the performance of Ant Colony Optimization (ACO) for instant delivery order scheduling.
• To develop an adaptive ACO algorithm that incorporates real-time logistics features (AACO-RTLFs).

Main Methods:

• Feature extraction from event, spatial, and time dimensions to define real-time logistics status.
• Development of an adaptive instant delivery model incorporating customer acceptable delivery time, emergency order marks, and weather conditions.
• Proposal of an adaptive ACO algorithm with adjusted parameters based on extracted key logistics factors.

Main Results:

• The adaptive ACO algorithm (AACO-RTLF) effectively improves instant delivery order scheduling.
• Numerical experiments using the Gurobi solver validated the algorithm's effectiveness on classical datasets.
• AACO-RTLF demonstrated superior performance compared to existing state-of-the-art algorithms in instant delivery scenarios.

Conclusions:

• The proposed AACO-RTLF algorithm offers significant advantages for instant delivery order scheduling.
• Real-time logistics feature integration and adaptive parameter adjustment are crucial for optimizing delivery efficiency.
• The adaptive instant delivery model effectively accounts for critical factors influencing delivery times.