# An intelligent stochastic optimization approach for air cargo order allocation under carbon emission constraints

## TL;DR

This paper introduces a new optimization method for air cargo order allocation that considers carbon emissions and improves efficiency.

## Contribution

A novel intelligent optimization method combining adaptive large-scale neighborhood search and scenario generation for stochastic order allocation under carbon constraints.

## Key findings

- The proposed method outperforms existing optimization methods in both capability and efficiency.
- The approach effectively handles high-dimensional stochastic order allocation with carbon emission constraints.
- Scenario generation enhances the evaluation of candidate solutions in uncertain environments.

## Abstract

In air cargo transportation, effective order allocation is crucial for improving the efficiency of business operations and reducing environmental impact. In this paper, we study a high-dimensional stochastic order allocation problem that assigns uncertain orders to different types of aircraft for transportation. Considering the carbon emission and the uncertainty of customer order arrivals in the actual transportation environment, a stochastic optimization model considering the cost of carbon emission is established with the objective of maximizing the expected profit from order transportation. A new intelligent optimization method is introduced for addressing the order assignment problem under carbon emission constraints by combining the improved adaptive large-scale neighborhood search algorithm with the scenario generation technique. The method finds the optimal solution through an improved adaptive large-scale neighborhood search algorithm and uses a scenario generation technique to generate the scenarios required for evaluating candidate solutions to the high-dimensional stochastic optimization problem. Experimental results show that this method surpasses the compared optimization methods regarding both optimization capability and optimization efficiency.