Multilateral Network Transformation for Transport Mode Selection of Multimodal Transportation

Abstract

As a challenging combinatorial optimization problem, transport mode selection in multimodal transportation is difficult to solve for large-scale networks. This study proposes a novel solution framework to address this challenge. First, we adopt a network transformation method, Node Splitting and Subnode Connecting (NSSC), tailoring it to convert the complex multilateral transportation network into a standard directed graph, making it amenable to established optimization models. Second, recognizing that exact solvers can be computationally prohibitive for large instances, we develop a high-performance heuristic algorithm. This algorithm is based on the concept of Effective Transfer (ET), a logistics-oriented principle to identify strategically advantageous routes. By using an ET-based route search to prune the solution space, our method can efficiently find high-quality, time-feasible solutions. Comparative experiments show that our proposed framework significantly outperforms the widely-used typical solver (Gurobi) and a well-established heuristic ( $K$ -Restricted Label Setting), and offers a better trade-off between solution quality, computational time, and memory usage than the solver and the heuristic on large networks.