Big Data-Driven Collaborative Optimization Model for Cold Chain Multimodal Transport Resources

Abstract

Cold chain logistics, essential for preserving the integrity of temperature-sensitive commodities such as perishable food and biopharmaceuticals, faces persistent inefficiencies in multimodal transport systems, where transportation costs constitute 30.47% to 39.82% of total logistics expenditure and cargo loss rates range from 10.23% to 14.68%. This study proposes an advanced big data-driven collaborative optimization model that integrates multi-source heterogeneous data, multi-objective optimization frameworks, and dynamic algorithmic mechanisms to enhance economic efficiency, timeliness, reliability, and environmental sustainability. By leveraging Internet of Things (IoT) sensors, blockchain for data integrity, digital twin simulations, and edge computing, the model achieves cost reductions of 14.862% and transit time savings of 19.627% in empirical validations across cross-border and e-commerce scenarios. Detailed data analyses, encompassing 3.224 million data points and 1,842 disruption scenarios, demonstrate the model’s robustness. The study addresses data-sharing reluctance, system interoperability challenges, and regulatory fragmentation, offering a scalable framework for AI-driven, sustainable cold chain logistics aligned with global policy imperatives.