A IoT-Based Optimization of Cold Chain Logistics for Cost Reduction and Quality Preservation

Abstract

Cold Chain Logistics (CCL) plays a vital role in the safe distribution of temperaturesensitive products such as fresh food, pharmaceuticals, vaccines, and biological materials, where maintaining product quality throughout storage and transportation is critical. Despite its importance, conventional CCL systems often struggle to simultaneously reduce logistics costs and preserve product quality due to limited real-time monitoring, lack of predictive intelligence, and reliance on static decision-making strategies. To overcome these challenges, this study proposes an AIoT-Based Intelligent Cold Chain Logistics Optimization Model (AIoT-ICCLM) that integrates Internet of Things (IoT) technologies with artificial intelligence–driven optimization techniques. The proposed model enables continuous real-time monitoring of environmental conditions and supports intelligent decision-making to improve both operational efficiency and quality preservation in CCL systems. location–routing optimization model, where distribution centers and refrigerated vehicles can be selectively equipped with IoT devices. Product quality degradation is explicitly modeled as a time-dependent  function, ensuring that all delivery decisions satisfy predefined minimum quality thresholds for perishable goods. The primary objective of the model is to minimize the total system cost, including facility establishment costs, vehicle operating costs, IoT infrastructure investment, operational expenses, and transportation costs. Due to the NP-hard nature of the formulated CCL optimization problem, four artificial intelligence–based metaheuristic algorithms—Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Gray Wolf Optimizer (GWO), and Emperor Penguin Optimizer (EPO)—are employed to efficiently obtain near-optimal solutions. Computational experiments using real-time and simulated datasets demonstrate that, although IoT deployment introduces additional initial infrastructure costs, it significantly reduces overall operational and transportation expenses through improved routing efficiency, proactive monitoring, and real-time decision support. Among the evaluated algorithms, the Emperor Penguin Optimizer (EPO) consistently achieves superior performance in terms of solution quality and computational efficiency. The experimental results confirm the effectiveness of the proposed AIoTICCLM in enabling intelligent, costefficient, and quality-preserving Cold Chain Logistics systems. This study provides valuable insights for logistics managers and policymakers regarding strategic IoT deployment and the practical application of AI-based optimization models in modern perishable goods supply chains.