Application of a Genetic Algorithm–Particle Swarm Optimization-Based Data-Driven Framework for Agricultural Cold Chain Logistics Network Layout Optimization
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This paper proposes a hybrid optimization framework based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) that dynamically optimizes network configurations using real-time logistics data. The framework combines GA’s global search capability with PSO’s local search advantage to efficiently optimize warehouse layout, transportation routes, and resource allocation, minimizing the total cost of cold chain logistics while ensuring timely delivery of perishable agricultural products. Experimental validation using both real-world and simulated datasets shows that the proposed GA-PSO hybrid method outperforms traditional Linear Programming (LP) and Deep Reinforcement Learning (DQN) approaches in reducing cold chain logistics costs (17.0%), shortening delivery time (11.0%), and improving warehouse utilization (7.8%). This study demonstrates that the algorithm framework can effectively address the dynamics and complexity of large-scale cold chain networks, providing a feasible and efficient solution for the intelligent optimization of agricultural cold chain logistics systems.
Fields of Study & Subjects
Food Supply Chain Traceability
Logistics and Infrastructure Analysis
Vehicle Routing Optimization Methods
Publication details
- Journal / source
- IEEE International Conference on Power, Electronics and Green Energy (ICPEGE)
- Pages
- 834–839
- Publication date
- 28 January 2026
- Language
- EN