Sustainable Dynamic Route Optimization for Pharmaceutical Cold-Chain Distribution by Integrating Reinforcement Learning and Improved Neighborhood Search

Pharmaceutical cold-chain distribution must maintain timely access to temperature-sensitive medicines while limiting the energy demand and carbon emissions associated with refrigerated transport. This study proposes a sustainable dynamic route optimization method that integrates reinforcement learning (RL) with an improved neighborhood search (NS) algorithm to balance delivery timeliness and transportation carbon emissions. The NS algorithm is enhanced with carbon emission and timeliness operators, and RL adaptively adjusts their weights under dynamic events, including traffic congestion, vehicle failure, and order insertion. The method is evaluated using the Solomon Benchmark dataset and a warehouse-to-community-pharmacy last-mile distribution case for chronic-disease medicines. The RL-NS algorithm achieves an average computation time of 45.3 ms and a standard deviation of 2.7, outperforming the comparison algorithms. In the case study, it reduces transportation carbon emissions by approximately 18% and delivery time by approximately 12% relative to traditional routing. By reducing route redundancy and enabling rapid replanning, the method supports lower-emission and potentially more energy-efficient transport operations. The findings demonstrate its relevance to sustainable transportation, sustainable logistics, and resilient pharmaceutical cold-chain management.