Clustering-based improved genetic algorithm for solving rural logistics route planning problem with conventional and new energy vehicles

In the context of global climate change and environmental sustainability, reducing carbon emissions has become a primary focus for both businesses and governments. The current challenges in rural logistics largely stem from low adoption of new energy technologies and widespread idling of vehicles, resulting in high carbon emissions in rural logistics operations. Against this backdrop, this study addresses the issues by considering the application of new energy sources, distribution strategies, vehicle carbon emission calculations, and other low-carbon optimization methods. The objective is to establish a model that optimizes node construction costs, operational costs, transportation costs, and carbon emission costs. This research aims to tackle the problem of village-level distribution center location and routing optimization, taking into account carbon emission costs as a decisive factor to reduce environmental impact. To achieve this goal, this paper proposes a comprehensive approach that combines the K-means++ algorithm with an enhanced genetic algorithm. In this approach, the K-means++ algorithm is first employed to select optimal locations for village-level distribution centers, minimizing construction, operational, and carbon emission costs. Subsequently, the enhanced genetic algorithm is utilized to determine the optimal distribution routes, incorporating a hybrid fleet of new energy and conventional vehicles, aiming to minimize overall costs, including carbon emissions and transportation costs. Application of our algorithm in a real rural distribution network demonstrates that, compared to traditional methods, it achieves higher efficiency while reducing carbon emission costs. Additionally, our study provides valuable insights for policymakers and decision-makers regarding carbon emission reduction and sustainable development, offering robust decision support for the planning and management of village-level distribution centers.