The Location Selection of Logistics Center in City Based on Particle Swarm Optimization

Huang, Yingyi; Wang, Xinyu; Li, Tianci; Chen, Hongyan

doi:10.21203/rs.3.rs-1964001/v1

Cited by 1 publication

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang X et al used genetic algorithms to optimize the location of the original logistics storage center [4]. Huang Y et al designed a siting model for logistics centers based on a particle swarm optimization algorithm [5]. The above heuristic algorithms have high time complexity.…”

Section: Introductionmentioning

confidence: 99%

Multi-level Logistics Network Node Siting Model Based on K-Means

Liu,

Tian,

Wang

et al. 2023

Atlantis Highlights in Intelligent Systems

View full text Add to dashboard Cite

Artificial intelligence plays a pivotal role in global logistics and supply chain management. AI enables real-time optimization for routes and minimizes wastage while increasing delivery efficiency. Companies can leverage AI in logistics to optimize resources and be more efficient. Currently, the node siting of logistics transportation networks faces two challenges. (1) The unreasonable selection of upstream and downstream nodes on the logistics transportation network can result in the wastage of transportation costs. (2) The siting of nodes in logistics transportation networks just takes the effect of geography into account and ignores other aspects that may have an impact on transportation efficiency. To tackle these challenges, we design a multi-level logistics network node siting model based on K-Means. Firstly, we adopt a space first and then attribute clustering strategy to cluster according to the spatial coordinates of each community to obtain the initial position of each distribution node, and optimize the siting based on the weight of express delivery in each community. Secondly, we determine the location of transit nodes and large distribution centers in turn according to the siting of distribution nodes. Taking Erdao District, Changchun City as an example, we finally build a logistics transportation network composed of 3 large distribution centers, 11 transit nodes and 42 distribution nodes using this model. This model can effectively solve the problem of node siting in multi-level logistics networks and provide a reference for future siting planning of logistics enterprises .

show abstract

Section: Introductionmentioning

confidence: 99%