Logistics Path Planning Method using NSGA-II Algorithm and BP Neural Network in the Era of Logistics 4.0

The distribution of fresh food is affected by its perishable characteristics, and compared with ordinary logistics distribution, the distribution path needs to be very reasonably planned. However, the complexity of the actual road network and the time variation of traffic conditions are not considered in the existing food logistics planning methods. In order to solve this problem, this study takes road section travel prediction as the starting point, and uses the non-dominant ranking genetic algorithm II and the backpropagation network to construct a new logistics path planning model. Firstly, the road condition information detected by the retainer detection and the floating vehicle technology is integrated, and the travel time prediction is input into the backpropagation network model. In order to make the prediction model perform better, it is improved using a whale optimization algorithm. Then, according to the prediction results, the non-dominant ranking genetic algorithm II is used for distribution route planning. Through experimental analysis, the average distribution cost of method designed by this study was 9476 yuan, and the average carbon emission was 2871kg. Compared with the other three algorithms, the distribution cost was more than 15% lower, and the carbon emission was more than 12.5% lower. The planning method designed by the institute can achieve more reasonable, low-cost, and environmentally friendly logistics and distribution, and bring more satisfactory services to the lives of urban residents.

@article{Li2024,
  title     = {Logistics Path Planning Method using NSGA-II Algorithm and BP Neural Network in the Era of Logistics 4.0},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {15},
  number    = {5},
  year      = {2024},
  publisher = {The Science and Information Organization},
  author    = {Liuqing Li},
  doi       = {10.14569/IJACSA.2024.0150518},
  url       = {https://doi.org/10.14569/IJACSA.2024.0150518}
}