Application of Swarm Intelligence Optimization Algorithm in Logistics Delivery Path Optimization under the Background of Big Data

Traditional logistics delivery route optimization algorithm has some problems such as long time to find the optimal route. Based on this, this paper discusses swarm intelligence optimization algorithm and logistics delivery route optimization. To solve the logistics vehicle routing problem, consider...

Full description

Saved in:
Bibliographic Details
Published in:Journal of function spaces Vol. 2023; pp. 1 - 12
Main Author: Zhao, Guofu
Format: Journal Article
Language:English
Published: New York Hindawi 24.02.2023
John Wiley & Sons, Inc
Wiley
Subjects:
Algorithms
Ant colony optimization
Artificial intelligence
Basic converters
Big Data
Cold storage
Construction costs
Crowding
Customer satisfaction
Distribution costs
Heuristic methods
Intelligence
Logistics
Mathematical optimization
Optimization algorithms
Planning
Route optimization
Route planning
Supply chain management
Swarm intelligence
Traveling salesman problem
Vehicle routing
Vehicles
Windows (intervals)
Iran
ISSN:2314-8896, 2314-8888
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditional logistics delivery route optimization algorithm has some problems such as long time to find the optimal route. Based on this, this paper discusses swarm intelligence optimization algorithm and logistics delivery route optimization. To solve the logistics vehicle routing problem, considering that the basic ACO (ant colony optimization) has the disadvantages of slow convergence speed and easy to fall into local optimum, this paper proposes a new hybrid population optimization algorithm and applies it to VRPTW (vehicle routing problem with time windows). In addition, the concept of crowding degree in AFSA (artificial fish swarm algorithm) is introduced into ACO. In the early stage of the optimization process, a strong crowding degree limit is set to ensure that most ants are not affected by pheromone concentration to conduct random optimization. The simulation results show that the AC (accuracy rate) of this algorithm is 95.08%, which is higher than the traditional PSO (particle swarm optimization) algorithm and general heuristic algorithm. The hybrid algorithm can effectively improve the optimization efficiency of VRPTW, lay a foundation for solving large-scale VRPTW, and provide new research ideas and methods. At the same time, the results fully show that the algorithm in this paper has certain advantages in performance, and it can be applied to logistics delivery route optimization.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2314-8896
2314-8888
DOI:10.1155/2023/3476711