Research on IRP of Perishable Products Based on Mobile Data Sharing Environment

Zelin Wang, Xiaoning Wei, Jiansheng Pan

Source Title: International Journal of Cognitive Informatics and Natural Intelligence (IJCINI)15(2)

ISSN: 1557-3958|EISSN: 1557-3966|EISBN13: 9781799859833|DOI: 10.4018/IJCINI.20210401.oa10

MLA

Wang, Zelin, et al. "Research on IRP of Perishable Products Based on Mobile Data Sharing Environment." IJCINI vol.15, no.2 2021: pp.139-157. http://doi.org/10.4018/IJCINI.20210401.oa10

APA

Wang, Z., Wei, X., & Pan, J. (2021). Research on IRP of Perishable Products Based on Mobile Data Sharing Environment. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 15(2), 139-157. http://doi.org/10.4018/IJCINI.20210401.oa10

Chicago

Wang, Zelin, Xiaoning Wei, and Jiansheng Pan. "Research on IRP of Perishable Products Based on Mobile Data Sharing Environment," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 15, no.2: 139-157. http://doi.org/10.4018/IJCINI.20210401.oa10

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Inventory routing problem (IRP) has always been a hot issue. Due to its particularity, perishable products have high requirements for inventory and transportation. In order to reduce the losses of perishable goods and improve the storage efficiency of perishable goods, based on the general inventory path problem, this paper further has studied the IRP of perishable goods. In addition, in the process of product distribution and transportation, there are a lot of real-time product information generated dynamically. These real-time mobile data must be shared by the whole distribution network, which will also dynamically affect the efficiency of IRP research. On the basis of some assumptions, the mathematical model has been established with inventory and vehicle as constraints and the total cost of the system as the objective. In view of the particularity of perishable inventory path problem, this paper proposed an improved differential evolution algorithm (IDE) to improve the differential evolution algorithm from two aspects. Firstly, the population has been initialized by gridding and the greedy local optimization algorithm has been used to assist the differential evolution algorithm, with these measures to improve the convergence speed of the algorithm. Then, the accuracy of the algorithm is improved by the adaptive scaling factor, two evolution modes and changing the constraints of the problem. Then the improved algorithm has been used to solve the inventory path problem. The results of numerical experiments show that the algorithm is effective and feasible and can improve the accuracy and speed up the convergence of the algorithm.