Iot-Driven Dynamic Replenishment of Fresh Produce in the Presence of Seasonal Variations : A Deep Reinforcement Learning Approach
Internet of Things (IoT) has been transforming inventory management disruptively by linking and synchronizing inventory products together. It is one of the driving forces for the prevailing innovation of AgriTech. For fresh produce replenishment in the presence of its inherent seasonal variations, not only can IoT devices capture bidirectional seasonal information of lead time and demand, but also detect fresh produce lost and waste (FPLW) caused by deterioration. Considering the massive data collected by IoT, we employ a data-driven Deep Reinforcement Learning (DRL) approach to develop the dynamic replenishment policy for a fresh-produce wholesaler to address the challenge posed by seasonal variations. Compared to the standard DQN and the best traditional policy (e.g., the BSP-low-EW policy), our DRL-based approach demonstrates significant improvements in all aspects of inventory management, especially a remarkable reduction in FPLW. Furthermore, the proposed policy is demonstrated with plausible robustness and scalable applicability
Year of publication: |
[2023]
|
---|---|
Authors: | Wang, Zihao ; Wang, Wenlong ; Zhang, Hong ; Shi, Junmin (Jim) |
Publisher: |
[S.l.] : SSRN |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Stochastic Sequential Allocations for Creative Crowdsourcing
Tian, Xuhan, (2021)
-
Inventory Control involving Unknown Censored Demand and Convex Inventory Costs
Yang, Jian, (2021)
-
The Intra-Regional Spillover Effect of Bond Defaults : Evidence from China's Credit Bond Market
Wang, Wenlong, (2021)
- More ...