2825. Adaptive Policies for the Stochastic Dynamic Multi-Period Inventory-Routing Problem
Invited abstract in session TB-58: Inventory Routing, stream Vehicle Routing and Logistics.
Tuesday, 10:30-12:00Room: Liberty 1.13
Authors (first author is the speaker)
| 1. | Francisco Maia
|
| Industrial Engineering and Management, FEUP, INESC TEC | |
| 2. | Gonçalo Figueira
|
| INESC-TEC, Faculty of Engineering of Porto University | |
| 3. | Fábio Moreira
|
| INESC TEC, INEGI, Faculty of Engineering, University of Porto |
Abstract
The Stochastic Dynamic Inventory-Routing Problem (SDIRP) is a fundamental problem within supply chain operations that combines inventory management and vehicle routing while addressing the dynamic and stochastic nature of customer demands.
This research aims to provide new insights into resolving an SDIRP, focusing on a central warehouse that periodically distributes homogeneous goods to geographically dispersed customers.
Decision-making involves a three-step policy: calculating a delivery priority for each customer, determining delivery quantities based on an (s, S) inventory rule, and computing a vehicle route with an exact method.
A simulator was developed to replicate the problem's dynamics and enable policy training and evaluation across various scenarios.
The priority rule is computed as a combination of key features extracted from the problem instances.
The way those features are combined into the policy is determined by two evolutionary methods: Genetic Programming and Genetic Algorithms.
Our policies were evaluated on instances with up to 50 customers and 20 periods, considering multiple demand uncertainties, holding and shortage costs, and vehicle capacities. The results highlight a competitive performance in total cost reduction compared to several myopic and direct lookahead benchmarks, enhancing stock balance and minimizing travel distances.
Keywords
- Vehicle Routing
- Inventory
- Machine Learning
Status: accepted
Back to the list of papers