Title: Continuous GA-based Optimization of Order-Up-To Inventory Policy in Logistic Networks for Achieving High Service Rate

Year of Publication: Sep - 2017
Page Numbers: 70-75
Authors: Przemyslaw Ignaciuk, Lukasz Wieczorek
Conference Name: The Fourth International Conference on Artificial Intelligence and Pattern Recognition (AIPR2017)
- Poland


The paper addresses the problem of efficient goods distribution in logistic networks having a mesh structure. The transfer of goods takes place among the interconnected nodes with non-negligible delay. The stock gathered at the nodes is replenished from external sources as well as from other nodes in the controlled network. External demand is imposed on any node without prior knowledge about the requested quantity. The inventory control is realized through the application of order-upto policy implemented in a distributed way. The aim is to provide high customer satisfaction while minimizing the total holding costs. In order to determine the optimal reference stock level for the policy operation at the controlled nodes a continuous genetic algorithm (GA) is applied and adjusted for the analyzed class of application centered problems.