Analysis of Admission and Inventory Control Policies for Production Networks

2008 ◽  
Vol 5 (2) ◽  
pp. 275-288 ◽  
Author(s):  
S. Ioannidis ◽  
V.S. Kouikoglou ◽  
Y.A. Phillis
Author(s):  
M.-A. Dittrich ◽  
S. Fohlmeister

AbstractDue to growing globalized markets and the resulting globalization of production networks across different companies, inventory and order optimization is becoming increasingly important in the context of process chains. Thus, an adaptive and continuously self-optimizing inventory control on a global level is necessary to overcome the resulting challenges. Advances in sensor and communication technology allow companies to realize a global data exchange to achieve a holistic inventory control. Based on deep q-learning, a method for a self-optimizing inventory control is developed. Here, the decision process is based on an artificial neural network. Its input is modeled as a state vector that describes the current stocks and orders within the process chain. The output represents a control vector that controls orders for each individual station. Furthermore, a reward function, which is based on the resulting storage and late order costs, is implemented for simulations-based decision optimization. One of the main challenges of implementing deep q-learning is the hyperparameter optimization for the training process, which is investigated in this paper. The results show a significant sensitivity for the leaning rate α and the exploration rate ε. Based on optimized hyperparameters, the potential of the developed methodology could be shown by significantly reducing the total costs compared to the initial state and by achieving stable control behavior for a process chain containing up to 10 stations.


1997 ◽  
Vol 45 (3) ◽  
pp. 327-340 ◽  
Author(s):  
Wallace J. Hopp ◽  
Mark L. Spearman ◽  
Rachel Q. Zhang

2020 ◽  
Vol 9 (1) ◽  
pp. 211
Author(s):  
Abdessamad Douraid ◽  
Hamid Ech-Cheikh ◽  
Khalid El Had ◽  
Mohamed Laradi

Inventory management is a challenging problem area in supply chain management and companies need to have inventories in warehouses in order to satisfy customer's needs. Meanwhile, these inventories have holding costs and this is a frozen fund that can be lost. Therefore, the task of inventory management is to find the right quantity of inventories that will fulfill the demand with the right price, avoiding overstocks. The aim of this paper is to carry out a comparing study of continuous inventory control policies in a stochastic environment of demand and lead time, in order to find out the impacts of the decision variables of each inventory control policy. For this purpose, the discrete event simulation approach has been chosen to generate various scenarios of inventory control policies of the procurement process by taking into account the production planning of the manufacturing company. The comparison of these configurations based on the essential key performance indicators of the supply chain, namely the cost and service level.  


Sign in / Sign up

Export Citation Format

Share Document