A Deep Reinforcement Learning Approach for Optimal Replenishment Policy in A Vendor Managed Inventory Setting for Semiconductors Muhammad Tariq Afridi, Santiago Nieto-Isaza, Hans Ehm, Thomas Ponsignon, Abdelgafar Hamed Proceedings Winter Simulation Conference, 2020 Vendor Managed Inventory (VMI) is a mainstream supply chain collaboration model. Measurement approaches defining minimum and maximum inventory levels for avoiding product shortages and over-stocking are rampant. No approach undertakes the responsibility aspect concerning inventory level status, especially in semiconductor industry which is confronted with short product life cycles, long process times, and volatile demand patterns. In this work, a root-cause enabling VMI performance measurement approach to assign responsibilities for poor performance is undertaken. Additionally, a solution methodology based on reinforcement learning is proposed for determining optimal replenishment policy in a VMI setting. Using a simulation model, different demand scenarios are generated based on real data from Infineon Technologies AG and compared on the basis of key performance indicators. Results obtained by the proposed method show improved performance than the current replenishment decisions of the company.
Comparative analysis between ANP and ANP-DEMATEL for six sigma project selection process in a healthcare provider Lecture Notes in Computer Science, 2014
Coupling ant colony optimization and discrete-event simulation to solve a stochastic location-routing problem Nilson Herazo-Padilla, Jairo R. Montoya-Torres, Andres Munoz-Villamizar, Santiago Nieto Isaza, Luis Ramirez Polo Proceedings of the 2013 Winter Simulation Conference Simulation Making Decisions in A Complex World Wsc 2013, 2013 This paper considers the stochastic version of the location-routing problem (SLRP) in which transportation cost and vehicle travel speeds are both stochastic. A hybrid solution procedure based on Ant Colony Optimization (ACO) and Discrete-Event Simulation (DES) is proposed. After using a sequential heuristic algorithm to solve the location subproblem, ACO is employed to solve the corresponding vehicle routing problem. DES is finally used to evaluate such vehicle routes in terms of their impact on the expected total costs of location and transport to customers. The approach is tested using random-generated data sets. because there are no previous works in literature that considers the same stochastic location-routing problem, the procedure is compared against the deterministic version of the problem. Results show that the proposed approach is very efficient and effective.
