Optimal control of a production-inventory system with productreturns

Vercraene, Samuel; Gayon, Jean-Philippe

doi:10.1016/j.ijpe.2012.11.012

Cited by 18 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several researchers model the MEIO problem as an MDP, as multiple convenient methods for solving MDPs exist. However, these authors typically focus on relatively simple structures of the supply chain, for example, the linear supply chain Lambrecht, Luyten and Vander Eecken 1985;Chen and Song 2001; Multi-echelon inventory optimization using DRL Vercraene and Gayon 2013;Iida 2001) and the divergent supply chain (Chen et al 2002;Minner et al 2003). Yet, determining optimal policies is intractable, even for simple network structures, due to the well-known curses of dimensionality (De Kok et al 2018;Bellman 1957).…”

Section: Multi-echelon Inventory Managementmentioning

confidence: 99%

Multi-echelon inventory optimization using deep reinforcement learning

Geevers

Hezewijk

Mes

2023

Cent Eur J Oper Res

View full text Add to dashboard Cite

This paper studies the applicability of a deep reinforcement learning approach to three different multi-echelon inventory systems, with the objective of minimizing the holding and backorder costs. First, we conduct an extensive literature review to map the current applications of reinforcement learning in multi-echelon inventory systems. Next, we apply our deep reinforcement learning method to three cases with different network structures (linear, divergent, and general structures). The linear and divergent cases are derived from literature, whereas the general case is based on a real-life manufacturer. We apply the proximal policy optimization (PPO) algorithm, with a continuous action space, and show that it consistently outperforms the benchmark solution. It achieves an average improvement of 16.4% for the linear case, 11.3% for the divergent case, and 6.6% for the general case. We explain the limitations of our approach and propose avenues for future research.

show abstract

Section: Multi-echelon Inventory Managementmentioning

confidence: 99%

Multi-echelon inventory optimization using deep reinforcement learning

Geevers

Hezewijk

Mes

2023

Cent Eur J Oper Res

View full text Add to dashboard Cite

show abstract

“…Opracowany przez nich model ma na celu znalezienie optymalnej wielkości zapasów produktów w magazynach lokalnych przy możliwie najmniejszych kosztach operacyjnych rozumianych jako koszty związane z realizacją popytu oraz koszty magazynowania w lokalnych i centralnym magazynie. Vercraene i Gayon analizują łańcuch dostaw, w którym zwroty mogą zasilać bądź to proces produkcyjny (jeżeli są to zwroty wymagające ponownego przetworzenia), bądź proces dystrybucyjny (jeżeli zwroty dotyczą produktów gotowych niewymagających przetworzenia przed ponownym wprowadzeniem na rynek) [Vercraene, Gayon 2013]. Podobnie jak w poprzednich modelach, kryterium dla określenia optymalnej wielkości zapasu podstawowego jest minimalizacja kosztów zdyskontowanych (średnich) dotyczących utrzymywania zapasów i braku towaru.…”

Section: Kosztowa Funkcja Celu Dla Optymalizacji Przepływów Zwrotnych...unclassified

Kryteria optymalizacji przepływów zwrotnych w zielonych łańcuchach dostaw

Mesjasz-Lech¹

2015

Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu

View full text Add to dashboard Cite

“…They also applied the cost optimization parameter to determine the control policy parameters. N-echelon inventory system has been considered in reference [7] for a remanufacturing system. They investigated the performances of three heuristic approaches for the case n = 2 based on a queuing framework to model production capacity.…”

Section: Inventory Systemsmentioning

confidence: 99%

A Review of Inventory Management for Remanufacturing Environment

Pourghadim

Noordin

Wong

2013

AMR

View full text Add to dashboard Cite

This paper outlines work carried out in the field of inventory management on remanufacturing. So far numerous authors have proposed quantitative models taking inventory management in remanufacturing into consideration. However, no general framework has been specified yet. Thus, it appears timely for a composed outline of the issues showing up in the context of remanufacturing inventory control. In this review, the area is subdivided into three main fields, in particular inventory policies, deterministic & stochastic models and lead time effects. For each of the aforementioned fields, the models proposed in the literature are reviewed and the areas in necessity of further research are indicated.

show abstract

Optimal control of a production-inventory system with productreturns

Cited by 18 publications

References 30 publications

Multi-echelon inventory optimization using deep reinforcement learning

Multi-echelon inventory optimization using deep reinforcement learning

Kryteria optymalizacji przepływów zwrotnych w zielonych łańcuchach dostaw

A Review of Inventory Management for Remanufacturing Environment

Contact Info

Product

Resources

About