We have used Reinforcement Learning together with Monte Carlo simnlation to solve a multi-period production planning problem in a westage hybrid manufacturing process (a combination of build-to-plan with build-to-order) with a capacity constraint. Our model minimizes inventory and penalty costs while considering real-world complexities such as different component types sharing the same manufact...

In this paper we have developed a two echelon supply chain production inventory model for deteriorating products having stock dependent demand under inflationary environment. This model is developed for finite time horizon. The shortages are allowed and partially backlogged. To make this study close to reality the production rate is assumed to be a function of demand rate. A numerical example a...

This paper examines the extended two-echelon newsboy problem for a manufacturer and retailer in a supply chain with asymmetric market information. In this scenario, the retailer has better knowledge of the market s demand, and the manufacturer perceives the same demand. This applied model presents how the manufacturer can take advantage of the retailer s market information and improve the effic...

A new two-layered optimisation-based control approach is developed for multi-product, multi-echelon supply chain networks. The first layer employs simple feedback controllers to maintain inventory levels at all network nodes within pre-specified targets. The feedback controllers are embedded as equality constraints within an optimisation framework that incorporates model predictive control prin...

In this paper, we examine the issue of order coordination between a supplier and multiple retailers in a decentralized multi-echelon inventory/distribution system where the supplier provides a product to multiple retailers who experience static demand and standard inventory costs. Specifically, we propose and analyze a new policy where a manufacturer, who outsources production to an OEM, offers...

Managing inventory in distribution systems involves taking decisions on the quantity of inventory to be placed at different stages so that a desired customer service level can be achieved at minimum cost. In this paper, we present the case of the distribution system of an Indian FMCG company, which despite having centralized control takes replenishment decisions based on local stock information...

Clark and Scarf [1960] characterize optimal policies in a two-echelon, twolocation inventory model. We extend their result to the infinite-horizon case (for both discounted and average costs). The computations required are far easier than for the finite horizon problem. Further simplification is achieved for normal demands. We also consider the more interesting case of multiple locations at the...

Model Predictive Control (MPC) is shown to provide a robust, flexible framework to stabilize inventories yet still meet customer demand with minimal safety stock. The translation of available information in the supply chain problem into MPC variables is demonstrated with a two-node supply chain example. A six-node, two-product, threeechelon demand network simulation proposed by Intel Corp. is w...

s-This paper further extends the existing cost model for a fixed-life perishable product in a two-echelon inventory problem into the net profit model. The extended model is subsequently evaluated by comparing its results with those obtained from OptQuest, a commercial simulationoptimization package. Within a limited but reasonable time, the comparative results do not show a significant improvem...