IMPLEMENTASI MODEL STOKASTIK PADA PERMASALAHAN OPTIMASI PERSEDIAAN KELAPA PADA TINGKAT DISTRIBUTOR

In the inventory system is given operational policies relating to product inventory control, such as how much is ordered, when to order with the aim of minimizing storage and ordering costs. Customer demand and lead time affect the inventory system. This study aims to determine the densitas distribution of demand data, total inventory costs and optimal coconut supply for the two order periods using the stochastic inventory model. Stochastic inventory models can be used if there is variable uncertainty. This paper discusses the optimization of coconut inventories using a stochastic model with uncertainty about demand and lead time. It is known that demand data is uniformly distributed, based on the realization value of random variable requests can be formed in 49 scenarios. Obtained an optimal total inventory cost for the two planning periods is Rp. 45,672,910, optimal supply for period one was 26031 coconuts. Inventory levels in two period for any scenarios are

Stochastic inventory models with reworks

In this paper, two stocks, for fresh and the returned things, are considered for the efficient stock management. Hence, we give two models: the first is for non-perishable and the second for perishable things. In addition, inventories kept in the stock may lose their fairly estimated worth, which we additionally viewed in model-II, for example, PC and versatile embellishments, or most current engine autos. In model-II, the stock decay (a loss of significant worth) in a steady rate ? is chosen arbitrarily. Though the models are more fitting where guarantees are accommodated to a settled time length after the deal for new things was made, they can be used to separate characteristics of a stock system for a broad scale production firm. It is expected that the stock level for both new and the returned things are pre-decided. When the stock level scopes at the re-order point s, a request for renewal is put with parameter for new things. The requests for both new and the returned things take after the Poisson process with parameter ? & ?, respectively. Service will be given according to Poisson process for returned things with parameter ?. The joint probability distribution for both returned and new things are derived in the steady state examination. A few system characteristics of two models are inferred here and the outcomes are outlined, based on some numerical cases.