Sharif Digital Repository

This study proposes a deep reinforcement learning approach to solve a perishable inventory allocation problem in a two-echelon supply chain. The inventory allocation problem is studied considering the stochastic nature of demand and supply. The examined supply chain includes two retailers and one distribution center (DC) under a vendor-managed inventory (VMI) system. This research aims to minimize the wastages and shortages occurring at the retailer's sites in the examined supply chain. With regard to continuous action space in the considered inventory allocation problem, the Advantage Actor-Critic algorithm is implemented to solve the problem. Numerical experiments are implemented on... 

This Thesis presents a robust network design model for supplying blood during and after an earthquake disaster. A two stage optimization model based on several real-world scenarios is developed. The purpose of this research is to locate and allocate fixed and mobile facilities in probabilistic situation, in which Tehran city with 22 districts is considered as a case study. This model can be categorized as a probabilistic model which demand and supply rate for blood and its derivatives is uncertain. Furthermore the blood transition between different blood types and conversion to its derivatives such as Platelet and plasma are involved in the proposed model. The supply chain for blood consists... 

Blood is a perishable product and can only be stored for a limited time. Reducing the level of wastage and shortage in supply chain of blood products is the main challenge of supply chain management. Wastage occurs whenever hospitals and blood banks order excessive blood while ordering insufficient amount results in shortage. Wastage can increase the costs in supply chain while shortage can cause important operation to be cancelled.This thesis presents an integer programming model for improving blood related operations in hospitals and blood banks. The presented model determines optimal order levels for each period which minimize total cost, shortage and wastage levels. The model is... 

Blood supply chains play a key role in the healthcare systems. Any improvement in the management of these chains have a direct impact on the whole healthcare system. In this research two model for centralized and decentralized blood supply chain networks have been developed by mixed integer linear programming. These models are multi-periodic and include both tactical and strategical decisions for the several periods. In this research the blood group compatibility has been considered in the models, also demand and supply of blood have been considered uncertain, and due to this reason in order to deal with the uncertainty of model the robust Possibilistic programming has been utilized to find... 

major challenges in field of blood supply chain has made it to an important field of study in these era. Due to specific holding environment and limited lifetime, inventory management and inventory planning of blood banks are interesting fields for research. On the other hand, various process in a blood bank make this field very complicated. In this thesis an integer programming model is presented to minimize wastage and shortages in a hospital blood bank (HBB). Elective demands are considered in a finite horizon. This model considers blood compatibility (in case of shortage of same blood group) and crossmathcing a single unit of blood package for more than one patient (demand). Inventory... 

Human blood is a valuable and scarce product which is only produced by human body. There is no replaceable material for our blood and there has always been a constant need to donors and blood products in societies. Like every other product, blood has to be transfused to patients after it is donated and this process requires a complete and effective blood supply chain. Considering all properties, complexities and uncertainties of a blood supply chain, we need to develop stable methodologies in order to simplify decision making in blood supply chain. In this research, we develop a novel blood distribution system from a regional blood center (RBC) to its nearby hospitals. It helps RBCs plan the... 

In this research, among the levels of the blood supply chain, hospital is chosen for study because of its importance. A model of inventory management of hospital blood bank is presented. In this case, we consider some assumptions which are more realistic. These assumptions include two types of emergency and ordinary demands, young blood demand, and finally, a cross-match process. In the existing articles, although blood groups considered in mathematical models, the priority of allocation of blood groups is not considered in these articles. In this study, three mathematical models are developed with deterministic parameters. In the first model, the assumption of ordinary and emergency demand,... 

Blood is a very valuable material for the life of human beings and should be transfused to the patient as soon as possible in case of necessity. It is s perishable product and different blood products have different shelf lives. Therefore, it is important to manage properly blood product inventories in hospitals to avoid shortage and outdate as much as possible. In this research, a bi-objective mixed-integer programming model is developed which aims to simultaneously minimize the total cost of the supply chain network and the total environmental impacts of the activities of the supply chain network. Since the nature of the problem is uncertain, a robust possibilistic programming approach is...