• 한국경영과학회지
• /
• 제10권1호
• /
• pp.65-78
• /
• 1985

In this paper, the approach getting a total demand by forecasting the new demand and the replacement demand separately and adding them is used for long term forecasting of durable goods. Cross country analysis using the income as an independent variable and S-shaped growth curve as a fitting model is developed as a method of forecasting new demand. To get the replacement demand the methods using the number of ownership and the replacement rate and the methods using the past demand and the distribution of the product life are proposed. And the theoretical explannation for product life cycle's diversity, which is the one of the major considerations in the long term forecasting, is attempted by the combination of the new demand and the replacement demand patterns. This is applicated the long term forecasting of Korean passenger cars.

• Journal of Electrical Engineering and Technology
• /
• 제12권5호
• /
• pp.1719-1728
• /
• 2017

Recent concerns about environmental conditions have triggered the growing interest in using green energy resources. These sources of energy, however, bring new challenges mainly due to their uncertainty and intermittency. In order to alleviate the concerns on the penetration of intermittent energy resources, this paper investigates impacts of realizing demand-side potentials. Among different demand-side management programs, this paper considers demand response wherein consumers change their consumption pattern in response to changing prices. The research studies demand response potentials from different load sectors on generation system well-being. Consumers' sensitivity to time-varying prices is captured via self and cross elasticity coefficients. In the calculation of well-being indices, sequential Monte Carlo simulation approach is accompanied with fuzzy logic. Finally, IEEE-RTS is used as the test bed to conduct several simulations and the associated results are thoroughly discussed.

• Journal of Information Technology Applications and Management
• /
• 제30권3호
• /
• pp.1-13
• /
• 2023

Demand forecasting is a crucial task for an online retail where has to manage daily fresh foods effectively. Failing in forecasting results loss of profitability because of incompetent inventory management. This study investigated the optimal performance of different forecasting models for a very short shelf-life product. Demand data of 13 perishable items with aging of 210 days were used for analysis. Our comparison results of four methods: Trivial Identity, Seasonal Naïve, Feed-Forward and Autoregressive Recurrent Neural Networks (DeepAR) reveals that DeepAR outperforms with the lowest MAPE. This study also suggests the managerial implications by employing coefficient of variation (CV) as demand variation indicators. Three classes: Low, Medium and High variation are introduced for classify 13 products into groups. Our analysis found that DeepAR is suitable for medium and high variations, while the low group can use any methods. With this approach, the case can gain benefit of better fill-rate performance.

• 대한산업공학회지
• /
• 제35권3호
• /
• pp.203-212
• /
• 2009

The bullwhip effect refers to the phenomenon where demand variability is amplified when one moves upward a supply chain. In this paper, we exactly quantify the bullwhip effect for cases of seasonal demand processes in a two-echelon supply chain with a single retailer and a single supplier. In most of the previous research, some measures of performance for the bullwhip effect are developed for cases of non-seasonal demand processes. The retailer performs demand forecast with a multiplicative seasonal mixed model by using the minimum mean square error forecasting technique and employs a base stock policy. With the developed bullwhip effect measure, we investigate the impact of seasonal factor on the bullwhip effect. Then, we prove that seasonal factor plays an important role on the occurrence of the bullwhip effect.

• Management Science and Financial Engineering
• /
• 제10권2호
• /
• pp.29-51
• /
• 2004

In this paper, the cost impact of incorrect assumptions about the demand process in a supply chain in which there are two participants, a retailer and a manufacturer, is considered. When participants in the supply chain do not notice serial correlation in the demand process, they would turn to a simple inventory model based on an i.i.d. demand assumption. A mathematical model that allows us to quantify the cost incurred by each participant in the supply chain, when they implement inventory policies based on correct or incorrect assumptions about the demand process, is developed. This model enables us to identify how much it differs from the optimal costs.

• 대한안전경영과학회지
• /
• 제2권3호
• /
• pp.81-88
• /
• 2000

In this research, the system is assumed to carry a single item of which the demand types vary. Demand type is defined as a management's classification of the item according to the demand source or to the service purpose. The purpose of this research is to find the optimal inventory control policy when the system carries a single item which consists of multiple demand types. In this research, the optimizing algorithm contains a heuristic, therefore, the optimal is not guaranteed by the algorithm. At least, this research provides the solution to the problems that have not been solved by the existing algorithms.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2000년도 추계학술발표논문집
• /
• pp.127-130
• /
• 2000

In this research, the system is assumed to carry a single item of which the demand types vary. Demand type is defined as a management's classification of the item according to the demand source or to the service purpose. The purpose of this research is to find the optimal inventory control policy when the system carries a single item which consists of multiple demand types. In this research, the optimizing algorithm contains a heuristic, therefore, the optimal Is not guaranteed by the algorithm. At least, this research provides the solution to the problems that have not been solved by the existing algorithms.

• 대한안전경영과학회지
• /
• 제16권4호
• /
• pp.323-330
• /
• 2014

Various inventory control theories have tried to modelling and analyzing supply chains by using quantitative methods and characterization of optimal control policies. However, despite of various efforts in this research filed, the existing models cannot afford to be applied to the realistic problems. The most unrealistic assumption for these models is customer demand. Most of previous researches assume that the customer demand is stationary with a known distribution, whereas, in reality, the customer demand is not known a priori and changes over time. In this paper, we propose a reinforcement learning based adaptive echelon base-stock inventory control policy for a multi-stage, serial supply chain with non-stationary customer demand under the service level constraint. Using various simulation experiments, we prove that the proposed inventory control policy can meet the target service level quite well under various experimental environments.

• 대한안전경영과학회지
• /
• 제8권3호
• /
• pp.115-123
• /
• 2006

The main focus of this study is to investigate the performance of a clark-scarf type multi-echelon serial supply chain operating with a base-stock policy and to optimize the inventory levels in the supply chains so as to minimize the systemwide total inventory cost, comprising holding and backorder costs as all the nodes in the supply chain. The source of supply of raw materials to the most upstream node, namely supplier, is assumed to have an infinite raw material availability. Retailer faces random customer demand, which is assumed to be stationary and normally distributed. If the demand exceeds on-hand inventory, the excess demand is backlogged. Using the echelon stock and demand quantile concepts and an efficient simulation technique, we derive near optimal inventory policy. Additionally we discuss the derived results through the extensive experiments for different supply chain settings.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1994년도 춘계공동학술대회논문집; 창원대학교; 08월 09일 Apr. 1994
• /
• pp.427-431
• /
• 1994

The objective of this paper is to provide an inventory control policy for the system that carries a single item with a multiple demand classes, when the demand is Poisson distributed random variable. The inventory control process includes the process of determining the reorder point, and the process of inventory control during the lead time. The goal of the optimization process is to achieve the service level of each demand class as well as the system-wide total service level at a preset desired service level while sustaining a minimum average inventory.