• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2310-2312
• /
• 2004

In Korea Electric Power Corporation (or KEPCO), several Demand-Side Management (or DSM) program have been carried out to effectively meet electric power demand at least costs by modifying customers electricity use patterns. As one of them, KEPCO applies low-priced night thermal-storage power service for heat appliances to facilitate efficient use of power facilities by shifting relatively high daytime demands to night hours to build loads during the off-peak periods. In the market of heat-storage type water-heater, electric water-heater has been mostly used, but it has low energy efficiency and needs high capacity electric equipments. So in order to replace these electric water heaters, 15 HP air-source heat pump water heater is developed in Korea Electric Research Institute (or KEPRI). This paper shows that measurement system for performance testing of heat pump water heater is established and heating capacity and performance is analyzed and measured for out-door environmental change.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2961-2967
• /
• 2014

Nowadays, a private protection act has come into effect which demands for the protection of personal image information obtained by the CCTV. According to this act, the object out of interest has to be mosaicked such that it can not be identified before the image is sent to the investigation office. Meanwhile, the demand for digital videos obtained by CCTV is also increasing for digital forensic. Therefore, due to the two conflicting demands, the demand for a solution which can automatically mask an object in the CCTV video is increasing and related IT industry is expected to grow. The core technology in developing a target masking solution is the object tracking technique. In this paper, we propose an object tracking technique which suits for the application of CCTV video object masking as a postprocess. The proposed method simultaneously uses the motion and the color information to produce a stable tracking result. Furthermore, the proposed method is based on the centroid shifting method, which is a fast color based tracking method, and thus the overall tracking becomes fast.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.12
• /
• pp.2165-2172
• /
• 2010

This paper presents the operation algorithm of microgrid on the Real Time Pricing(RTP) for building the smart grid. RTP is higher power price variability than flat rate and time of use. However it has an effect on peak clipping and peak load shifting due to the increased price on peak time power demand. When the RTP are applied to the microgrid system, the proposed algorithm is able to be effective and economic operation. The implemented system is operated for the economic operation in microgrid connected with the power system. On the other hand, when the microgrid is operated on isolation mode, it focus on the improvement of stability and the power supply reliability of the sensitive loads. The test system are implemented and calculated on various operation modes based on non-dispachable generator output and RTP data for validating the proposed operation algorithm. The calculated results are compared to the implemented results using real-time simulator. It can be confirmed that the proposed operation system are identical results to the calculated one. When the proposed operation algorithm is applied to the system, it can be show the effectiveness of the peak clipping and peak load shifting and the improvement of economic feasibility.

• Journal of applied mathematics & informatics
• /
• v.19 no.1_2
• /
• pp.397-414
• /
• 2005

In the existing literature, most of the purchasing models were developed only for retailers problem ignoring the constraint of storage capacity of retailers shop/showroom. In this paper, we have developed a deterministic model of wholesaler-retailers' problem of single product. The storage capacity of wholesaler's warehouse/showroom and retailers' showroom/shop are assumed to be finite. The items are transported from wholesaler's warehouse to retailers' Own Warehouse (OW) in a lot. The customer's demand is assumed to be displayed inventory level dependent. Demands are met from OW and that spaces of OW will immediately be filled by shifting the same amount from the Rented Warehouse (RW) till the RW is empty. The time duration between selling from OW and filling up its space by new ones from RW is negligible. According to relative size of the retailers' existing (own) warehouse capacity and the demand factors, different scenarios are identified. Our objectives are to optimize the cost functions of wholesaler and two retailers separately. To solve this problem, a real coded Genetic Algorithm (GA) with roulette wheel selection/reproduction, whole arithmetic crossover and non-uniform mutation is developed. Finally a numerical example is presented to illustrate the results for different scenarios. To compare the results of GA, Generalised Reduced Gradient Method has been used for the problem. Also, a sensitivity analysis has been performed to study the variations of the optimal average cost with respect to the different parameters.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.2
• /
• pp.94-100
• /
• 2016

A virtual power plant (VPP) technology is a cluster of distributed generation installations. VPP system is that integrates several types of distributed generation sources, so as to give a reliable overall power supply. Virtual power plant systems play a key role in the smart grids concept and the move towards alternative sources of energy. They ensure improved integration of the renewable energy generation into the grids and the electricity market. VPPs not only deal with the supply side, but also help manage demand and ensure reliability of grid functions through demand response (DR) and other load shifting approaches in real time. In this paper, utilizing a variety of distributed generation resources(such as emergency generator, commercial generator, energy storage device), activation scheme of the virtual power plant technology. In addition, through the analysis of the domestic electricity market, it describes a scheme that can be a virtual power plant to participate in electricity market. It attempts to derive the policy support recommendation in order to obtain the basics to the prepared in position of power generation companies for the commercialization of virtual power plant.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.5
• /
• pp.351-360
• /
• 2016

Rapid population growth with high living standards and high electronics use for personal comfort has raised the electricity demand exponentially. To fulfill this elevated demand, conventional energy sources are shifting towards low production cost and long term usable alternative energy sources. Hybrid renewable energy systems (HRES) are becoming popular as stand-alone power systems for providing electricity in remote areas due to advancement in renewable energy technologies and subsequent rise in prices of petroleum products. Wind and solar power are considered feasible replacement to fossil fuels as the prediction of the fuel shortage in the near future, forced all operators involved in energy production to explore this new and clean source of power. Presented paper proposes fuzzy logic based Energy Management System (EMS) for Wind Turbine (WT), Photo Voltaic (PV) and Diesel Generator (DG) hybrid micro-grid configuration. Battery backup system is introduced for worst environmental conditions or high load demands. Dump load along with dump load controller is implemented for over voltage and over speed protection. Fuzzy logic based supervisory control system performs the power flow control between different scenarios such as battery charging, battery backup, dump load activation and DG backup in most intellectual way.

• Korean Institute of Interior Design Journal
• /
• no.32
• /
• pp.131-137
• /
• 2002

The development of fast information network connections and the information highway of todays society have made consumers to demand various services in interior design. The media influencing consumer behavior is with no doubt, the Internet. The exponential growth in Internet users in Korea is surprised to all other countries. At this time where new businesses and events on the Internet are developing successfully, the educational and cultural benefits to consumers, which is quite different from the time when consumers only depended on television and newspaper, are enabling consumer demand to grow together with the abundant floods of information. This implies that consumer choice is shifting from needs-based to wants-based products and services. In the past where only the necessities were mass-produced and there was a lack in goods in general, there just werent enough products or varieties for consumers to either compare or evaluate. Today, comparing and evaluating has become natural with the access to information, and consumers have teamed to choose interior products that fit their preferences. In other words, this means that consumers are now at a transition point where they are moving from the simple everyday needs of the past to wants of the present that allows them to form a standard for selecting products of their own preference.

• Proceedings of the KSR Conference
• /
• 2005.05a
• /
• pp.985-990
• /
• 2005

The success of road transportation, in dominating the surface movement of freight, is now threatened by increased traffic congestion, falling average motorway speed and rising in logistics costs, oil price. Due to the necessity for an effective transport system, we need to improve domestic transport infrastructure to reduce logistics cost by shifting to rail system. To analysis the demand characteristics in advance against these hypothetical circumstances, Stated Preference, which is called SP, approaches have been adopted to analysis the shipper's mode choice behaviors as RP(Revealed Preference) approaches are not appropriate. The results also indicate that the most effective policy to divert the freight volume from road to railway is to reduce freight rates for the railway with improved reliability.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.974-979
• /
• 2007

From '1994 Gwacheon accident of the Electric Multiple Unit(EMU)' till '2004 Seoul subway 2 lines Guui station accident', the accident is increasing at day and the service demand of the citizen is coming to be various. But it does not deal with technical or operation side demands. There is a possibility of saying that the accident of the EMU or deficit operation is caused by the RCM. The EMU where the efficiency is good though does the time passes and it becomes old anger and does not display that efficiency not only the cause of formation accident does becomes. The breakdown about under occurring before getting up an accident, appropriately shifting the parts is to a maintenance very the pending question fact which is important is a possibility of doing. From there is by an EMU, RCM in reliability base grudge is a tool of confirms an improvement point and the place where it judges. From the research which it sees will present about technical development plan of RCM.