• Journal of the Korea Society of Computer and Information
• /
• v.23 no.5
• /
• pp.9-14
• /
• 2018

For an efficient management of electricity market and power systems, accurate forecasts for electricity demand are essential. Since there are many factors, either known or unknown, determining the realized loads, it is difficult to forecast the demands with the past time series only. In this paper we perform a cluster analysis on electricity demand data collected from Jan. 2000 to Dec. 2017. Our purpose of clustering on electricity demand data is that each cluster is expected to consist of data whose latent variables are same or similar values. Then, if properly clustered, it is possible to develop an accurate forecasting model for each cluster separately. To validate the feasibility of this approach for building better forecasting models, we clustered data with t-SNE. To apply t-SNE to time series data effectively, we adopt the dynamic time warping as a similarity measure. From the result of experiments, we found that several clusters are well observed and each cluster can be interpreted as a mix of well-known factors such as trends, seasonality and holiday effects and other unknown factors. These findings can motivate the approaches which build forecasting models with respect to each cluster independently.

• Journal of Information Technology Applications and Management
• /
• v.30 no.3
• /
• 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.

• Journal of the Korean Professional Engineers Association
• /
• v.35 no.4
• /
• pp.19-23
• /
• 2002

Recently, deficit of water for daily We, industrial, agricultural use and Increasing water demand of river maintenance has increased gradually by the improvement of living condition of the Republic of Korea. Comprehensive measures for water deficit In the future are studied, based on the Investigated result of the actual condition of water use.

• 한국신재생에너지학회:학술대회논문집
• /
• 2006.11a
• /
• pp.561-565
• /
• 2006

The paper presents a method of assessing the adequate tapaclty of photovoltaic generation systems for public buildings based on analysis of load variation patterns of customers. When PV systems are installed for supplying power for the customer load, reverse power relay is required by the guideline to be installed at the point of common coupling with the power network. The suggested method analyzes daily, weekly and monthly load demand of the customer that Irishes PV system installation, and determines the appropriate rating of the PV system for preventing PV generation from exceeding the customer demand. This work is expected to support renewable energy dissemination projects of public organizations.

• Journal of Labour Economics
• /
• v.31 no.1
• /
• pp.1-27
• /
• 2008

This study analyzes the causes of increase in temporary workers observed in the recent Korean labor market. In the analysis of sectors with relatively high ratio of temporary workers, the manufacturing sector tends to hire temporary workers in order to raise profitability, while wholesale & retails and construction sectors tend to employ temporary workers due to the fluctuation of product demand. Another possibility is that with the expansion of college graduates, it is likely that temporary jobs are used as a screening device to reduce the uncertainty of workers quality.

• IE interfaces
• /
• v.23 no.1
• /
• pp.12-23
• /
• 2010

A semiconductor market is one of the most competitive markets in the world. To survive this competition, important targets for production planning are on-time delivery and profit maximization. In our research, we modify the linear programming model for the current production planning by adding new objective functions that maximize the profit. In addition, we propose a production planning process that gives a priority to new products, reflecting daily fluctuations in demand to weekly production planning. We validate our model with real data sets obtained from a major company semiconductor manufacturer and performed the paired t-test to verify the results. The results showed that our model forecasted profit and loss with 93.2% accuracy and improved the due date satisfaction by 10%.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.33 no.4
• /
• pp.52-60
• /
• 1991

This study was conducted to investigate the appropriate operation method minimizing the deviation between irrigation water demand and release from the reservoirs, and the simulation technique was used in the operation model. This model was applied to the grouped reservoirs system consisted of Dongsang, Daia and Keungchun reservoirs and Eowoo-weir in Chonbuk FLIA district. The results obtained in this study are summarized as follows; 1.The area above the Eowoo weir point was divided into 6 small watersheds, and daily inflows from each watershed were calculated by Tank model. It showed that the average annual runoff ratio was 40-60% respectively. 2.Based on the Blaney-Criddle formula daily water requirement of Chonbuk FLIA irrigation area was estimated, mean water requirement for paddy field during the irrigation period was 818.lmm. 3.Using the basic data such as inflow and water demand, four different release types were selected. Through the simulated operation the difference between intake water required at Eowoo-weir point and release from the 3 reservoirs was estimated. The best result was obtained when Daia and Keungchun reservoirs are operated parallelly at fixed release ratio and the release of Dongsang reservoir was determined according to the storage of Daia reservoir.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.106-118
• /
• 2020

This study examined the impact of COVID-19 on traffic demand (Average Daily Traffic : ADT) by analyzing the available data on highway traffic volume and the spread of COVID-19 cases in Korea. This study used the data from 228 permanent traffic counts (PTCs) on highways from January to May of 2019 and 2020 to analyze the change in ADT. The first cases of infection in Korea occurred on January 20, 2020, and the maximum daily number of infections was 909 on February 29. On April 30, 2020, the daily number of infections decreased to four. The ADT decreased by 3.3% due to the impact of COVID-19. Considering that the traffic volume has increased 2.3% annually over the past decade, the actual decrease in ADT due to the COVID-19 is estimated to be 5.6% (3.3% + 2.3%). The ADT for weekends decreased significantly, compared to during the week. An analysis of the changes in ADT according to the road type revealed decreases in the following: urban roads -4.6%, rural roads -3.2%, and recreational roads -0.7%. Urban roads decreased the most, and tourist roads decreased the least.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.9
• /
• pp.47-54
• /
• 2009

These clays, because of world economy recession, exports decreased rapidly and manufacturing industry growth fell into negative. Industrial power consumption has been reduced about 7[%] that forms 53[%] of total load demand in Korea. And also, daily load pattern has been changed in several ways because of power consumption decrease influenced by domestic demand recession and heating power load decreased by the rise in temperature. This research analyzes, by analyzing maximum load demand, average load demand, load pattern based on relative factor, and load sensitiveness in accordance with temperature, that maximum load demand is more sensitive to atmospheric temperature than GDP growth rate and average load demand tends to be reduced according to GDP growth rate. I suppose KPX could operate the network system economically and safely by forecasting load demand in winter and summer seasons based on the results.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.3
• /
• pp.105-112
• /
• 2019

Due to abnormal high temperature, electric power demand has exceeded the backup power reserved for emergency case, hence, resulting in a major power outage. In today's overcrowded cities, the unexpected disruption in energy supply and demand is a major threat to the enormous economic damage and urban malfunctions. Existing methods for estimating the demand of the emergency power source do not lend themselves to predict the actual demand in the spatial dimension of the city. In addition, the reserve power is arbitrarily distributed in the case of emergency. This paper presents a method that predicts the emergency power demand using the spatial distribution of emergency power demand by applying the daily energy consumption intensity and emergency power demand according to urban spatial information and building use.