• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1083-1093
• /
• 2021

It is an essential to predict water usage for establishing an optimal supply operation plan and reducing power consumption. However, the water usage by consumer has a non-linear characteristics due to various factors such as user type, usage pattern, and weather condition. Therefore, in order to predict the water consumption, we proposed the methodology linking various techniques that can consider non-linear characteristics of water use and we called it as KWD framework. Say, K-means (K) cluster analysis was performed to classify similar patterns according to usage of each individual consumer; then Wavelet (W) transform was applied to derive main periodic pattern of the usage by removing noise components; also, Deep (D) learning algorithm was used for trying to do learning of non-linear characteristics of water usage. The performance of a proposed framework or model was analyzed by comparing with the ARMA model, which is a linear time series model. As a result, the proposed model showed the correlation of 92% and ARMA model showed about 39%. Therefore, we had known that the performance of the proposed model was better than a linear time series model and KWD framework could be used for other nonlinear time series which has similar pattern with water usage. Therefore, if the KWD framework is used, it will be possible to accurately predict water usage and establish an optimal supply plan every the various event.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.293-302
• /
• 2016

Since the electricity is produced and consumed simultaneously, predicting the electric load and securing affordable electric power are necessary for reliable electric power supply. In particular, a university campus is one of the highest power consuming institutions and tends to have a wide variation of electric load depending on time and environment. For these reasons, an accurate electric load forecasting method that can predict power consumption in real-time is required for efficient power supply and management. Even though various influencing factors of power consumption have been discovered for the educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative prediction of electric load. In this paper, we build an electric load forecasting model by implementing and evaluating various machine learning algorithms. To do that, we consider three building clusters in a campus and collect their power consumption every 15 minutes for more than one year. In the preprocessing, features are represented by considering periodic characteristic of the data and principal component analysis is performed for the features. In order to train the electric load forecasting model, we employ both artificial neural network and support vector machine. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to real electric load.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.829-835
• /
• 2018

Recently, studies have been actively conducted to reduce spare power that is unnecessarily generated or wasted in existing power systems and to improve energy use efficiency. In this study, smart meter, which is one of the element technologies of smart grid, is implemented to improve the efficiency of energy use by controlling power of electric devices, and predicting trends of energy usage based on deep learning. We propose and develop an algorithm that controls the power of the electric devices by comparing the predicted power consumption with the real-time power consumption. To verify the performance of the proposed smart meter based on the deep running, we constructed the actual power consumption environment and obtained the power usage data in real time, and predicted the power consumption based on the deep learning model. We confirmed that the unnecessary power consumption can be reduced and the energy use efficiency increases through the proposed deep learning-based smart meter.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.137-146
• /
• 2011

In order to support increased consumer awareness regarding energy consumption, we present new ways of monitoring and predicting with energy in electric appliances. The proposed system is a design of a common electrical power outlet called smart plug that measures the amount of current passing through current sensor at 0.5 second. To acquire data for training and testing the proposed neural network, weather parameters used include average temperature of day, min and max temperature, humidity, and sunshine hour as input data, and power consumption as target data from smart plug. Using the experimental data for training, the neural network model based on Back-Propagation algorithm was developed. Multi layer perception network was used for nonlinear mapping between the input and the output data. It was observed that the proposed neural network model can predict the power consumption quite well with correlation coefficient was 0.9965, and prediction mean square error was 0.02033.

• Computers and Concrete
• /
• v.25 no.1
• /
• pp.83-94
• /
• 2020

The use of fly ash in modern-day concrete technology aiming sustainable constructions is on rapid rise. Fly ash, a spinoff from coal calcined thermal power plants with pozzolanic properties is used for cement replacement in concrete. Fly ash concrete is cost effective, which modifies and improves the fresh and hardened properties of concrete and additionally addresses the disposal and storage issues of fly ash. Soft computing techniques have gained attention in the civil engineering field which addresses the drawbacks of classical experimental and computational methods of determining the concrete compressive strength with varying percentages of fly ash. In this study, models based on soft computing techniques employed for the prediction of the compressive strengths of fly ash concrete are collected from literature. They are classified in a categorical way of concrete strengths such as control concrete, high strength concrete, high performance concrete, self-compacting concrete, and other concretes pertaining to the soft computing techniques usage. The performance of models in terms of statistical measures such as mean square error, root mean square error, coefficient of correlation, etc. has shown that soft computing techniques have potential applications for predicting the fly ash concrete compressive strengths.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.18 no.2
• /
• pp.312-322
• /
• 2012

Objectives: The purpose of this study was to investigate the factors related to adjustment of college for nursing students and to develop a collective model for successful prediction and concrete paths of the factors. Methods: Data collection was conducted from May 19th 2010 to Jun 4th 2010. Five hundred thirty-one questionnaires were used for data analysis after distributing 560 sheets to senior students in 8 different locations. Data was analyzed with SPSS 18.0 Win program and AMOS 18.0. Results: Mother attachment does not have a direct effect on adjustment to college life but does effect psychological well-being and coping, which indirect adjustment to college life. In addition, the more psychological well-being and coping usage frequency, and the less stress of clinical practice, the higher score of adjustment to college life. According to the results, explanatory power of the model for the college nursing students' adjustment was 62.0%. Conclusions: To improve adjustment to college life, it is recommended to have a direct method of developing psychological well-being and coping improvement program to improve mother attachment. The research is meaningful in a sense that it explains the cause and effect relationship between adjustment to college life and relevant variables to predict comprehensive dimensional explanation of adjustment of college life for nursing students.

• The Journal of Information Systems
• /
• v.5
• /
• pp.205-248
• /
• 1996

Historically, the en-users' acceptance of the expert systems(ES) have generally been used as a proxy for the ES' implementation success by both practitioners and academicians. However, with regard to bank loan decisions, most loan officers approach the acquisition of an ES with apprehension. In order to overcome this skepticism, more research should focus on the behavioral aspects relate to systems acquisition and usage. This research applied Vroom's(1964) expectancy theory in an effort to predict end-users' motivation to use an ES in a bank loan decision context. Because human behaviors and judgements are nonlinear rather than linear functions, accurately predicting human behavior is very difficult. To increase the prediction power for end-users' motivation to use an ES in a bank loan decision context, this research used an artificial neural network (ANN) model. In this research, an attempt was made to evaluate adequacy of the surrogates by analyzing differences between real bank loan officers and student surrogates in applying expectancy theory to estimate bank loan officers' motivation to use ES in a bank loan decision context.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.3
• /
• pp.376-383
• /
• 2012

A number of scientific researches are currently being conducted on the potential health hazards of power frequency electric and magnetic field (EMF). There exists a non-objective and psychological belief that they are harmful, although no scientific and objective proof of such exists. This possible health risk from ELF magnetic field (MF) exposure, especially for children under 17 years of age, is currently one of Korea's most highly contested social issues. Therefore, to assess the magnetic field exposure levels of those children in their general living environments, the personal MF exposure levels of 436 subjects were measured for about 6 years using government funding. Using the measured database, estimation formulas were developed to predict personal MF exposure levels. These formulas can serve as valuable tools in estimating 24-hour personal MF exposure levels without directly measuring the exposure. Three types of estimation formulas were developed by applying evolutionary computation methods such as genetic algorithm (GA) and genetic programming (GP). After tuning the database, the final three formulas with the smallest estimation error were selected, where the target estimation error was approximately 0.03 ${\mu}T$. The seven parameters of each of these three formulas are gender (G), age (A), house type (H), house size (HS), distance between the subject's residence and a power line (RD), power line voltage class (KV), and the usage conditions of electric appliances (RULE).

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.226-230
• /
• 2007

This paper proposes a local scheduling method based on user pattern for Volunteer computing project, Korea@Home. It enables Korea@Home participants to run the agent without disturbance. It is devised to prevent user's application from delay while running the agent and decreases the frequency of switching resource between the user and the agent. We analyze the user's patterns of donating computing resource with Korea@Home which is a representative volunteer computing project in Korea. It has contributed the computing power to several applications including climate prediction and virtual screening. It promotes the volunteers to participate continuously without disturbance and increases the potential computing power with non-disturbance scheduling based on user usage pattern for Volunteer Computing.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.30 no.3
• /
• pp.130-142
• /
• 2018

We use heat pumps with thermal storage system to reduce peak usage of electric power during winters and summers. A heat pump stores thermal energy in a thermal storage tank during the night, to meet load requirements during the day. This system stabilizes the supply and demand of electric power; moreover by utilizing the inexpensive midnight electric power, thus making it cost effective. In this study, we propose a system wherein the thermal storage tank and heat pump are modeled using the TRNSYS, whereas the control simulations are performed by (i) conventional control methods (i.e., thermal storage priority method and heat pump priority method); (ii) region control method, which operates at the optimal part load ratio of the heat pump; (iii) load response control method, which minimizes operating cost responding to load; and (iv) dynamic programming method, which runs the system by following the minimum cost path. We observed that the electricity cost using the region control method, load response control approach, and dynamic programing method was lower compared to using conventional control techniques. According to the annual simulation results, the electricity cost utilizing the load response control method is 43% and 4.4% lower than those obtained by the conventional techniques. We can note that the result related to the power cost was similar to that obtained by the dynamic programming method based on the load prediction. We can, therefore, conclude that the load response control method turned out to be more advantageous when compared to the conventional techniques regarding power consumption and electricity costs.