• Advances in Energy Research
• /
• v.6 no.2
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.14 no.4
• /
• pp.269-276
• /
• 2012

The objective of this short communication is to introduce several evaluation methods to crop model users because the evaluation of crop model performance is an important step to develop or select crop model. In this paper, mean error, mean absolute error, index of agreement, root mean square error, efficiency of model, accuracy factor and bias factor were explained and compared in terms of dimension and observed number. Efficiency of model and index of agreement are dimensionless and independent of number of observation. Relative root mean square, accuracy factor and bias factor are dimensionless and not independent of number of observation. Mean error and mean absolute error are affected by dimension and number of observation.

• KIEAE Journal
• /
• v.17 no.3
• /
• pp.5-13
• /
• 2017

Purpose: Various studies have been performed to address the issue of increased energy use by buildings. In particular, research on complex envelopes that combines diverse envelope element techniques is currently in progress in the building sector. The present study aimed to develop an awning system using a light shelf, and to verify its validity through performance evaluation. Method: In the present study, a testbed was established for the performance evaluation of the awning system using a light shelf, and the uniformity ratio and lighting energy consumption were compared and analyzed relative to those with no awning and light shelf installation (Case 1), awning installation (Case 2), and light shelf installation (Case 3). Result: 1) In the present study, an awning system using a light shelf (Case 4) where an opening is made on the awning screen and natural light can be introduced through the light shelf located at the bottom was developed. 2) The optimum standard for Case 4 obtained through the performance evaluation was a 0.6m lighting length and a 2m extension length at a light shelf angle of $30^{\circ}$. 3) Case 4 with the optimum standard had a 5.5% lower uniformity ratio than Case 2, but had a higher uniformity ratio than Case 1 and Case 3. 4) Case 4 with the optimum standard showed 13.3%, 44.6%, and 0%~8.7% lighting energy reductions compared to Case 1, Case 2, and Case 3, respectively. 5) Based on the above results, Case 4 suggested in the present study was found to be effective for indoor light environment improvement and lighting energy reduction.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2009.05a
• /
• pp.348-351
• /
• 2009

In order to evaluate the performance of a grounding system against lightning or fault currents including high frequency components, the grounding impedance should be considered rather than its ground resistance. Recently, some researches on the evaluation and modeling of the grounding impedances have been carried out but the results have not been yet sufficient. This paper deals with the frequency dependence of the resistivity and relative dielectric constant of sand associated with water contents. As a result, the resistivity of sand is getting lower with increasing water content and it is nearly independent on the frequency in the range of less than 1MHz, and is decreased over the frequency range of above 1MHz. Also, the relative dielectric constant is rapidly decreased with the frequency in the range of less than 10kHz, but it is nearly not dependent on the frequency over the frequency range of 10kHz. It was found from this work that the frequency dependance of resistivity and relative dielectric constant of soil should be considered in designing the grounding systems for protection against lightning or surges.

• Nuclear Engineering and Technology
• /
• v.56 no.5
• /
• pp.1725-1732
• /
• 2024

In nuclear power plants, reactor coolant leakage can occur due to various reasons. Early detection of leaks is crucial for maintaining the safety of nuclear power plants. Currently, a detection system is being developed in Korea to identify reactor coolant system (RCS) leakage of less than 0.5 gpm. Typically, RCS leaks are detected by monitoring temperature, humidity, and radioactivity in the containment, and a water level in the sump. However, detecting small leaks proves challenging because the resulting changes in the containment humidity and temperature, and the sump water level are minimal. To address these issues and improve leak detection speed, it is necessary to quantify the leaks and develop an artificial intelligence-based leak detection system. In this study, we employed bidirectional long short-term memory, which are types of neural networks used in artificial intelligence, to predict the relative humidity in the leakage area for leak quantification. Additionally, an optimization technique was implemented to reduce learning time and enhance prediction performance. Through evaluation of the developed artificial intelligence model's prediction accuracy, we expect it to be valuable for future leak detection systems by accurately predicting the relative humidity in a leakage area.

• Journal of the Korean Solar Energy Society
• /
• v.26 no.4
• /
• pp.9-16
• /
• 2006

Geothermal-energy has been getting popular as a natural energy source for green buildings these days. Public building with gross area more than $3000m^2$, planned after March, 2005, should spend about 5% of total building cost for equipment run by natural energy source (e.g. geothermal, solar heat, solar power, etc) according to renewable energy promotion law in Korea. As a result geothermal-energy using heat pump system is emerging as a effective alternative for realistic and economic plan although design guidelines and construction code for the system is in progress and technical data is far from sufficient. The quantitative analysis on the performance of geothermal-energy using heat pump system is insufficient for appropriate design of it. In this paper, cooling performance of geothermal-energy using heat pump system of residential and retail etc. mixed-use building has been analyzed on the basis of temperature comparison between inlet and outlet of heat exchangers of the operating system. Additionally, dry-bulb temperature and relative humidity have been measured and analyzed together as an index of indoor thermal environment.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.5
• /
• pp.67-73
• /
• 2013

The conversion of solar radiation into electrical energy by Photo-Voltaic (PV) effect is a very promising technology, being clean, silent and reliable, with very small maintenance costs and small ecological impact. The output power produced by the PV panels depends strongly on the incident light radiation. The continuous modification of the sun-earth relative position determines a continuously changing of incident radiation on a fixed PV panel. The point of maximum received energy is reached when the direction of solar radiation is perpendicular on the panel surface. Thus an increase of the output energy of a given PV panel can be obtained by mounting the panel on a solar tracking device that follows the sun trajectory. Tracking systems that have two axes and follow the sun closely at all times during the day are currently the most popular. This paper presents research conducted into the performance of Solar tracking system with photosensors. The results show that an optimized dual-axis tracking system with photosensor performance and analysis. From the obtained results, it is seen that the sun tracking system improves the energy and energy efficiency of the PV panel.ti-junction CPV module promises to accelerate growth in photovoltaic power generation.

• Structural Engineering and Mechanics
• /
• v.39 no.5
• /
• pp.717-732
• /
• 2011

Nonlinear dynamic analysis and evaluation of eccentric braced steel frames (EBF) equipped with friction damper (FD) is studied in this research. Previous studies about assessment of seismic performance of steel braced frame with FD have been generally limited to installing this device in confluence of cross in concentrically braced frame such chevron and x-bracing. Investigation is carried out with three types of steel frames namely 5, 10 and 15 storeys, representing the short, medium and high structures respectively in series of nonlinear dynamic analysis and 10 slip force values subjected to three different earthquake records. The proper place of FD, rather than providing them at all level is also studied in 15 storey frame. Four dimensionless indices namely roof displacement, base shear, dissipated energy and relative performance index (RPI) are determined in about 100 nonlinear dynamic analyses. Then average values of maximum roof displacement, base shear, energy dissipated and storey drift under three records for both EBF and EBF equipped with friction damper are obtained. The result indicates that FD reduces the response compared to EBF and is more efficient than EBF for taller storey frames.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.3
• /
• pp.710-716
• /
• 2008

This paper covers the performance evaluation of two flash memory-based file storages, NAND and NOR, which are the major flash types. To evaluate their performances, we set up separate file storages for the two types of flash memories on a PocketPC-based experimental platform. Using the platform, we measured and compared the I/O throughputs in terms of buffer size, amount of used space, and kernel-level write caching. According to the results from our experiments, the overall performance of the NAND-based storage is higher than that of NOR by up to 4.8 and 5.7 times in write and read throughputs, respectively. The experimental results show the relative strengths and weaknesses of the two schemes and provide insights which we believe assist in the design of flash memory-based file storages.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2897-2904
• /
• 2023

The Standardized Plant Analysis Risk-Human Reliability Analysis (SPAR-H) method is a widely used method in human reliability analysis (HRA). Performance shaping factors (PSFs) refer to the factors that may influence human performance and are used to adjust nominal human error probabilities (HEPs) in SPAR-H. However, the PSFs are assumed to be independent, which is unrealistic and can lead to unreasonable estimation of HEPs. In this paper, a new method is proposed to handle the dependencies among PSFs in SPAR-H to obtain more reasonable results. Firstly, the dependencies among PSFs are analyzed by using decision-making trial and evaluation laboratory (DEMATEL) method. Then, PSFs are assigned different weights according to their dependent relationships. Finally, multipliers of PSFs are modified based on the relative weights of PSFs. A case study is illustrated that the proposed method is effective in handling the dependent PSFs in SPAR-H, where the duplicate calculations of the dependent part can be reduced. The proposed method can deal with a more general situation that PSFs are dependent, and can provide more reasonable results.