• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.11A
• /
• pp.1173-1181
• /
• 2007

A number of routing algorithms have been studied for wireless mobile ad-hoc network. Among them, the AODV routing algorithm with on-demand method periodically transmits hello message and monitors link state during data transmission in order to maintain routing paths. When a path is disconnected, a node that senses it transmits a RERR packet to the transmitting node or transmits a RREQ locally so that the path could be repaired. With that, the control packet such as a RREQ is broadcast, which causes the consumption of bandwidth and incurs data latency. This paper proposes a LRRLBP algorithm that locally repairs a path by predicting link state before disconnecting the path based on the AODV routing protocol for solving such problems. Intensive simulations with the results using NS-2 simulator are shown for verifying the proposed protocol.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1141-1148
• /
• 2013

End-uses of household water have been influenced by a housing type, life style and housing area which are considered as internal factors. Also, there are external factors such as water rate, weather and water supply facilities. Analysis of influential factors on water consumption in households would give an explanation on the cause of changing trends and would help predicting the water demand of end-use in household. In this paper, we used real data to predict toilet and laundry water-uses and utilized the linear regression model with autoregressive errors. The results showed that the monthly autoregressive error models explained about 71% for describing the water demand of end-use in toilet and laundry water-uses.

• Korean Chemical Engineering Research
• /
• v.50 no.3
• /
• pp.479-491
• /
• 2012

In this paper we performed evaluation of the economics of a district heating system (DHS) consisting of energy suppliers and consumers, heat generation and storage facilities and power transmission lines in the capital region, as well as identification of optimal operating conditions. The optimization problem is formulated as a mixed integer linear programming (MILP) problem where the objective is to minimize the overall operating cost of DHS while satisfying heat demand during 1 week and operating limits on DHS facilities. This paper also propose a new forecasting model of the system marginal price (SMP) using past data on power supply and demand as well as past cost data. In the optimization, both the forecasted SMP and actual SMP are used and the results are analyzed. The salient feature of the proposed approach is that it exhibits excellent predicting performance to give improved energy efficiency in the integrated DHS.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.6
• /
• pp.187-193
• /
• 2018

There has been a gradual increase in the demand for the electric power in Korea. In order to meet the demand, power station should have technical functions with increased effectiveness. When accident happens in electric machinery at power stations, huge amount of economic losses and mulfunction of equipments occur. One of the accidents is a deteriorated cables operating power stations. In order to prevent cable accident in advance, we should monitor the insulation status of the cable. Cable accidents are resulting from the junctions. We have developed and installed a device in order to identify the status of junction part of power cable at Korea Western Power Co., Ltd.. We performed an accurate diagnosis for the stable utilization of junctions where the accidents occurs most frequently, and to increase the reliability. In this paper, we present the concepts of our device and the method of monitoring diagnosis for the stable use of junctions at cables predicting the life time of cables by analyzing the data obtained by the device. We also present the hardware aspect of the device we have developed.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.1
• /
• pp.1-13
• /
• 2022

The Yongin Light Rail train was manufactured by Bombardier Transportation in Canada in 2008 and is a privately invested railway line that has been operating in Yongin-si, Gyeonggi-do, since 2013. When the frequency of train failure increases due to aging, and there is a delay in the delivery period of imported parts used in the Bombardier manufactured trains, timely vehicle maintenance may not be performed due to lack of parts. To solve this problem, it is necessary to build a 'vehicle parts maintenance demand forecasting system' that analyzes the accurate and actual maintenance demand annual based on the condition of vehicle parts. The full scope of analysis in this paper analyzes failure data from various angles after opening of Yongin light rail vehicle to analyze failure patterns for each part and identify replacement cycles according to possible failures and consumption of parts. Based on this study, it is expected that Yongin Light Rail's maintenance system will change from the existing time-based replacement (TBM) concept to the condition-based maintenance (CBM) concept. It is expected that this study will improve the efficiency of the Yongin Light Rail maintenance system and increase vehicle availability. This paper is a fundamental for establishing of a system for predicting the replacement timing of vehicle parts for Yongin Light Rail. It reports the results of data analysis on some vehicle parts.

• Korean Journal of Agricultural Science
• /
• v.49 no.2
• /
• pp.193-202
• /
• 2022

The recurrent neural network (RNN) algorithm has been widely used in water-related research areas, such as water level predictions and water quality predictions, due to its excellent time series learning capabilities. However, studies on water quality predictions using RNN algorithms are limited because of the scarcity of water quality data. Therefore, most previous studies related to water quality predictions were based on monthly predictions. In this study, the quality of the water in a reservoir in Nonsan, Chungcheongnam-do Republic of Korea was predicted using the RNN-LSTM algorithm. The study was conducted after constructing data that could then be, linearly interpolated as daily data. In this study, we attempt to predict the water quality on the 7th, 15th, 30th, 45th and 60th days instead of making daily predictions of water quality factors. For daily predictions, linear interpolated daily water quality data and daily weather data (rainfall, average temperature, and average wind speed) were used. The results of predicting water quality concentrations (chemical oxygen demand [COD], dissolved oxygen [DO], suspended solid [SS], total nitrogen [T-N], total phosphorus [TP]) through the LSTM algorithm indicated that the predictive value was high on the 7th and 15th days. In the 30th day predictions, the COD and DO items showed R² that exceeded 0.6 at all points, whereas the SS, T-N, and T-P items showed differences depending on the factor being assessed. In the 45th day predictions, it was found that the accuracy of all water quality predictions except for the DO item was sharply lowered.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.27 no.5
• /
• pp.213-220
• /
• 2023

Seismic fragility curves play a crucial role in assessing potential seismic losses and predicting structural damage caused by earthquakes. This study compares non-sampling-based methods of seismic fragility curve derivation, particularly the probabilistic seismic demand model (PSDM) and finite element reliability analysis (FERA), both of which require employing sophisticated finite element analysis to evaluate and predict structural damage caused by earthquakes. In this study, a three-dimensional finite element model of API 5L X65, a buried gas pipeline widely used in Korea, is constructed to derive seismic fragility curves. Its seismic vulnerability is assessed using nonlinear time-history analysis. PSDM and a FERA are employed to derive seismic fragility curves for comparison purposes, and the results are verified through a comparison with those from the Monte Carlo Simulation (MCS). It is observed that the fragility curves obtained from PSDM are relatively conservative, which is attributed to the assumption introduced to consider the uncertainty factors. In addition, this study provides a comprehensive comparison of seismic fragility curve derivation methods based on sophisticated finite element analysis, which may contribute to developing more accurate and efficient seismic fragility analysis.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.128-130
• /
• 2021

This study aims to implement a Regression Analysis system for predicting the appropriate production of flatfish. Due to Korea's signing of FTAs with countries around the world and accelerating market opening, Korean flatfish farming businesses are experiencing many difficulties due to the specificity and uncertainty of the environment. In addition, there is a need for a solution to problems such as sluggish consumption and price drop due to the recent surge in imported seafood such as salmon and yellowtail and changes in people's dietary habits. in this study, Using the python module, xlwings, it was used to obtain for the production amount of flatfish and to predict the amount of flatfish to be produced later. was used to predict the amount of flatfish to be produced in the future. Therefore, based on the analysis results of this prediction of flatfish production, the flatfish aquaculture industry will be able to come up with a plan to achieve an appropriate production volume and control supply and demand, which will reduce unnecessary economic loss and promote new value creation based on data. In addition, through the data approach attempted in this study, various analysis techniques such as artificial neural networks and multiple regression analysis can be used in future research in various fields, which will become the foundation of basic data that can effectively analyze and utilize big data in various industries.

• Earthquakes and Structures
• /
• v.1 no.1
• /
• pp.21-41
• /
• 2010

Multi-span steel-concrete composite (SCC) bridges are very sensitive to earthquake loading. Extensive damage may occur not only in the substructures (piers), which are expected to yield, but also in the other components (e.g., deck, abutments) involved in carrying the seismic loads. Current seismic codes allow the design of regular bridges by means of linear elastic analysis based on inelastic design spectra. In bridges with superstructure transverse motion restrained at the abutments, a dual load path behavior is observed. The sequential yielding of the piers can lead to a substantial change in the stiffness distribution. Thus, force distributions and displacement demand can significantly differ from linear elastic analysis predictions. The objectives of this study are assessing the influence of piers-deck stiffness ratio and of soil-structure interaction effects on the seismic behavior of continuous SCC bridges with dual load path, and evaluating the suitability of linear elastic analysis in predicting the actual seismic behavior of these bridges. Parametric analysis results are presented and discussed for a common bridge typology. The response dependence on the parameters is studied by nonlinear multi-record incremental dynamic analysis (IDA). Comparisons are made with linear time history analysis results. The results presented suggest that simplified linear elastic analysis based on inelastic design spectra could produce very inaccurate estimates of the structural behavior of SCC bridges with dual load path.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.353-360
• /
• 2016

Recently, solar photovoltaic(PV) power generation which generates electrical power from solar panels composed of multiple solar cells, showed the most prominent growth in the renewable energy sector worldwide. However, in spite of increased demand and need for a photovoltaic power generation, it is difficult to early detect defects of solar panels and equipments due to wide and irregular distribution of power generation. In this paper, we choose an optimal machine learning algorithm for estimating the generation amount of solar power by considering several panel information and climate information and develop a defect detection system by using the chosen algorithm generation. Also we apply the algorithm to a domestic solar photovoltaic power plant as a case study.