• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• 한국경영정보학회:학술대회논문집
• /
• 2007.11a
• /
• pp.245-250
• /
• 2007

Prior research on the user experience assumes that when users acquire good experience through the usage of a certain device or system, the user satisfaction increases, and the user satisfaction can forecast the user loyalty effectively. However, theoretical model based on the user satisfaction does not reflect users' emotional or relationship-based experience factors which are fostered through users' long-term interaction with a device or system. Therefore, this research developed the new theoretical model based on the concept of emotional attachment and integrated the model to the existing user satisfaction model to overcome theoretical and practical limitations of the user satisfaction concept. Also, this integrated model was empirically evaluated to check its validity by surveying users of 4 kinds of electronic products.

• Journal of the Korean housing association
• /
• v.17 no.2
• /
• pp.19-26
• /
• 2006

Building would be deteriorated with time elapse, influenced by its geographic situation, climate and other environmental conditions. In addition, the systematic maintenance could be provided to keep the resident a recent living condition. The existing breakdown maintenance will be changed into the preventive maintenance. The preventive maintenance is required to get the repair time, the repair scope and frequency. In this paper, it aimed at providing the repair time range over the building components, utilizing the relation between the determination curve and the performance recovery through repair. Results of this study are as follows : First, the forecast of the repair time over the building components could be calculated and equalized with the deterioration and performance degree. Second, the repair time range of building components would be provided into five categories and 3rd repair time. Results of this study will set up the long-term repair plan of building, and finally keep an housing condition comfortable.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.43 no.2
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.722-724
• /
• 2004

Demand estimates in electric power systems have traditionally consisted of time-series analyses over long time periods. The resulting database consisted of huge amounts of data that were then analyzed to create the various coefficients used to forecast power demand. In this research, we take advantage of universally used analysis techniques analysis, but we also use easily available data-mining techniques to analyze patterns of days and special days(holidays, etc.). We then present a new method for estimating and forecasting power flow using decision tree analysis. And because analyzing the relationship between the estimate and power system ceiling Trices currently set by the Korea Power Exchange. We included power system ceiling prices in our estimate coefficients and estimate method.

• The Journal of Asian Finance, Economics and Business
• /
• v.1 no.3
• /
• pp.29-36
• /
• 2014

This paper attempts to measure the impact of non-financial factors including analyst practices and broker resources on performance of sell side research. Results reveal that these non-financial factors have a measurable impact on performance of target price forecasts. Number of pages written by an analyst (surrogate for analyst practice) is significantly and directly linked with target price accuracy indicating a more elaborate analyst produces better target price forecasts. Analyst compensation (surrogate for broker resource) is significantly and inversely linked with target price accuracy. Out performance by analysts working with lower paying firms is possibly associated with motivation to migrate to higher paying broking firms. The study finds that employing more number of analysts per research report has no significant impact on target price accuracy -negative coefficient indicates that team work may not result in better target price forecasts. Though insignificant, long term forecast horizon negatively affects target price accuracy while stock volatility improves target price accuracy.

• Korean System Dynamics Review
• /
• v.16 no.3
• /
• pp.31-48
• /
• 2015

The purpose of this paper is to simulate drinking population, an alcoholic abuser and an alcoholic through therapy programs and system dynamic model. Then we try to research relationship between an alcoholic crime and related therapy programs. The results of the model simulation were consistently increased drinking population and 3 types drinkers until 2020 years. Specially the growth rate of drinking abusers will be passing that of a drinking population. Second, It showed clearly the decreasing effects of drinking crime on therapy programs(clinical treatment, preventive displine and counseling treatment). Finally, it will be positvely necessary the long-term and various alcoholic therapy program for reducing the ratio of drinking abusers and an alcoholic. In the second place, government and medical centers must be established a concrete information systems for collecting alcoholic datum.

• Proceedings of the KSR Conference
• /
• 2009.05a
• /
• pp.66-72
• /
• 2009

In order to forecast the progress of the track irregularity, we should observe the long-term track quality and divide a track into some separated divisions which have homogeneous property. For this, we define the division of track which has homogeneous property as a 'Segment' and manage the 'TQI(Track Quality Index)' using track induction data based on each segment. In this study, we introduce some methods of estimating track quality and figure out the TQIs of sample section using new FRA TQI method. In addition, we conducted a basic study of the forecasting model for the progress of track irregularity by analyzing track maintenance data.

• Korean Management Science Review
• /
• v.31 no.1
• /
• pp.41-48
• /
• 2014

This study presents a bottom-up approach for analyzing greenhouse gas (GHG) emissions for the shipbuilding industry in Korea. The overall procedures for deriving GHG emissions from the Korean shipbuilding industry are presented. Based on the long-term forecast on energy demands of the Korean shipbuilding industry, reference energy system (RES) and energy balance (EB) for the shipbuilding process are derived for bottom-up modeling.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2000.10a
• /
• pp.384-389
• /
• 2000

A artificial neural network model was developed to analyze and forecast the flow fluctuation at small streams in the Balan watershed. Backpropagation neural networks were found to perform very well in forecasting daily streamflows. In order to deal with slow convergence and an appropriate structure, two algorithms were proposed for speeding up the convergence of the backpropagation method, and the Bayesian Information Criterion(BIC) was proposed for obtaining the optimal number of hidden nodes. From simulations using daily flows at the HS#3 watershed of the Balan Watershed Project, which is 412,5 ㏊ in size and relatively steep in landscape, it was found that those algorithms perform satisfactorily.