• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.694-706
• /
• 2019

In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price time series. We collected historic cryptocurrency price time series data and preprocessed them in order to make them clean for use as train and target data. After such preprocessing, the price time series data were systematically encoded into the three-dimensional price tensor representing the past price changes of cryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as input data of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to find the most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our study showed that the LSTM model outperforms the gradient boosting model, a general machine learning model known to have relatively good prediction performance, for the time series classification of the cryptocurrency price trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GB model.

• 한국신재생에너지학회:학술대회논문집
• /
• 2011.05a
• /
• pp.76.1-76.1
• /
• 2011

With the growing penetration of distributed generation including from renewable sources, smart grid power system is needed to address the reliability problem. One important feature of smart grid is demand response. In order to design a demand response program, it is indispensable to understand how consumer reacts upon the change of electricity price. In this paper, we construct an econometrics model to estimate the hourly price elasticity of demand. This panel model utilizes the hourly load data obtained from KEPCO for the period from year 2005 to 2009. The hourly price elasticity of demand is found to be statistically significant for all the sample under investigation. The samples used for this analysis is from the past historical data under the price structure of three different time zones for each season. The result of the analysis of this time of use pricing structure would allow the policy maker design an appropriate incentive program. This study is important in the sense that it provides a basic research information for designing future demand response programs.

• KIEAE Journal
• /
• v.10 no.5
• /
• pp.159-164
• /
• 2010

High-rising buildings are a sort of solution to recent cities. Till now real estate development was concentrated in new development on vacant lots, and it resulted urban sprawl. Generally large cities are confronted with the exodus of industry and population from city. High-rising buildings solve many problems associated with this problem. The purpose of this research is to identify the effect of super high-rise mixed use building project process on apartment price. For this study, the hypothesis is that price of apartments is influenced by project process of super high-rise mixed use building. The study concerned 4 variations of project process that is building permits stage, sale stage, construction starting stage and stage of moving into building. The target projects of buildings are selected by number of floor(over 40 floors) and construction time. And 48 apartment complex are selected around super high-rise mixed use building. This study uses hedonic price function to analysis effect of project process of super high-rise mixed use building. A price of apartments is defined as a dependent variable. Characteristics of residence, complex, district and super high-rise building are defined as independent variables. The results are as follows; first, there is no error in price model of this study. Second, it is found that apartment price was influenced negatively by building permit stage and sale stage of super high-rise mixed use building. But that was influenced positively by construction starting stage and stage of moving into building of that. Third, as the project process of super high-rise mixed use building was proceeded, price of apartments was increased.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.11
• /
• pp.1793-1799
• /
• 2016

As one of the main trends in global industries is eco-friendly energy, the interest on Electric Vehicle(EV) has been increased. However, if large amount of EVs start to charging, it could cause rapid increase in demand power of the power system. To guarantee stable operation of the power system, those unpredictable power consume should be mitigated. In this paper, therefore, we propose a practical smart EVs charging scheme to prevent the rapid increase of the demand power and also provide load flattening function. For that we considered Time-of-Use(ToU) price and actual data such as driving pattern and parameters of distribution system. Simulation results show that the proposed method provides proper load flattening function while preventing the rapid increase of the demand power of the power system.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.1
• /
• pp.14-19
• /
• 2008

The paper presents an intelligent time series model to predict uncertain electricity market price in the deregulated industry environment. Since the price of electricity in a deregulated market is very volatile, it is difficult to estimate an accurate market price using historically observed data. The parameter of an intelligent time series model is obtained based on the simultaneous perturbation stochastic approximation (SPSA). The SPSA is flexible to use in high dimensional systems. Since prediction models have their modeling error, an error compensator is developed as compensation. The SPSA based intelligent model is applied to predict the electricity market price in the Pennsylvania-New Jersey-Maryland (PJM) electricity market.

• New & Renewable Energy
• /
• v.17 no.2
• /
• pp.1-8
• /
• 2021

We estimated the price range of electricity transactions under the prosumer system, considering the spread of renewable energy and the prospect of introducing a surplus power trading system between power consumers in Korea. The range (min/max) of power transaction prices was estimated by prosumers and consumers who could purchase electricity from utilities if needed. It is assumed that utilities purchased electricity from prosumers and consumers under a Time-of-Use (TOU) rate, trading at a monthly price. The range of available transaction prices according to the amount of power purchased from utilities and the amount of transaction power was also estimated. The price range that can be traded is expected to vary depending on variables such as the TOU rate, purchased and surplus power, levelized cost of electricity, etc.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.1-10
• /
• 2017

With the current global need for eco-friendly energies, the large scale use of Electric Vehicles (EVs) is predicted. However, the need to frequently charge EVs to an electrical power system involves risks such as rapid increase of demand power. Therefore, in this paper, we propose a practical smart EV charging scheme considering a Time-of-Use (ToU) price to prevent the rapid increase of demand power and provide load leveling function. For a more practical analysis, we conduct simulations based on the actual distribution system and driving patterns in the Republic of Korea. Results show that the proposed method provides a proper load leveling function while preventing a rapid increase of demand power of the system.

• Korean Journal of Agricultural Science
• /
• v.45 no.4
• /
• pp.859-870
• /
• 2018

Dried red peppers are a staple agricultural product used in Korean cuisine and as such, are an important aspect of agricultural producers' income. Correctly forecasting both their supply and demand situations and price is very important in terms of the producers' income and consumer price stability. The primary objective of this study was to compare the performance of time series forecasting models for dried red peppers in Korea. In this study, three models (an autoregressive model with exogenous variables [ARX], AR-exponential generalized autoregressive conditional heteroscedasticity [EGARCH], and ARX-EGARCH) are presented for forecasting the wholesale price of dried red peppers. As a result of the analysis, it was shown that the ARX model and ARX-EGARCH model, each of which adopt both the rolling window and the adding approach and use the agricultural cooperatives price as the exogenous variable, showed a better forecasting performance compared to the autoregressive model (AR)-EGARCH model. Based on the estimation methods and results, there was no significant difference in the accuracy of the estimation between the rolling window and adding approach. In the case of dried red peppers, there is limitation in building the price forecasting models with a market-structured approach. In this regard, estimating a forecasting model using only price data and identifying the forecast performance can be expected to complement the current pricing forecast model which relies on market shipments.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.11a
• /
• pp.142-146
• /
• 2006

This paper considers a SCM issue concerned with an integrated problem of inventory control and dynamic pricing strategies when demands are price and time dependent. The associated price markdowns are conducted for inventory control in a two-layer market consisting of retailer and outlet as in fashion apparel market. The objective function consists of revenue terms (sales revenue and salvage value) and purchasing cost term. Specifically, decisions on price markdowns and order quantity are made to maximize total profit in the supply chain so as to have zero inventory level at the end of the sales horizon. To solve the proposed problem, a gradient method is applied, which shows an optimal decision on both the initial inventory level and the discount pricing policy. Sensitivity analysis is conducted on the demand parameters and the final comments on the practical use of the proposed model are presented.

• Communications for Statistical Applications and Methods
• /
• v.10 no.1
• /
• pp.153-166
• /
• 2003

This study presents the time-divided forecasting model to integrate evolutionary optimization algorithm and change point detection based on artificial neural networks (ANN) for the prediction of (Korea) stock price index. The genetic algorithm(GA) is introduced as an evolutionary optimization method in this study. The basic concept of the proposed model is to obtain intervals divided by change points, to identify them as optimal or near-optimal change point groups, and to use them in the forecasting of the stock price index. The proposed model consists of three phases. The first phase detects successive change points. The second phase detects the change-point groups with the GA. Finally, the third phase forecasts the output with ANN using the GA. This study examines the predictability of the proposed model for the prediction of stock price index.