• Communications for Statistical Applications and Methods
• /
• v.29 no.6
• /
• pp.709-719
• /
• 2022

Recently, as the importance of environmental protection has emerged, interest in new and renewable energy is also increasing worldwide. In particular, the solar energy sector accounts for the highest production rate among new and renewable energy in Korea due to its infinite resources, easy installation and maintenance, and eco-friendly characteristics such as low noise emission levels and less pollutants during power generation. However, although climate prediction is essential since solar power is affected by weather and climate change, solar radiation, which is closely related to solar power, is not currently forecasted by the Korea Meteorological Administration. Solar radiation prediction can be the basis for establishing a reasonable new and renewable energy operation plan, and it is very important because it can be used not only in solar power but also in other fields such as power consumption prediction. Therefore, this study was conducted for the purpose of improving the accuracy of solar radiation. Solar radiation was predicted by a total of three weather variables, temperature, humidity, and cloudiness, and solar radiation outside the atmosphere, and the results were compared using various models. The CatBoost model was best obtained by fitting and comparing the Boosting series (XGB, CatBoost) and RNN series (Simple RNN, LSTM, GRU) models. In addition, the results were further improved through Time series cross-validation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.4
• /
• pp.932-938
• /
• 2017

This paper presents the structure of an energy management system for distributed energy resources of a grid-connected microgrid. The energy management system of a grid-connected microgrid collects information of the microgrid such as the status of distributed energy resources and the time varying pricing plan through various protocols. The energy management system performs forecasting and optimization based on the collected information. It derives the operation schedule of distributed energy resources to reduce the microgrid electricity bill. In order to achieve optimal operation, the energy management system should include an optimal scheduling algorithm and a protocol that transfers the derived schedule to distributed energy resources. The energy management system operates as a rolling horizon controller in order to reduce the effect of a prediction error. Derived control schedules are transmitted to the distributed energy resources in real time through the international standard communication protocol.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1957-1980
• /
• 2021

The significant aim of this research has always been to evaluate the mechanism for efficient and inherently aware usage of vitality in-home devices, thus improving the information of smart metering systems with regard to the usage of selected homes and the time of use. Advances in information processing are commonly used to quantify gigantic building activity data steps to boost the activity efficiency of the building energy systems. Here, some smart data mining models are offered to measure, and predict the time series for energy in order to expose different ephemeral principles for using energy. Such considerations illustrate the use of machines in relation to time, such as day hour, time of day, week, month and year relationships within a family unit, which are key components in gathering and separating the effect of consumers behaviors in the use of energy and their pattern of energy prediction. It is necessary to determine the multiple relations through the usage of different appliances from simultaneous information flows. In comparison, specific relations among interval-based instances where multiple appliances use continue for certain duration are difficult to determine. In order to resolve these difficulties, an unsupervised energy time-series data clustering and a frequent pattern mining study as well as a deep learning technique for estimating energy use were presented. A broad test using true data sets that are rich in smart meter data were conducted. The exact results of the appliance designs that were recognized by the proposed model were filled out by Deep Convolutional Neural Networks (CNN) and Recurrent Neural Networks (LSTM and GRU) at each stage, with consolidated accuracy of 94.79%, 97.99%, 99.61%, for 25%, 50%, and 75%, respectively.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.1
• /
• pp.70.1-70.1
• /
• 2014

We study the origin and acceleration mechanism of solar energetic particles (SEPs), which are one of the major causes of hazardous impacts in the space weather. By adopting the velocity dispersion to the multi-channel energy band observations from SOHO/ERNE and Wind/3DP, we estimate the onset time for each energy band and investigate coronal structure and CME's dynamics associated with the SEPs. Through this study we will find clues to answer the questions about the origin and acceleration of SEPs as well as their associated with flare and/or CMEs. We will apply our findings to improve the forecasting system of the solar radiation storms.

• Annual Conference of KIPS
• /
• 2012.04a
• /
• pp.1085-1087
• /
• 2012

현재 급격한 화석 에너지의 사용 증가로 인해 자원이 고갈되고 있으며, 심각한 환경오염의 문제가 발생하고 있다. 이러한 화석 에너지의 문제점 때문에 무공해이면서 자원 량이 무한에 가까운 신재생 에너지가 거론되고 있는데, 그 중에서 경제적인 면과 기술력이 가장 발전한 풍력 에너지가 각광 받고 있다. 하지만 풍력 발전은 풍속이 짧은 시간 안에 급격한 변화를 일으켜 풍력 터빈의 손상을 초래하며 정확한 풍력발전량의 예측이 힘들어 전력 생산량이 불규칙하다. 그리하여 전력의 공급과 수요의 균형을 위해 풍력발전량의 정확한 예측이 필요하다. 따라서 이 연구에서는 ANFIS을 적용하고 전력 생산 변화의 빠르기 PRR을 이용하여 풍력발전량을 예측하였다. 실험에서는 ANFIS기법에 PRR속성을 이용하여 단순한 ANFIS 기법 보다 더 정확한 풍력 발전량의 예측 결과를 얻을 수 있었다.

• International journal of advanced smart convergence
• /
• v.7 no.1
• /
• pp.42-47
• /
• 2018

Recently, as the demand for limited resources continues to rise and problems of resource depletion rise worldwide, the importance of renewable energy is gradually increasing. In order to solve these problems, various methods such as energy conservation and alternative energy development have been suggested, and biogas, which can utilize the gas produced from biomass as fuel, is also receiving attention as the next generation of innovative renewable energy. New and renewable energy using biogas is an energy production method that is expected to be possible in large scale because it can supply energy with high efficiency in compliance with energy supply method of recycling conventional resources. In order to more efficiently produce and manage these biogas, a biogas plant has emerged. In recent years, a large number of biogas plants have been installed and operated in various locations. Organic wastes corresponding to biogas production resources in a biogas plant exist in a wide variety of types, and each of the incoming raw materials is processed in different processes. Because such a process is required, the case where the biogas plant process is inefficiently operated is continuously occurring, and the economic cost consumed for the operation of the biogas production relative to the generated biogas production is further increased. In order to solve such problems, various attempts such as process analysis and feedback based on the feedstock have been continued but it is a passive method and very limited to operate a medium/large scale biogas plant. In this paper, we propose "CNN-based production yield prediction algorithm for increasing process efficiency of biogas plant" for efficient operation of biogas plant process. Based on CNN-based production yield forecasting, which is one of the deep-leaning technologies, it enables mechanical analysis of the process operation process and provides a solution for optimal process operation due to process-related accumulated data analyzed by the automated process.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.8 no.1
• /
• pp.46-52
• /
• 2005

A marine environmental information system (MEIS) useful for optimal route planning of ships running in the ocean was developed. Utilizing the simulated marine environmental data produced by the European Center for Medium-Range Weather Forecasts based on global environmental data observed by satellites, the real-time forecast and long-term statistics of marine environments around planned and probable ship routes are provided. The MEIS consists of a land-based data acquisition and analysis system(MEIS-Center) and a onboard information display system(MEIS-Ship) for graphic description of marine information and optimal route planning of ships. Also, it uses of satellite communication system for data transfer. The marine environmental components of winds, waves, air pressures and storms are provided, in which winds are described by speed and direction and waves are expressed in terms of height, direction and period for both of wind waves and swells. The real-time information is characterized by 0.5° resolution, 10 day forecast in 6 hour interval and daily update. The statistic information of monthly average and maximum value expected for a return period is featured by 1.5° resolution and based on 15 year database. The MEIS-Ship include an editing tool for route simulation and the forecasting and statistic information on planned routes can be displayed in graph or table. The MEIS enables for navigators to design an optimal navigational route that minimizes probable risk and operational cost.

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.723-734
• /
• 2021

Wind energy is one of the rapidly developing renewable energies which is being developed and invested in response to climate change. As renewable energy policies and power plant installations are promoted, the supply of wind power in Korea is gradually expanding and attempts to accurately predict demand are expanding. In this paper, the ARIMA and ARIMAX models which are Time series techniques and the SVR, Random Forest and XGBoost models which are machine learning models were compared and analyzed to predict wind power generation in the Jeonnam and Gyeongbuk regions. Mean absolute error (MAE) and mean absolute percentage error (MAPE) were used as indicators to compare the predicted results of the model. After subtracting the hourly raw data from January 1, 2018 to October 24, 2020, the model was trained to predict wind power generation for 168 hours from October 25, 2020 to October 31, 2020. As a result of comparing the predictive power of the models, the Random Forest and XGBoost models showed the best performance in the order of Jeonnam and Gyeongbuk. In future research, we will try not only machine learning models but also forecasting wind power generation based on data mining techniques that have been actively researched recently.

• Journal of Energy Engineering
• /
• v.22 no.1
• /
• pp.1-7
• /
• 2013

This paper attempts to estimate the residential electricity demand function, using survey data of 521 households in Korea. As the residential electricity demand function provides us information on the pattern of consumer's electricity consumption, it can be usefully utilized in predicting the impact of policy variables such as electricity price and forecasting electricity demands. We apply least absolute deviation(LAD) estimation as a robust approach to estimating parameters. The results showed that price and income elasticities are -0.68 and 0.14 respectively, and statistically significant at the 10% levels. The price and income elasticities portray that residential electricity is price- and income-inelastic. This implies that the residential electricity is indispensable goods to human-being's life, thus the residential electricity demand would not be promptly adjusted to responding to price and/or income change.

• Journal of Environmental Policy
• /
• v.12 no.3
• /
• pp.97-122
• /
• 2013

The ARDL(Autoregressive Distributed Lag) method is employed analyzes the long-run equilibrium relationships among environmental pollution($CO_2$ emissions) per capita, income levels per capita, and energy consumption per capita. The error correction model is employed to analyze the short-term effects of income and energy consumption on $CO_2$ emissions. The Toda-Yammamoto method is employed for causal analysis among the three variables. The results show that income levels, energy consumption, and $CO_2$ emissions are cointegrated. We found the N type relationship between income and $CO_2$ emissions. Long-term elasticities of income and energy consumption with respect to $CO_2$ emission were greater than their short-term elasticities. There were a bilateral causality between energy consumption and $CO_2$ emissions. There was a unilateral causality from $CO_2$ emissions to income and from energy consumption to income not vice versa. Energy consumption can be an important variable to contribute to forecasting $CO_2$ emissions.