• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.675-683
• /
• 2015

In the 21st century, we now face the serious problems of the enormous consumption of the energy resources. Depending on the power consumption increases, both China and South Korea face a reduction in available resources. This paper considers the regression models and time-series models to compare the performance of the forecasting accuracy based on Mean Absolute Percentage Error (MAPE) in order to forecast the electricity demand accurately on the short-term period (68 months) data in Northeast China and find the relationship with Korea. Among the models the support vector regression (SVR) model shows superior performance than time-series models for the short-term period data and the time-series models show similar results with the SVR model when we use long-term period data.

• New & Renewable Energy
• /
• 제18권3호
• /
• pp.1-9
• /
• 2022

This study analyzed the anticipated supply-and-demand of forest biomass energy (through wood pellets) until 2050, in South Korea. Comparing the utilization rates of forest resources of five countries (United Kingdom, Germany, Finland, Japan, and S. Korea), it was found that S. Korea does not nearly utilize its forest resources for energy purposes. The total demand for wood pellets in S. Korea (based on a power generation efficiency of 38%) was predicted to be 3,629 and 4,371 thousand tons in 2034 and 2050, respectively. The anticipated total wood pellet power generation ratio to target power consumption is 1.13% (5,745 GWh), 1.17% (6,336 GWh), and 1.25% (7,631 GWh) in 2020, 2030, and 2050, respectively. Low value-added forest residues left unattended in forests are called "Unused Forest Biomass" in S. Korea. From the analysis, the total annual potential amount of raw material, sustainably collectible amount, and available amount of wood pellet in 2050 were estimated to be 6,877, 4,814, and 3,370 thousand tons, respectively. The rate of contribution to Nationally Determined Contributions was up to 0.64%. Through this study, the authors found that forest biomass energy will contribute to a carbon neutral society in the near future at the national level.

• Korean Journal of Artificial Intelligence
• /
• 제12권1호
• /
• 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.

• Journal of Electrical Engineering and Technology
• /
• 제13권2호
• /
• pp.559-567
• /
• 2018

In this paper, we propose a new load forecasting method for smart air conditioning (A/C) based on the modified thermodynamics of indoor temperature and the unbiased finite memory estimator (UFME). Based on modified first-order thermodynamics, the dynamic behavior of indoor temperature can be described by the time-domain state-space model, and an accurate estimate of indoor temperature can be achieved by the proposed UFME. In addition, a reliable A/C load forecast can be obtained using the proposed method. Our study involves the experimental validation of the proposed A/C load forecasting method and communication construction between DR server and HEMS in a test bed. Through experimental data sets, the effectiveness of the proposed estimation method is validated.

• Journal of Industrial Technology
• /
• 제30권A호
• /
• pp.3-8
• /
• 2010

Recently, There have been many attempts to optimize energy usage in buildings and houses using Information Technology(IT) and the typical implementation can be found in Intelligent Building and Zero Energy Building. These kinds of buildings need to forecast the building loads, estimate the capacity requirement for power supply, and decide the capacity of the main transformer of the building. Currently, the capacity of the main transformer has been decided just using typical load estimation method not considering the load characteristics and patterns. In this paper, we propose a new load estimation method considering the load characteristics and patterns of the builiding. The proposed method was applied to actual mail center and verified the feasibility of application to actual design of buildings.

• Progress in Superconductivity and Cryogenics
• /
• 제17권2호
• /
• pp.18-24
• /
• 2015

Large wind turbine generators with high temperature superconductors (HTS) are in incessant development because of their advantages such as weight and volume reduction and the increased efficiency compared with conventional technologies. In addition, nowadays the wind turbine market is growing in a function of time, increasing the capacity and energy production of the wind farms installed and increasing the electrical power for the electrical generators installed. As a consequence, it is raising the wind power energy contribution for the global electricity demand. In this study, a forecast of wind energy development will be firstly emphasized, then it continue presenting a recent status of the technology development of large scale HTSG for wind power followed by an explanation of HTS wire trend, cryogenics cooling systems concept, HTS magnets field coil stability and other technological parts for optimization of HTS generator design - operating temperature, design topology, field coil shape and level cost of energy, as well. Finally, the most relevant projects and designs of HTS generators specifically for offshore wind power systems are also mentioned in this study.

• Journal of Energy Engineering
• /
• 제26권4호
• /
• pp.29-34
• /
• 2017

Factors of Zero-Energy Building are divided into active and passive factor. Passive factor means insulation, heat bridge of building like insulation, windows and doors, awning, outside etc. and active factor means energy output and efficiency coefficient. Energy output of active factor is achieved by new generating energy. This study anticipated how many effects will be produced when not new generating energy but Vehicle to Building; V2B, bi-directional charging and discharging technology, is applied to Zero-Energy Building. In new generating energy, power generation will be anticipated by geography and climate, but in V2B, several input variable like user's discharging intention and number of usable charger etc. should be considered. We can check how much V2B contribute to the Zero-Energy Building by anticipated results, and that results should be anticipated by using probabilitic method because there is few statistical data. This study anticipate change of charging and discharging pattern, based by Demand Response slot, by using monte carlo method among the probabilitic methods.

• Journal of the Korean Institute of Gas
• /
• 제24권6호
• /
• pp.34-46
• /
• 2020

In order to supply stable natural gas in the future, it is necessary to forecast the demand in advance and secure the quantity of supply. In this paper, we propose a method of estimating the demand function of industrial natural gas, which is the core of the increase of domestic natural gas demand in the future. The cross-sectional data of 304 domestic industries were used to estimate the demand function of the industrial natural gas, and the effect of industry specific characteristics such as capital investment, manufacturing cost. Finally, the least absolute deviation estimation method which is robust to outliers and does not assume the homogeneity of the error term and the normality, And the results were derived. In addition, the economic value of industrial city gas was estimated using the price elasticity of industrial city gas. Therefore, it can be seen that the continuous expansion and supply of city gas to the industrial sector is beneficial at the national level, and the government needs to promote expansion through the industrial city gas support policy.

• The Korean Journal of Applied Statistics
• /
• 제36권1호
• /
• pp.49-62
• /
• 2023

Solar energy, which is rapidly increasing in proportion, is being continuously developed and invested. As the installation of new and renewable energy policy green new deal and home solar panels increases, the supply of solar energy in Korea is gradually expanding, and research on accurate demand prediction of power generation is actively underway. In addition, the importance of solar radiation prediction was identified in that solar radiation prediction is acting as a factor that most influences power generation demand prediction. In addition, this study can confirm the biggest difference in that it attempted to predict solar radiation using medium-term forecast weather data not used in previous studies. In this paper, we combined the multi-linear regression model, KNN, random fores, and SVR model and the clustering technique, K-means, to predict solar radiation by hour, by calculating the probability density function for each cluster. Before using medium-term forecast data, mean absolute error (MAE) and root mean squared error (RMSE) were used as indicators to compare model prediction results. The data were converted into daily data according to the medium-term forecast data format from March 1, 2017 to February 28, 2022. As a result of comparing the predictive performance of the model, the method showed the best performance by predicting daily solar radiation with random forest, classifying dates with similar climate factors, and calculating the probability density function of solar radiation by cluster. In addition, when the prediction results were checked after fitting the model to the medium-term forecast data using this methodology, it was confirmed that the prediction error increased by date. This seems to be due to a prediction error in the mid-term forecast weather data. In future studies, among the weather factors that can be used in the mid-term forecast data, studies that add exogenous variables such as precipitation or apply time series clustering techniques should be conducted.

• Journal of Korea Multimedia Society
• /
• 제19권8호
• /
• pp.1530-1537
• /
• 2016

Recently, solar power generation shows the significant growth in the renewable energy field. Using the short-term prediction, it is possible to control the electric power demand and the power generation plan of the auxiliary device. However, a short-term prediction can be used when you know the weather forecast. If it is not possible to use the weather forecast information because of disconnection of network at the island and the mountains or for security reasons, the accuracy of prediction is not good. Therefore, in this paper, we proposed a system capable of short-term prediction of solar power generation amount by using only the weather information that has been collected by oneself. We used temperature, humidity and insolation as weather information. We have applied a moving average to each information because they had a characteristic of time series. It was composed of min, max and average of each information, differences of mutual information and gradient of it. An artificial neural network, SVM and RBF Network model was used for the prediction algorithm and they were combined by Ensemble method. The results of this suggest that using a moving average during pre-processing and ensemble prediction models will maximize prediction accuracy.