• New & Renewable Energy
• /
• v.19 no.4
• /
• pp.98-107
• /
• 2023

A study was conducted to analyze data from 1981 to 2020 for understanding the impact of climate on solar energy generation. A significant increase of 104.6 kWhm^-2 was observed in the annual cumulative solar radiation over this period. Notably, the distribution of solar radiation shifted, with the solar radiation in Busan rising from the seventh place in 1981 to the second place in 2020 in South Korea. This study also examined the correlation between long-term temperature trends and solar radiation. Areas with the highest solar radiation in 2020, such as Busan, Gwangju, Daegu, and Jinju, exhibited strong positive correlations, suggesting that increased solar radiation contributed to higher temperatures. Conversely, regions like Seosan and Mokpo showed lower temperature increases due to factors such as reduced cloud cover. To evaluate the impact on solar energy production, simulations were conducted using climate data from both years. The results revealed that relying solely on historical data for solar energy predictions could lead to overestimations in some areas, including Seosan or Jinju, and underestimations in others such as Busan. Hence, considering long-term climate variability is vital for accurate solar energy forecasting and ensuring the economic feasibility of solar projects.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.163-165
• /
• 1996

In this paper, we are proposed development of electric energy method and load curve. A daily electric energy is forecasted using artificial neural network. The load curve is obtained by combining forecasted electric energy and typical daily load patterns which are classified using KSOM and Fuzzy system. As a result, we know that we could get more accurate results and easier application than the results from based on the hourly historical data.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.379-391
• /
• 2024

To meet increasing traffic requirements in mobile networks, small base stations (SBSs) are densely deployed, overlapping existing network architecture and increasing system capacity. However, densely deployed SBSs increase energy consumption and interference. Although these problems already exist because of densely deployed SBSs, even more SBSs are needed to meet increasing traffic demands. Hence, base station (BS) switching operations have been used to minimize energy consumption while guaranteeing quality-of-service (QoS) for users. In this study, to optimize energy efficiency, we propose the use of deep reinforcement learning (DRL) to create a BS switching operation strategy with a traffic prediction model. First, a federated long short-term memory (LSTM) model is introduced to predict user traffic demands from user trajectory information. Next, the DRL-based BS switching operation scheme determines the switching operations for the SBSs using the predicted traffic demand. Experimental results confirm that the proposed scheme outperforms existing approaches in terms of energy efficiency, signal-to-interference noise ratio, handover metrics, and prediction performance.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.2
• /
• pp.21-25
• /
• 2023

The purpose of this study was to compare the performance using multiple regression models to predict the energy consumption of steel industry. Specific independent variables were selected in consideration of correlation among various attributes such as CO2 concentration, NSM, Week Status, Day of week, and Load Type, and preprocessing was performed to solve the multicollinearity problem. In data preprocessing, we evaluated linear and nonlinear relationships between each attribute through correlation analysis. In particular, we decided to select variables with high correlation and include appropriate variables in the final model to prevent multicollinearity problems. Among the many regression models learned, Boosted Decision Tree Regression showed the best predictive performance. Ensemble learning in this model was able to effectively learn complex patterns while preventing overfitting by combining multiple decision trees. Consequently, these predictive models are expected to provide important information for improving energy efficiency and management decision-making at steel industry. In the future, we plan to improve the performance of the model by collecting more data and extending variables, and the application of the model considering interactions with external factors will also be considered.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.161-171
• /
• 2019

Varied methods have been researched continuously because the past as the daily maximum electricity demand expectation has been a crucial task in the nation's electrical supply and demand. Forecasting the daily peak electricity demand accurately can prepare the daily operating program about the generating unit, and contribute the reduction of the consumption of the unnecessary energy source through efficient operating facilities. This method also has the advantage that can prepare anticipatively in the reserve margin reduced problem due to the power consumption superabundant by heating and air conditioning that can estimate the daily peak load. This paper researched a model that can forecast the next day's daily peak load when considering the influence of temperature and weekday, weekend, and holidays in the Seasonal ARIMA, TBATS, Seasonal Reg-ARIMA, and NNETAR model. The results of the forecasting performance test on the model of this paper for a Seasonal Reg-ARIMA model and NNETAR model that can consider the day of the week, and temperature showed better forecasting performance than a model that cannot consider these factors. The forecasting performance of the NNETAR model that utilized the artificial neural network was most outstanding.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.1
• /
• pp.3-8
• /
• 2017

In this study future wind resource maps have been produced under climate change scenario using ensemble regional climate model weather research and forecasting(WRF) for the period from 2045 to 2054(mid 21st century). Then various spatiotemporal analysis has been conducted in terms of monthly and diurnal. As a result, monthly variation(monsoon circulation) was larger than diurnal variation(land-sea circulation) throughout the South Korea. Strong wind area with high wind power energy was varied on months and regions. During whole years, strong wind with high wind resource was pronounced at cold(warm) months in particular Gangwon mountainous and coastal areas(southwestern coastal area) driven by strong northwesterly(southwesterly). Projected strong and weak wind were presented in January and September, respectively. Diurnal variation were large over inland and mountainous area while coastal area were small. This new monthly and diurnal variation would be useful to high resource area analysis and long-term operation of wind power according to wind variability in future.

• Journal of Korean Society for Atmospheric Environment
• /
• v.32 no.1
• /
• pp.82-99
• /
• 2016

This study was carried out to understand the regional contribution of Particulate Matter (PM) emissions from East Asia ($82^{\circ}{\sim}149^{\circ}E$, $18^{\circ}{\sim}53^{\circ}N$) to Seoul during high concentration period in February 2014. The Community Multi-scale Air Quality (CMAQ) version 5.0.2 with Decoupled Direct Method (DDM) was used to analyze levels of contributions over Seoul. In order to validate model performance of the CMAQ, predicted PM and its chemical species concentrations were compared to observations in China and Seoul. Model predictions could depict the daily and hourly variations of observed PM. The calculated PM concentrations, however, had a tendency of underestimation. The discrepancies are due to uncertainties of meteorological data, emission inventories and CMAQ model itself. The high PM concentration in Seoul was induced by stationary anticyclone over the West Coast of Korea during 24 to 27 February. The DDM in CMAQ was used to analyze the contributions of emissions from East Asia on Seoul during this PM episode. $PM_{10}$ concentration in Seoul is contributed by 39.77%~53.19% from China industrial and urban region, 15.37%~37.10% from South Korea, and 9.03%~18.05% North Korea. These indicate that $PM_{10}$ concentrations in Seoul during the episode period are dominated by long-range transport from China region as well as domestic sources. It was also found that the largest contribution region in China were Shandong peninsula during the PM event period.

• Nuclear Engineering and Technology
• /
• v.50 no.1
• /
• pp.68-79
• /
• 2018

The Ki-Jang research reactor (KJRR), a new research reactor in Korea, is being planned to fulfill multiple purposes. In this study, as an assessment of the environmental radiological impact, we characterized the atmospheric dispersion and deposition of radioactive materials released by an unexpected incident at KJRR using the weather research and forecasting-mesoscale model interface program-California Puff (WRF-MMIF-CALPUFF) model system. Based on the reproduced three-dimensional gridded meteorological data obtained during a 1-year period using WRF, the overall meteorological data predicted by WRF were in agreement with the observed data, while the predicted wind speed data were slightly overestimated at all stations. Based on the CALPUFF simulation of atmospheric dispersion (${\chi}/Q$) and deposition (D/Q) factors, relatively heavier contamination in the vicinity of KJRR was observed, and the prevailing land breeze wind in the study area resulted in relatively higher concentration and deposition in the off-shore area sectors. We also compared the dispersion characteristics between the PAVAN (atmospheric dispersion of radioactive release from nuclear power plants) and CALPUFF models. Finally, the meteorological conditions and possibility of high doses of radiation for relatively higher hourly ${\chi}/Q$ cases were examined at specific discrete receptors.

• Korean System Dynamics Review
• /
• v.10 no.3
• /
• pp.105-124
• /
• 2009

The situation of the global food markets has been being rapidly restructured and entering on a new phase by new dynamic and driving forces. The factors such as economic growth and income increase, high energy price, globalization, urbanization, and global climate change are transforming patterns of food consumption, production, and markets. The prices and markets of world food and energy are getting increasingly linked each other. Food and fuel are the global dilemma issues associated with the risk of diverting farmland or of consuming cereals for biofuel production in detriment of the cereals supply to the global food markets. An estimated 100 million tons of grain per year are being redirected from food to fuel. Therefore, the objectives of this study are as follows: Firstly, the study examines situations of the world food and energy resources, analyzes the trends of prices of the crude oil and biofuel, and formulates the food-energy links mechanism. Secondly, the study builds a simulation model, based on system dynamics approach, for not only analyzing the global cereals market and energy market but also forecasting the global production, consumption, and stock of those markets by 2030 in the future. The model of this study consists of four sectors, i.e., world population dynamics sector, global food market dynamics sector, global energy market dynamics sector, scenario sector of world economic growth and oil price.