• Journal of The Korean Society of Agricultural Engineers
• /
• v.50 no.4
• /
• pp.99-109
• /
• 2008

As the price of traditional fossil fuels continue to increase, more people attach importance to the pollution of the environment caused by fossil fuel's burning, developing and using renewable energy resources has become a very important project all over the world. Also, the rural energy planning which is another method to improve energy utilization ratio and reduce environment pollution, is also regarded as a very effective way to reduce the energy consumption. There is a quantity of renewable energy resources and natural tribes in rural area, which is both feasible to develop the renewable energy and the regional energy planning. To carry out this, it is needs to know the area's quantity of renewable energy resources and the total energy consumption. This paper is to find out the relationship between rural energy consumption and rural conditions, and to found a energy consumption model which can conjecture the energy consumption in rural family. and the cost of rural family's energy consumption was founded to conjecture how much money dose it cost in rural family's energy consumption. The energy consumption model was concluded using the surveys of 76 families in 14 villages at the area of Chungcheongbuk-Do(province). The main factors to energy consumption was selected out which were number of family members, acreage of house, acreage of farmland and family's annual income.

• 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.

• New & Renewable Energy
• /
• v.6 no.3
• /
• pp.13-21
• /
• 2010

This paper analyzes the factors of renewable energy consumption in Korea, China and Japan. We consider renewable energy consumption per capita as dependent variable, GDP per capita, $CO_2$ emissions per capita and real oil prices as independent variables. To analyze this model, this paper uses three econometric methods such as OLS, fixed effect model and panel GLS, utilizing data from 1990 to 2006 in Korea, China and Japan. According to the results by OLS for each country, an increase in GDP per capita or $CO_2$ emissions per capita or oil prices leads to an increase in renewable energy consumption. According to the results by fixed effect model, an increase in GDP per capita or $CO_2$ emissions per capita leads to an increase in renewable energy consumption. And real oil prices do not have a significant impacts on this model. According to the results by panel GLS, an increase in real GDP per capita as a proxy of income leads to an increase renewable energy consumption. And both $CO_2$ emissions per capita and real oil prices do not correlated closely with renewable energy consumption. Thus oil is not substituted to renewable energy in Northeast asian countries.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.10
• /
• pp.6799-6806
• /
• 2015

Electric energy consumption is always followed by the introduction of diversity scale-up and state-of-the-art equipments in logistic centers. In order to analyze the status and the characteristic of the electric energy consumption quantitatively, and also to evaluate the efficiency of the electric energy, this research aims to develop an estimation model of standard electric energy consumption for logistic centers. The proposed model applies the thermodynamics theory so as to effectively reflect the peculiarity that the temperature in the logistic center influences the electric energy consumption. And the model consists of the energy consumed by the refrigerator, which can be subdivided into the heat conducted through the wall, the heat convected by the open doors and the heat lost into the goods, and the electric consumption of the machinery equipments. The model also includes a variety of explanatory variables to support an operator of logistics centers in evaluating the efficiency of energy consumption and establishing improvement strategies for energy efficiency. Application of the model developed in this study is discussed with observed data on energy consumption of a logistics center.

• Journal of Energy Engineering
• /
• v.22 no.1
• /
• pp.38-43
• /
• 2013

There was a dire need to compile data about energy consumption data by use to analyze residential energy consumption patterns relating to changes in lifestyles, or changes in life behavior. Accordingly, bottom-up model for residential energy consumption by residential use was developed by life behavior classification in an attempt to analyze energy consumption. This paper multiplied each appliance's running times by each appliance by life behavior and built a residential bottoms-up model to figure out the energy consumption of each household. The uses by life behavior were broken down into lighting, heating, cooling, entertainment, obtaining information, hygiene, and cooking.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.6B
• /
• pp.316-324
• /
• 2007

In this paper we proposed an energy consumption model for IR-UWB wireless sensor networks. The model takes the advantages of PHY-MAC cross layer design, and we used slotted and un-slotted sleeping protocols to compare the energy consumption. We addressed different system design issues that are responsible to energy consumption and proposed an optimum model for the system design. We expect the slotted sleeping will consume less energy for bursty load than that of the un-slotted one. But if we consider latency, the un-slotted sleeping model performs better than the slotted sleeping case.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.1
• /
• pp.129-136
• /
• 2019

In this study, we proposed a model for forecasting power energy demand by investigating how outside temperature at a given time affected power consumption and. To this end, we analyzed the time series of power consumption in terms of the power spectrum and found the periodicities of one day and one week. With these periodicities, we investigated two time series of temperature and power consumption, and found, for a given hour, an approximate linear relation between temperature and power consumption. We adopted an exponential smoothing model to examine the effect of the linearity in forecasting the power demand. In particular, we adjusted the exponential smoothing model by using the variation of power consumption due to temperature change. In this way, the proposed model became a mixture of a time series model and a regression model. We demonstrated that the adjusted model outperformed the exponential smoothing model alone in terms of the mean relative percentage error and the root mean square error in the range of 3%~8% and 4kWh~27kWh, respectively. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric energy together with the outside temperature.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.26 no.8
• /
• pp.394-400
• /
• 2014

Several models and methods have been developed to verify the improvement of energy performance in retrofit buildings. The verification is important to confirm the effectiveness of new technologies or retrofits. Inverse model toolkit proposed by ASHRAE evaluates the changes of the energy performance of retrofit buildings by using actual energy consumption data. In this study, the inverse model toolkit was used to analyze heating and cooling energy performance of an office building. Analyzed coefficients of correlation of actual energy consumption with estimated energy consumption was above 0.92 and well fitted. It was confirmed that energy consumption of natural gas decreased by 43.4% and also that electricity decreased by 13.8%, after the retrofit of the case building. For the energy usage, cooling energy was increased by 7.4%, heating energy was decreased by 42.3%, hot water and cooking were increased by 3.4%, lighting and electronics were decreased by 19.3%, and the total energy was decreased by 18.9%.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.15 no.4
• /
• pp.287-293
• /
• 2003

This study examined the temperature-dependent regression model of energy consumption based on various measuring period. The methodology employed was to construct temperature-dependent linear regression model of daily energy consumption from one day to three months data-sets and to compare the annual heating energy consumption predicted by these models with actual annual heating energy consumption. Heating energy consumption from a building in Daejon was examined experimentally. From the results, predicted value based on one day experimental data can have error over 100%. But predicted value based on one week experimental data showed error over 30%. And predicted value based on over three months experimental data provides accurate prediction within 6% but it will be required very expensive.

• Asia-Pacific Journal of Business
• /
• v.14 no.4
• /
• pp.305-318
• /
• 2023

Purpose - This study analyzed the decoupling phenomenon between energy consumption and economic growth in Korea from 1990 to 2021. The main purpose of this study is to suggest policy implications for achieving a low-carbon society and decoupling that Korea must move forward in the face of the climate change crisis. Design/methodology/approach - This study investigated the relationship between energy consumption and economic growth by energy source and sector using the energy-EKC (EEKC) hypothesis which included the energy consumption on the traditional Environmental Kuznets Curve (EKC), and the impulse response function (IRF) model based on Bayesian vector auto-regression (BVAR). Findings - During the analysis period, the trend of decoupling of energy consumption and economic growth in Korea is confirmed starting from 1996. However, the decoupling tendency appeared differently depending on the differences in energy consumption by sources and fields. The results of the IRF model using data on energy consumption by source showed that the impact of GDP and renewable energy consumption resulted in an increase in energy consumption of bio and waste, but a decrease in energy consumption by sources, and the impact of trade dependence was found to increase the consumption of petroleum products. Research implications or Originality - According to the main results, efficient distribution by existing energy source is required through expansion of development of not only renewable energy but also alternative energy. Additionally, in order to increase the effectiveness of existing energy policies to achieve carbon neutrality, more detailed strategies by source and sector of energy consumption are needed.