• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.933-940
• /
• 2018

The conversion of the internal combustion engine vehicle to the electric vehicle is suggested as a solution to the problem of global climate change and environmental pollution. Accordingly, this study was started to promote the use of electric vehicles. The purpose of this study is to identify the basic background knowledge and current status of electric vehicles in Korea and abroad, and expand from previous understanding on which factors affect ones choice on electric vehicles by considering individual characteristics and context in detail. In the analysis, a set of demand forecasting models were constructed by grouping the respondents based on the household characteristics as well as the vehicle ownership. At the time in need for better understanding of the feasibility of electric vehicles, it is expected that the research can assist the promotion of electric vehicles. In the follow-up study, I would like to continue the research on the activation of electric vehicles.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.5
• /
• pp.113-123
• /
• 2011

Recently, the global warming problem has arised around world, many nations has set up a various regulations for decreasing $CO_2$. In particular, $CO_2$ emissions reduction effect is very powerful in transport part, so there is a rising interest about development of green car, or electric vehicle in auto industry. For this reason, it is important to make a strategy for charging infra and forcast electric power demand, but it hasn't introduced about demand forecasting electric vehicle. Thus, this paper presents a demand forecasting for electric vehicles using choice based multigeneration diffusion model. In this paper, it estimates innovation coefficient, immitation coefficient in Bass model by using hybrid car market data and forecast electric vehicle market by year using potential demand market through SP(Stated Preference) experiment. Also, It facilitates more accurate demand forecasting electric vehicle market refelcting multigeneration diffusion model in accordance with attribute progress in development of electric vehicle. Through demand forecasting methodology in this paper, it can be utilized power supply and building a charging infra in the future.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.119-127
• /
• 2020

As the electric vehicle (EV) market in South Korea grows, it is required to expand charging facilities to respond to rapidly increasing EV charging demand. In order to conduct a comprehensive facility planning, it is necessary to forecast future demand for electricity and systematically analyze the impact on the load capacity of facilities based on this. In this paper, we design and develop a Long Short-Term Memory (LSTM) neural network model that predicts the daily peak electric load at each charging station using the EV charging data of KEPCO. First, we obtain refined data through data preprocessing and outlier removal. Next, our model is trained by extracting daily features per charging station and constructing a training set. Finally, our model is verified through performance analysis using a test set for each charging station type, and the limitations of our model are discussed.