• Journal of Korean Society of Transportation
• /
• v.35 no.3
• /
• pp.210-219
• /
• 2017

Electric vehicles, which are attracting attention as eco-friendly vehicles, have been increasing in number since 2011 in Korea. The purpose of this study is to analyze the efficient operation of existing charging stations and factors to consider when installing additional charging stations based on the case of Jeju Island where the electric vehicle penetration rate is high and the charging infrastructure is relatively well established. The characteristics of using electric car charging stations by region, type of facility, and time of day are analyzed. As a result of analyzing the frequency of using the charger installed in Jeju Island, the utilization of both the fast charger and the slow charger is found to be concentrated in a specific area. The usage rate of charger installed in a business facility and a public parking lot is high in both fast charger and slow charger. However, according to the usage rate by time of day, the fast charger has a high utilization rate throughout the afternoon, while the use of a slow charger is concentrated in the morning. In order to enable users to utilize the electric vehicle charging station efficiently, it is necessary to provide a publicity guide for the charging station having a low utilization rate, a notice for using the charger, and a notification of completion of charging. Considering the charging demand, the area where the charger is not yet installed should be considered as the area to install the charger, and in addition, the additional installation should be considered in the area and the facility where the amount of charge is large. Service improvement is expected to be possible by utilizing actual electric vehicle charging behavior analysis result.

• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.57-69
• /
• 2022

Even though demand to charge EV(electric vehicles) is increasing, there are some problems to construct EV charging stations and problems from deficient them. Typical problem of EV charging stations is discordance for EV charging station location with its demand. This study investigates methods to determine the optimized location for fast EV charging stations considering charging demand in Seoul. Firstly, variables influencing on determination of determine the optimized location for fast EV charging stations were decided, and then evaluation of weights of the variables and data collection were conducted. Using the weights, location potential scores for each area-cell were calculated and optimized locations for fast EV charging stations were resulted.