BROWSE
Detail
Conference Paper
Pattern Analysis of the Time-Series Operational Data of Electric Vehicle Chargers in the Large-Scale Car Park
Cited 1 time in 
Share 
Share
- Authors
- J. Choi, W.-K. Park, C. Zheng
- Issue Date
- 2023-11
- Citation
- International Conference on Electric Vehicle and Vehicle Engineering (CEVVE) 2023, pp.1-4
- Language
- English
- Type
- Conference Paper
- Abstract
- The adoption of electric vehicles (EVs) continues to rise worldwide. Understanding the charging demand for EVs is crucial for charging stations to enable efficient management and resource planning. Policymakers and infrastructure companies also focus on the charging demand to secure public services, such as grid or transportation networks. Consequently, this study analyzes time-series operational data from EV chargers to provide insights into EV charging patterns. Temporal event records of EV chargers were obtained from a large-scale car park located in China. Two types of charging patterns were analyzed. First, different charging profiles of EVs were classified with respect to the types of cars and users. Second, general charging behaviors of EVs were identified on a daily and yearly basis. Additionally, a forecasting study was conducted by repeated hour-ahead forecasting over a one-year period. Statistical forecasting models, particularly the autoregressive integrated moving average (ARIMA) model, demonstrated acceptable forecasting performance. The result of this study would help introduce or enhance EV-related applications, such as vehicle-to-grid services or car navigation systems.
- KSP Keywords
- Autoregressive integrated moving average (ARIMA) model, Car navigation, Charging demand, EV charging, Forecasting model, Forecasting performance, Operational Data, Public Services, Statistical forecasting, Temporal event, Time series