.png){kind=icon}
.png){kind=icon}
Return
A data-driven framework for medium-term electric vehicle charging demand forecasting
.png){kind=icon}
OA
AI
DOI：10.1016/j.egyai.2023.100267.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The rapid phase-in of electric vehicles (EV) will cause unprecedented issues with managing the supply of electricity and charging stations. It is in the interest of utility providers and everyday consumers to be able to plan for peak charging times, and related congestion. While past work has been done for localized, shortterm forecasting, it has not included longer term forecasting, or considered the relationships between multiple stations. Importantly, past work has also not offered a framework for dataset construction and evaluated different dataset features. We propose a methodology to forecast demand at public EV charging stations, and use it to explore the potential of data-driven models to predict demand up to one week in advance. Our strategy includes selecting parameters for formatting a dataset given a list of charging events, a way to consider flexible prediction horizons, and deployment of deep and supervised learning-based models. To the best of our knowledge, ours is the first study to propose machine learning to forecast medium-term public EV charging demand, to exploit weather and other features at public charging stations, and to forecast demand at multiple stations and the entire network. We validated our approach using data from eleven stations over three years from Scotland, UK. Our method outperforms the benchmark time series method, and predicts network demand with a symmetric mean absolute percentage error (SMAPE) of 5.9% and a mean absolute error (MAE) of 124.7 kWh, or less than twelve percent of average daily demand.
Keywords:
Public EV charging
Forecasting
Energy consumption
Smart grid
Time-series
Multi-task learning
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.