TY - JOUR
T1 - Day-Ahead Forecast of Electric Vehicle Charging Demand with Deep Neural Networks
AU - Van Kriekinge, Gilles
AU - De Cauwer, Cedric
AU - Sapountzoglou, Nikolaos
AU - Coosemans, Thierry
AU - Messagie, Maarten
PY - 2021/10/3
Y1 - 2021/10/3
N2 - The increasing penetration rate of electric vehicles, associated with a growing charging demand, could induce a negative impact on the electric grid, such as higher peak power demand. To support the electric grid, and to anticipate those peaks, a growing interest exists for forecasting the day-ahead charging demand of electric vehicles. This paper proposes the enhancement of a state-of-the-art deep neural network to forecast the day-ahead charging demand of electric vehicles with a time resolution of 15 min. In particular, new features have been added on the neural network in order to improve the forecasting. The forecaster is applied on an important use case of a local charging site of a hospital. The results show that the mean-absolute error (MAE) and root-mean-square error (RMSE) are respectively reduced by 28.8% and 19.22% thanks to the use of calendar and weather features. The main achievement of this research is the possibility to forecast a high stochastic aggregated EV charging demand on a day-ahead horizon with a MAE lower than 1 kW.
AB - The increasing penetration rate of electric vehicles, associated with a growing charging demand, could induce a negative impact on the electric grid, such as higher peak power demand. To support the electric grid, and to anticipate those peaks, a growing interest exists for forecasting the day-ahead charging demand of electric vehicles. This paper proposes the enhancement of a state-of-the-art deep neural network to forecast the day-ahead charging demand of electric vehicles with a time resolution of 15 min. In particular, new features have been added on the neural network in order to improve the forecasting. The forecaster is applied on an important use case of a local charging site of a hospital. The results show that the mean-absolute error (MAE) and root-mean-square error (RMSE) are respectively reduced by 28.8% and 19.22% thanks to the use of calendar and weather features. The main achievement of this research is the possibility to forecast a high stochastic aggregated EV charging demand on a day-ahead horizon with a MAE lower than 1 kW.
KW - aggregated charging demand
KW - recurrent neural network
KW - feature importance
KW - electric vehicle
KW - day-ahead forecast
UR - http://www.scopus.com/inward/record.url?scp=85116865429&partnerID=8YFLogxK
U2 - 10.3390/wevj12040178
DO - 10.3390/wevj12040178
M3 - Article
VL - 12
JO - World Electric Vehicle Journal
JF - World Electric Vehicle Journal
SN - 2032-6653
IS - 4
M1 - 178
ER -