Search

• A deep learning approach to predicting the electric vehicle (EV) charging demand. • A real-world large EV trajectory dataset was used for model training and validation. • The deep learning approach outperformed traditional time series prediction models. • Input data structures, and sample sizes were not influential to prediction accuracy. Short-term prediction of the Electric Vehicle (EV) charging demand is of great importance to the operation of EV fleets and charging stations. This paper develops a Long Short-Term Memory (LSTM) neural network to predict the EV charging demand at the station level for the next few hours (e.g., 1–5 h), using a unique trajectory dataset containing over 76,000 private EVs in Beijing in January 2018. To explore the performance of the LSTM model, we set up four scenarios by 1) comparing LSTM against two typical time series prediction models, i.e., the Auto-Regressive Moving Average model (ARIMA), and the Multiple Layer Perceptron model (MLP), 2) and investigating how different input data structures, sample sizes, and time spans and intervals would influence model accuracy. The results suggest that the LSTM model outperformed the ARIMA, and MLP models, and their MAPE1 values are 6.83 %, 21.58 %, and 18.31 %, respectively. In addition, we find that the time span and interval tend to be more influential to the LSTM model's prediction accuracy than input data structures, and sample sizes. In general, the LSTM model with a shorter time span or interval (e.g., 1 h) would perform better. [ABSTRACT FROM AUTHOR]

• The capacity optimization model of the integrated photovoltaic- energy storage-charging station was built. • The case study bases on the data of 21 charging stations in Beijing. • The construction of the integrated charging station shows the maximum economic and environment benefit in hospital and minimum in residential. • A decline in energy storage costs increases the benefits of all-scale investments, an increase in electric vehicles promotes the benefits of small-scale investments, expansion of the peak-to-valley price distance increases the benefits of large-scale investments. The coupled photovoltaic-energy storage-charging station (PV-ES-CS) is an important approach of promoting the transition from fossil energy consumption to low-carbon energy use. However, the integrated charging station is underdeveloped. One of the key reasons for this is that there lacks the evaluation of its economic and environmental benefits. Based on the electricity load of different types of buildings and the data of electric vehicle charging stations in Beijing, this paper analyzes the economic and environmental benefits of integrated charging station developed over different scales by the capacity optimization model. Said benefits are shown to differ considerably with different locations (building types): the construction of the integrated charging station in places where the electricity load is high at night, and where the curve of daytime electricity consumption is consistent with the PV generation curve (e.g., hospitals), shows maximal economic benefits and carbon dioxide emissions reduction. In other (e.g., residential) areas, where power consumption is lower across both day and nighttime hours, the economic benefits and carbon dioxide emissions reduction are lowest. The economic and environmental benefits of the integrated charging station also markedly differ on different scales: with scale expansion, the rate of return on investment and the carbon dioxide emissions reduction first increase and then decrease. A decline in energy storage costs increases the economic benefits of all integrated charging station scales, an increase in EVs increases the economic benefits of small-scale investments, and expansion of the peak-to-valley price difference increases the economic benefits of large-scale investments. [ABSTRACT FROM AUTHOR]