Paper Title
Electricity Demand Forecast Error Mitigation in a Fast Charging Station

Abstract
The highlighted global energy crisis and environmental degradation have significantly boosted the development of electric vehicles(EVs), Compared to gasoline-powered vehicles, EVs can dramatically reduce the greenhouse gas emission, energy cost for drivers, and dependencies on imported petroleum. As the trend for electric vehicles is increasing day by day the load on power stations are also increasing. Due to this high-level uncertainty in EV it may bring about deleterious impacts to the electric grid. Therefore, an advanced system is needed to overcome this problem. Therefore, in this paper we proposed an advanced demand forecast method which can calculate the expected EV charging load in FCSs. If we are able to predict the approaching vehicles, we can ensure the energy needed for the same. Firstly, the wavelet transform (WT) method and long short-term memory (LSTM) neural network are combined to predict the non-stationary traffic flow (TF). Then, a queuing theory-based model is developed to convert the predicted TF to the expected EV charging demand in FCS by considering charging service limitations and driver behaviors. Keywords - Electric Vehicle, Fast Charging Station, Energy Storage System