Abstract
The electric taxis (ETs) charging load is of great importance for the normal and the stable operation of power systems. A prediction model for the ET spatio-temporal charging load is proposed, which considers the drivers’ subjective decision-making and the ET travel patterns. First, an improved Gaussian mixture model with a genetic algorithm is developed based on the real ET data. Besides, a prospect theory based on the Dijkstra algorithm for choosing charging stations is put forward. Then, considering the ambient temperature, a calculation method for the remaining energy in the ET battery is utilized. Based on the refined travel patterns and the Monte Carlo method, the charging load in three scenarios are analyzed, which studies the influence of temperature. ET charging loads of different scales are obtained and the influence of charging load on the typical daily load profile is discussed. The simulation results show that the prediction models can combine the drivers’ psychology with the objective traveling time, and the average error between the real load and the predicted load is less than 1%.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
