Effective Electric Vehicles Navigation Strategy Considering the Uncertainty of the Charging Load

With the increased penetration level of electric vehicles (EV), there is a virtual issue to address the uncertainty of EVs. Under the premise of uncertain information, how to maximize the revenue of charging stations (CSs) by guiding the EVs' charging behavior is the concern of this paper. In this paper, long short-term memory neural network has been used to forecast the charging load of the CSs, and the model predictive control (MPC) method is combined to formulate an effective two-stage energy scheduling strategy for CSs. n order to better motivate electric vehicles to achieve the corresponding CS, this paper constructs an incentive subsidy model, which effectively guides the EVs' charging behavior by changing the service price of the station. In the day-ahead phase, CSs trade with the grid based on forecast information. In the day-ahead market, energy is purchased at a lower price through the trading pool; in the real-time stage, by changing the price of charging services, price incentives are given to EVs, guiding electric vehicles to transfer between stations, and changing EVs at each station. load, thereby further compensating for the deviation of the charging load to reduce the cost of CSs. The effectiveness and economy of the two-stage EV navigation strategy based on incentive price is verified by experimental results.