A clustering-based approach to scenario-driven planning for EV charging with autonomous mobile chargers

The main goal of this paper is long-term planning for electric vehicle (EV) charging infrastructure using autonomous mobile chargers (AMCs). The proposed method employs a clustering-based strategy to group EVs based on similar charging patterns, thereby reducing the number of scenarios and simplifying the planning problem. This reduces the number of possible scenarios and simplifies the planning problem. Each cluster then undergoes a short-term scheduling process to determine the optimal allocation of AMCs among its EVs. The program evaluates the probability of each scenario as well as the corresponding time results. Eventually, it formulates an ideal long-term strategy for the deployment and operation of AMC. This plan incorporates the concept of confidence level to address uncertainty in forecasting vehicle behavior and charging requirements. It ensures that the number and capacity of chargers are sufficient to meet system requirements at various confidence levels. The concept of confidence level strikes a balance between the cost of deploying mobile chargers and the risk of failing to satisfy the charging demand. This approach leads to optimal and reliable planning for EV charging infrastructure. •Introduction of a novel strategy employing autonomous EV mobile chargers.•Utilizing constant power charging in mobile chargers to reduce the number of chargers.•Applying clustering algorithms to group EV charging data and identify distinct patterns for better charger management.•Application of PCA and k-means clustering to simplify the data for more effective EV pattern recognition.•Clustering and scheduling algorithms optimize charger assignment, reduce idle time, lower costs, and improve EV charging.