Stacking regression technology with event profile for electric vehicle fast charging behavior prediction

Large-scale deployment of electric vehicles (EVs) poses a huge challenge to the operation of the distribution network. As a possible mobile energy carrier, the interaction between EVs and distribution networks can provide some opportunities for power operation. Where to charge and how to charge have become an important research topic in EV charging scheduling. Previous studies mainly focused on slow-charging behavior analysis rather than fast-charging behavior. Here, we provide an in-depth understanding of EV user fast-charging behavior in public stations based on more than 220,000 real-world charging records with the Variational-Bayesian Gaussianmixture model. Characteristics related to charging energy and charging duration are mainly considered in the cluster model, especially dwelling duration after charging is taken into account to better support the decision of charging recommendation strategy and charging power allocation. Inspired by the future application scenario of the charging behavior cluster of previous studies, we propose a charging behavior prediction framework considering behavior catalogues with stacking regression technology. The results show that the proposed framework improves the prediction accuracy of charging behavior and can effectively evaluate the priority of charging behavior.

Automated summary

The large-scale deployment of electric vehicles presents challenges to the distribution network, but also provides opportunities for power operation. Previous research on EV charging scheduling focused on slow-charging behavior, neglecting fast-charging behavior. This study provides an in-depth understanding of EV user fast-charging behavior in public stations using a Variational-Bayesian Gaussian mixture model. Charging energy, duration, and dwelling duration after charging are considered in the cluster model to support charging recommendation strategy and power allocation decision. Inspired by previous studies, a charging behavior prediction framework is proposed that improves prediction accuracy and priority evaluation.