Scalable probabilistic estimates of electric vehicle charging given observed driver behavior.

To prepare for rapid growth in global electric vehicle adoption, grid and policy planners depend on detailed forecasts of future charging demand. In this paper we propose a novel holistic, scalable, probabilistic framework to produce large-scale estimates of electric vehicle charging load for long-term planning that capture real drivers' charging patterns. Our framework captures the uncertainty and stochasticity in charging demand by taking a graphical modeling approach. It has three core elements: driver groups, charging segment choices, and charging session time and energy requirements. The framework uses hierarchical clustering to group drivers by their charging histories, capturing their heterogeneous behaviors and preferences across different segments or types of charging. The framework uses probabilistic mixture models for each driver group's sessions to identify the unique charging behaviors observed within each segment. We illustrate its application with a large data set from California, profiling the charging patterns and unique driver clusters it identifies. Using the model knobs representing drivers' battery capacities, behavior, and segment access we present scenarios for California's charging demand in 2030 with 8 million passenger electric vehicles. Peak charging demand ranged from 3.3 to 8.7 GW across scenarios. Each was calculated in under 45 s on a laptop computer. • Novel data-driven, graphical model framework for large-scale electric vehicle charging. • Hierarchical clustering of electric vehicle drivers by charging behavior histories. • Driver clusters highlight patterns for mixed use of multiple charging segments. • Distributions over driver groups and behaviors determine future charging demand. • Scenarios presented for charging of 8 million electric vehicles in California in 2030. [ABSTRACT FROM AUTHOR]