DiffCharge: Generating EV Charging Scenarios via a Denoising Diffusion Model

TL;DR

DiffCharge is a novel diffusion-based model that generates realistic EV charging scenarios, capturing temporal correlations and station-specific features, aiding grid management amid uncertain EV charging behaviors.

Contribution

The paper introduces DiffCharge, a diffusion model that synthesizes diverse, realistic EV charging profiles with temporal and station-specific features, improving scenario generation for grid planning.

Findings

Outperforms existing methods on real-world datasets

Effectively captures temporal and station-specific features

Enhances EV integration in power grids

Abstract

Recent proliferation of electric vehicle (EV) charging events has brought prominent stress over power grid operation. Due to the stochastic and volatile EV charging behaviors, the induced charging loads are extremely uncertain, posing modeling and control challenges for grid operators and charging management. Generating EV charging scenarios would aid via synthesizing a myriad of realistic charging scenarios. To this end, we propose a novel denoising Diffusion-based Charging scenario generation model DiffCharge, which is capable of generating a broad variety of realistic EV charging profiles with distinctive temporal properties. It is able to progressively convert the simply known Gaussian noise to genuine charging time-series data, by learning a parameterized reversal of a forward diffusion process. Besides, we leverage the multi-head self-attention and prior conditions to capture the temporal correlations and unique information associated with EV or charging station types in real charging profiles. Moreover, We demonstrate the superiority of DiffCharge on extensive real-world charging datasets, as well as the efficacy on EV integration in power distribution grids.