Multiscale Spatio-Temporal Enhanced Short-term Load Forecasting of Electric Vehicle Charging Stations

TL;DR

This work tackles the challenging problem of short-term EV charging station load forecasting by modeling nonlinear temporal dynamics, spatial interactions, and multiscale temporal patterns. It introduces MSTEM, a Multiscale Spatio-temporal Enhanced Model that fuses a Multiscale Graph Construction and Learning (MGCL) module with a Temporal Enhanced Neural Network (TENN) and a residual fusion-based output layer. The MGCL component captures hierarchical spatial dependencies across multiple time scales, while TENN, augmented with LSTM units, models long-term temporal relations; the output layer combines both sources and applies a nonnegative constraint. Evaluations on real-world Perth EVCS data for fast and slow charging demonstrate that MSTEM outperforms six baselines across MSE, MAE, and RMSE, indicating improved reliability for short-term EVCS load forecasting with practical implications for grid operation and energy management.

Abstract

The rapid expansion of electric vehicles (EVs) has rendered the load forecasting of electric vehicle charging stations (EVCS) increasingly critical. The primary challenge in achieving precise load forecasting for EVCS lies in accounting for the nonlinear of charging behaviors, the spatial interactions among different stations, and the intricate temporal variations in usage patterns. To address these challenges, we propose a Multiscale Spatio-Temporal Enhanced Model (MSTEM) for effective load forecasting at EVCS. MSTEM incorporates a multiscale graph neural network to discern hierarchical nonlinear temporal dependencies across various time scales. Besides, it also integrates a recurrent learning component and a residual fusion mechanism, enhancing its capability to accurately capture spatial and temporal variations in charging patterns. The effectiveness of the proposed MSTEM has been validated through comparative analysis with six baseline models using three evaluation metrics. The case studies utilize real-world datasets for both fast and slow charging loads at EVCS in Perth, UK. The experimental results demonstrate the superiority of MSTEM in short-term continuous load forecasting for EVCS.

Figures (1)

• Figure 1: The overall structure of the multiscale spatio-temporal enhanced model.