A Spatio-temporal Load Forecasting Method for Electric Vehicles Based on Multi-Graph Dynamic Fusion
Authors:
Open Access
- 1 May 2026
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3229 (1)
Abstract
Large-scale charging of electric vehicles poses challenges to safety of power grid operations, and accurately predicting their spatio-temporal load is key to achieving vehicle-grid coordination. Aiming at the limited expression ability of inter-regional correlation relationships in existing load forecasting models, this paper proposes a spatio-temporal load forecasting framework based on multi-graph dynamic fusion to capture more precise spatial dependencies. Experiments using real charging load data from Shenzhen demonstrate that the proposed model outperforms baseline models across primary performance metrics, achieving a 10.9% reduction in MAE compared to the optimal baseline model. This validates its effectiveness and generalization capability in complex spatio-temporal load prediction tasks.Keywords
This publication has 10 references indexed in Scilit:
- A Physics-Informed and Attention-Based Graph Learning Approach for Regional Electric Vehicle Charging Demand PredictionIEEE Transactions on Intelligent Transportation Systems, 2024
- A Freeway Traffic Flow Prediction Model Based on a Generalized Dynamic Spatio-Temporal Graph Convolutional NetworkIEEE Transactions on Intelligent Transportation Systems, 2024
- Load Forecasting of Electric Vehicle Charging Stations: Attention Based Spatiotemporal Multi–Graph Convolutional NetworksIEEE Transactions on Smart Grid, 2023
- Operating Status Prediction Model at EV Charging Stations With Fusing Spatiotemporal Graph Convolutional NetworkIEEE Transactions on Transportation Electrification, 2022
- Multistep electric vehicle charging station occupancy prediction using hybrid LSTM neural networksEnergy, 2022
- A Stacked GRU-RNN-Based Approach for Predicting Renewable Energy and Electricity Load for Smart Grid OperationIEEE Transactions on Industrial Informatics, 2021
- Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic ForecastingIEEE Transactions on Knowledge and Data Engineering, 2021
- Reinforcement Learning-Based Load Forecasting of Electric Vehicle Charging Station Using Q-Learning TechniqueIEEE Transactions on Industrial Informatics, 2020
- Deep-Learning-Based Probabilistic Forecasting of Electric Vehicle Charging Load With a Novel Queuing ModelIEEE Transactions on Cybernetics, 2020
- Spatio-Temporal Graph Deep Neural Network for Short-Term Wind Speed ForecastingIEEE Transactions on Sustainable Energy, 2018