Probabilistic Dual-Adaptive Spatio-Temporal Graph Convolutional Networks for forecasting energy consumption dynamics of electric vehicle charging stations

• Published in: Computers & electrical engineering 2025-03, Vol.122, p.109976, Article 109976
• Main Authors: Mekkaoui, Djamel Eddine, Midoun, Mohamed Amine, Smaili, Abdelkarim, Feng, Bowen, Talhaoui, Mohamed Zakariya, Shen, Yanming
• Format: Article
• Language: English
• Subjects: Adaptive learning; Electric vehicles; Energy load forecasting; Probabilistic approach; Spatio-temporal analysis
• ISSN: 0045-7906
• DOI: 10.1016/j.compeleceng.2024.109976

Energy consumption forecasting is a crucial and challenging task in intelligent energy systems, particularly with the growing adoption of electric vehicles (EVs). Accurate energy demand forecasting relies on analyzing historical data and integrating appropriate factors. Recently, the application of graph convolutional networks (GCNs) has gained prominence in time series forecasting. In light of these developments, we introduce the Probabilistic Dual-Adaptive Spatio-Temporal Graph Convolutional Network (DAS-GCN). Unlike previous approaches, it synergistically interacts with two novel blocks considering user station switching behavior and correlations: Bi-Spatial Graph Integration Unit (Bi-SGI) leverages the spatial intelligence in GCNs, and Adaptive Probabilistic Graph Integration Module (A-PGI) utilizes user transition behavior to dynamically selects the appropriate Poisson probability distribution for the adjacency matrix. This dual approach enables comprehensive and enhanced data analysis by facilitating the learning of charging network and node connectivity, allowing for accurate forecasting of complex EV charging demands. Extensive experiments were performed on real-world datasets, integrating load duration and user transition patterns into energy load forecasting for a comprehensive energy load study. Experimental results show that DAS-GCN model significantly outperforms traditional methods and recent spatiotemporal forecasting approaches in predictive accuracy for both short- and long-term predictions.