Scholarlink

<p>Achieving energy-optimal urban mobility requires precise predictive energy management for electric buses (EBs). However, existing trip-level predictive models largely overlook the topological structure and complex driving dynamics of stop-route networks. This study proposes an edge-enhanced Graph Transformer framework that models each trip as a directed graph, with stops as nodes and inter-stop micro-trips as edges, to predict trip-level energy consumption rates (ECR). Using real-world data from 219 EBs across 47 routes in Guangzhou, the model integrates stop, route, kinetic, and environmental features. A novel edge enhancement mechanism is introduced to strengthen micro-trip dynamics within the attention computation. Feature contributions are quantitatively analyzed using SHAP values, and internal decision-making patterns are interpreted through attention weight visualization. The proposed model achieves MAE of 0.0756 kWh/km, RMSE of 0.0972 kWh/km, MAPE of 10.14%, and <i>R</i><sup>2</sup> of 0.77 on unseen routes, outperforming all baselines. Edge enhancement yields MAPE reductions of 8.51% and 5.92% for Graph Transformer and GCN, respectively. Mechanism analysis confirms that edge features dominate feature fusion with approximately 62% attention weight allocation. The achieved prediction accuracy falls within the typical SOC safety margins maintained in EB battery management, supporting practical deployment in charging scheduling and energy-aware route planning.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predictive energy management for urban electric bus transit: An edge-enhanced Graph Transformer approach

  • 期刊论文

  • 发表日期：

    2026年7月24日

查看全文
  • Jiahao Zhan,
  • Ying Yang,
  • Zhe Zhang,
  • Yang Liu,
  • Qing Yu,
  • Mingyang Pei,
  • Xiaobo Qu

摘要

Achieving energy-optimal urban mobility requires precise predictive energy management for electric buses (EBs). However, existing trip-level predictive models largely overlook the topological structure and complex driving dynamics of stop-route networks. This study proposes an edge-enhanced Graph Transformer framework that models each trip as a directed graph, with stops as nodes and inter-stop micro-trips as edges, to predict trip-level energy consumption rates (ECR). Using real-world data from 219 EBs across 47 routes in Guangzhou, the model integrates stop, route, kinetic, and environmental features. A novel edge enhancement mechanism is introduced to strengthen micro-trip dynamics within the attention computation. Feature contributions are quantitatively analyzed using SHAP values, and internal decision-making patterns are interpreted through attention weight visualization. The proposed model achieves MAE of 0.0756 kWh/km, RMSE of 0.0972 kWh/km, MAPE of 10.14%, and R2 of 0.77 on unseen routes, outperforming all baselines. Edge enhancement yields MAPE reductions of 8.51% and 5.92% for Graph Transformer and GCN, respectively. Mechanism analysis confirms that edge features dominate feature fusion with approximately 62% attention weight allocation. The achieved prediction accuracy falls within the typical SOC safety margins maintained in EB battery management, supporting practical deployment in charging scheduling and energy-aware route planning.