发表机构
Centre Borelli, ENS Paris-Saclay; EDF Lab; Laboratoire de Mathématiques d'Orsay, Université Paris-Saclay（巴黎萨克雷高等师范学院博雷利中心; 法国电力公司实验室; 巴黎萨克雷大学奥赛数学实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GraphToolbox是一个基于PyTorch Geometric的可配置Python框架，统一了图构建、模型训练、聚合与解释，在电力负荷预测中实现系统性架构评估，并降低预测误差。
AI 中文摘要
电力负荷预测通常涉及在区域、变电站和馈线上观测到的空间相关信号，而图神经网络（GNN）为表示这些关系提供了一种自然的方式。然而，构建一个完整的GNN预测实验是费力的，因为图构建、模型选择、训练、聚合和解释分散在不兼容的工具中。我们提出了GraphToolbox，一个开源的Python框架，它将上述阶段统一到一个基于PyTorch Geometric构建的配置驱动流水线中。该框架提供数据驱动的图构建、一个适配器（可实例化并训练65种PyTorch Geometric卷积中的51种，以及PyTorch Geometric Temporal的循环单元）、在线专家聚合、预测可解释性以及对缓存预测的显著性检验。我们在两个案例研究中评估了该流水线。在法国区域负荷上，完整预测扫描中包含的48种卷积的误差范围在1.14%至1.60%之间，在线聚合将其降低至0.98%，且图模型优于经典的加性和提升基线。在净负荷上，直接图模型的准确性低于经典加性模型，而分别预测每个物理组件可改善图模型，但未能缩小这一差距。两项比较使用相同的实验接口，展示了GraphToolbox在系统化架构评估中的作用。
英文摘要
Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) provide a natural way to represent these relations. Building a complete GNN forecasting experiment is nonetheless laborious, because graph construction, model selection, training, aggregation, and interpretation sit in incompatible tools. We present GraphToolbox, an open-source Python framework that unifies these stages in one configurationdriven pipeline built on PyTorch Geometric. It offers data-driven graph construction, an adapter that instantiates and trains 51 of the 65 PyTorch Geometric convolutions together with the recurrent cells of PyTorch Geometric Temporal, online expert aggregation, forecasting interpretability, and significance testing on cached forecasts. We evaluate the pipeline in two case studies. On French regional load, the 48 convolutions included in the complete forecasting sweep fall in a band from 1.14% to 1.60% error, online aggregation lowers this to 0.98%, and the graph models improve on classical additive and boosting baselines. On net-load, direct graph models are less accurate than a classical additive model, while forecasting each physical component separately improves them without closing that gap. Both comparisons use the same experimental interface, illustrating the role of GraphToolbox in systematic architectural evaluation.
