跨配电网聚合层级的峰值感知短期负荷预测
Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels
查看机构详情
- Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大大学埃尔朗根-纽伦堡）
- Siemens AG（西门子股份公司）
- Ostbayerische Technische Hochschule Amberg-Weiden（东巴伐利亚安贝格-魏登应用技术大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究提出峰值感知评估框架，对比统计、ML及基础模型在配电网多层级负荷预测中的表现，发现Chronos-2在高需求时段精度最优，并强调分位数选择对实际运行的重要性。
中文摘要 AI 辅助
对于配电系统运营商而言，短期负荷预测（STLF）支持拥塞管理、电压控制和资产保护。现有的大多数方法侧重于所有时间步长的整体精度，而忽视了高需求（HD）时段的表现，在这些时段，较大的预测误差会增加拥塞和电压越限的风险。在本文中，我们使用来自英国和瑞士的开放数据集，研究了跨三个运营商相关的配电网聚合层级（区域代码（AC）、二次变电站（SUB）和低压（LV）馈线）的峰值感知短期负荷预测。我们在一个峰值感知评估框架下比较了统计基线、机器学习模型（LightGBM和XGBoost）以及近期的时间序列基础模型（Chronos Bolt和Chronos-2），该框架使用NMAE和MAPE报告整体和HD预测性能。结果表明，Chronos-2在所有聚合层级上实现了最佳的HD性能，在AC层级的HD-NMAE和HD-MAPE分别为0.039和4.53%，在SUB层级为0.080和9.45%，在LV层级为0.138和16.14%，而Chronos-Bolt始终排名第二。与梯度提升的ML模型相比，Chronos-2在各层级上的平均HD-NMAE降低了约20-51%，同时在整体指标上保持最佳或接近最佳。对概率性Chronos输出的分位数分析进一步确定了特定于聚合层级的运行点，运行时测量表明基础模型推理速度足够快，可满足实际部署需求。总体而言，研究结果强调了峰值感知评估和特定于聚合层级的分位数选择，是通往更具运行相关性的配电网短期负荷预测的实用途径。
英文摘要
For distribution system operators, short-term load forecasting (STLF) supports congestion management, voltage control, and asset protection. Most existing approaches focus on overall accuracy across all time steps and neglect performance during high-demand (HD) periods, where larger forecast errors can increase the risk of congestion and voltage violations. In this paper, we study peak-aware STLF across three operator-relevant distribution grid aggregation levels, area codes (AC), secondary substations (SUB), and low-voltage (LV) feeders, using open datasets from the United Kingdom and Switzerland. We compare statistical baselines, machine learning models (LightGBM and XGBoost), and recent time-series foundation models (Chronos Bolt and Chronos-2) under a peak-aware evaluation framework that reports both overall and HD forecasting performance using NMAE and MAPE. The results show that Chronos-2 achieves the best HD performance across all aggregation levels, with HD-NMAE and HD-MAPE of 0.039 and 4.53% at AC, 0.080 and 9.45% at SUB, and 0.138 and 16.14% at LV, while Chronos-Bolt consistently ranks second best. Compared with the gradient boosted ML models, Chronos-2 reduces mean HD-NMAE by about 20-51% across levels while remaining best or near-best on the overall metrics. A quantile analysis of the probabilistic Chronos outputs further identifies aggregation-specific operating points, and runtime measurements indicate that foundation model inference is fast enough for practical deployment. Overall, the findings highlight peak-aware evaluation and aggregation specific quantile selection as a practical pathway toward more operationally relevant STLF in distribution networks.
