从智能电表数据揭示住宅光伏与电动汽车共同采用：负荷原型与检测用于需求侧规划
Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning
浏览论文内容
中文总结 AI 辅助
本文利用智能电表数据，通过DTW聚类和BiLSTM检测，揭示住宅光伏与电动汽车共同采用模式，助力需求侧规划。
中文摘要 AI 辅助
电动汽车（EV）和屋顶光伏（PV）系统的日益普及正在重塑住宅电力需求，并为需求侧管理（DSM）、电价设计和低压电网规划带来新的挑战。现有文献大多单独研究EV充电或PV发电，对家庭共同采用的行为动态了解不足。我们开发了一个集成的两部分工作流程来分析高级计量基础设施（AMI）数据。发现组件采用动态时间规整（DTW）k均值结合DTW质心平均，将每日进口或出口负荷曲线聚类为可解释的行为原型；预测组件则在21天窗口上训练双向长短期记忆（BiLSTM）模型，并与表格基线进行PV/EV活动检测的基准比较。由于无法获取充电器测量数据，EV活动标签是从类似充电的负荷特征中推断出来的。利用澳大利亚维多利亚州AusNet半小时住宅数据，聚类揭示了仅PV、仅EV、共同采用和无任何采用四类群体之间的不同模式；对于共同采用者，以中午为中心的工作日出口原型约占50%的天数。在验证调优的阈值下，BiLSTM和XGBoost均实现了强判别能力。BiLSTM的接收者操作特征曲线下面积（AUROC）为0.991，宏F1为0.906，并且在最难分类的类别上获得了最高召回率（仅EV召回率为0.836）。基于树的基线仍具有竞争力。性能在合理的标签规则（宏F1：0.894--0.914）和严格前向时间划分（宏F1：0.894--0.906）下保持稳定。
英文摘要
The increasing adoption of electric vehicles (EVs) and rooftop photovoltaic (PV) systems is reshaping residential electricity demand and creating new challenges for demand-side management (DSM), tariff design, and low-voltage network planning. Much of the existing literature examines EV charging or PV generation in isolation, leaving the behavioral dynamics of household co-adoption less understood. We develop an integrated, two-part workflow to analyze advanced metering infrastructure (AMI) data. A discovery component applies dynamic time warping (DTW) k-means with DTW barycenter averaging to cluster daily import or export profiles into interpretable behavioral archetypes, while a predictive component trains a bidirectional long short-term memory (BiLSTM) model on 21-day windows and benchmarks it against tabular baselines for PV/EV activity detection. The EV activity labels are inferred from charging-like load signatures because charger measurements are unavailable. Using half-hourly AusNet residential data from Victoria, Australia, the clustering uncovers distinct patterns across PV-only, EV-only, co-adoption, and neither cohorts; for co-adopters, a midday-centered weekday export archetype accounts for approximately 50% of days. At validation-tuned thresholds, both BiLSTM and XGBoost achieve strong discrimination. BiLSTM obtains 0.991 for the area under the receiver operating characteristic curve (AUROC), 0.906 for macro-F1, and the highest recall on the most difficult class (0.836 for EV-only recall). Tree-based baselines remain competitive. Performance remains stable across plausible labeling rules (macro-F1: 0.894--0.914) and strictly forward temporal splits (macro-F1: 0.894--0.906).
发表机构
- Monash University（莫纳什大学）
- Monash Energy Institute（莫纳什能源研究所）
机构由 AI 辅助整理，请以论文原文为准。
