Department of Computer Science, Chair for Application and Middleware Systems, Technical University of Munich, 85748 Garching, Germany.
Sci Data. 2018 Mar 27;5:180048. doi: 10.1038/sdata.2018.48.
Energy metering has gained popularity as conventional meters are replaced by electronic smart meters that promise energy savings and higher comfort levels for occupants. Achieving these goals requires a deeper understanding of consumption patterns to reduce the energy footprint: load profile forecasting, power disaggregation, appliance identification, startup event detection, etc. Publicly available datasets are used to test, verify, and benchmark possible solutions to these problems. For this purpose, we present the BLOND dataset: continuous energy measurements of a typical office environment at high sampling rates with common appliances and load profiles. We provide voltage and current readings for aggregated circuits and matching fully-labeled ground truth data (individual appliance measurements). The dataset contains 53 appliances (16 classes) in a 3-phase power grid. BLOND-50 contains 213 days of measurements sampled at 50kSps (aggregate) and 6.4kSps (individual appliances). BLOND-250 consists of the same setup: 50 days, 250kSps (aggregate), 50kSps (individual appliances). These are the longest continuous measurements at such high sampling rates and fully-labeled ground truth we are aware of.
随着传统仪表被电子智能仪表所取代，能源计量越来越受欢迎，这些智能仪表承诺为用户节省能源并提高舒适度。要实现这些目标，需要更深入地了解消费模式，以减少能源足迹：负荷曲线预测、功率分解、设备识别、启动事件检测等。公共数据集可用于测试、验证和基准化这些问题的可能解决方案。为此，我们提出了 BLOND 数据集：以高采样率对典型办公环境进行连续能源测量，并使用常见设备和负荷曲线。我们提供聚合电路的电压和电流读数以及匹配的完全标记的真实数据（各个设备的测量值）。该数据集包含三相电网中的 53 种电器（16 个类别）。BLOND-50 包含 213 天的测量数据，以 50kSps（聚合）和 6.4kSps（各个设备）的速率进行采样。BLOND-250 采用相同的设置：50 天，250kSps（聚合），50kSps（各个设备）。这些是我们所知的最长的以如此高的采样率和完全标记的真实数据进行的连续测量。
