Department of Computer Science North China Electric Power University (Baoding), BaoDing, China.
Hebei Key Laboratory of Knowledge Computing for Energy & Power, BaoDing, China.
Sci Data. 2024 May 14;11(1):493. doi: 10.1038/s41597-024-03310-3.
With the development of Non-Intrusive Load Monitoring (NILM), it has become feasible to perform device identification, energy consumption decomposition, and load switching detection using Deep Learning (DL) methods. Similar to other machine learning problems, the research and validation of NILM necessitate substantial data support. Moreover, different regions exhibit distinct characteristics in their electricity environments. Therefore, there is a need to provide open datasets tailored to different regions. In this paper, we introduce the Transient Dataset of Household Appliances with Intensive Switching Events (TDHA). This dataset comprises switch instantaneous data from 10 typical household appliances in China. The TDHA dataset features a high sampling rate, accurate labelling, and realistic representation of actual appliance start-up waveforms. Additionally, appliance switching is achieved through precise control of relay switches, thus mitigating interference caused by mechanical switches. By furnishing such a dataset, we aim not only to enhance the recognition accuracy of existing NILM algorithms but also to facilitate the application of NILM algorithms in regions sharing similar electricity consumption characteristics to those of China.
随着非侵入式负载监测（NILM）的发展，使用深度学习（DL）方法进行设备识别、能耗分解和负载切换检测已经成为可能。与其他机器学习问题类似，NILM 的研究和验证需要大量的数据支持。此外，不同地区的电力环境具有明显的特征差异。因此，需要提供针对不同地区的开放数据集。在本文中，我们介绍了具有密集开关事件的瞬态家用设备数据集（TDHA）。该数据集包含来自中国 10 种典型家用电器的开关瞬时数据。TDHA 数据集具有高采样率、准确的标签和实际电器启动波形的真实表示。此外，通过精确控制继电器开关来实现电器开关，从而减轻机械开关引起的干扰。通过提供这样一个数据集，我们的目标不仅是提高现有 NILM 算法的识别精度，还促进 NILM 算法在与中国具有相似用电特征的地区的应用。
