The growing availability of smart meter data has facilitated the development of energy-saving services like demand response, personalized energy feedback, and non-intrusive-load-monitoring applications, all of which heavily rely on advanced machine learning algorithms trained on energy consumption datasets. To ensure the accuracy and reliability of these services, real-world smart meter data collection is crucial. The Plegma dataset described in this paper addresses this need bfy providing whole- house aggregate loads and appliance-level consumption measurements at 10-second intervals from 13 different households over a period of one year. It also includes environmental data such as humidity and temperature, building characteristics, demographic information, and user practice routines to enable quantitative as well as qualitative analysis. Plegma is the first high-frequency electricity measurements dataset in Greece, capturing the consumption behavior of people in the Mediterranean area who use devices not commonly included in other datasets, such as AC and electric-water boilers. The dataset comprises 218 million readings from 88 installed meters and sensors. The collected data are available in CSV format.

智能电表数据的可用性不断增加，促进了需求响应、个性化能源反馈和非侵入式负载监控应用等节能服务的发展，所有这些都严重依赖于在能耗数据集上训练的先进机器学习算法。为了确保这些服务的准确性和可靠性，现实世界的智能电表数据收集至关重要。本文描述的 Plegma 数据集满足了这一需求，通过在一年内以 10 秒的间隔提供 13 个不同家庭的全屋总负载和电器水平消耗测量结果。它还包括湿度和温度、建筑特征、人口统计信息和用户实践例程等环境数据，以实现定量和定性分析。 Plegma 是希腊第一个高频电力测量数据集，捕获地中海地区人们的消费行为，这些人使用其他数据集中不常见的设备，例如交流电和电热水壶。该数据集包含来自 88 个安装的仪表和传感器的 2.18 亿个读数。收集的数据以 CSV 格式提供。