8 years of hourly heat and electricity demand for a residential building

The heating and electricity consumption data are the results of an energy audit program aggregated for multiple load profiles of a residential customer. These profiles include HVAC systems loads, convenience power, elevator, etc. The datasets are gathered between December 2010 and November 2018 with a one-hour timestep resolution, thereby containing 140,160 measurements, half of which is for heat or electricity. In addition to the historical energy consumption values, a concatenation of weather variables is also available. The weather variables are air pressure, temperature, and humidity plus wind speed, cloudiness percentage, and solar irradiation at the predetermined location. For further characteristics, interested readers are invited to see the reference [1].[1] Taheri S, Jooshaki M, Moeini-Aghtaie M. Long-term planning of integrated local energy systems using deep learning algorithms. International Journal of Electrical Power & Energy Systems. 2021 Jul 1;129:106855. DOI: https://doi.org/10.1016/j.ijepes.2021.106855

该数据集汇集了住宅客户的多种负载配置文件的热能和电力消耗数据，这些数据由能源审计计划综合汇总而成。配置文件包括暖通空调系统负载、便利电力、电梯等。数据集收集时间跨度为2010年12月至2018年11月，以每小时的时间步长进行采集，因此包含140,160次测量，其中一半涉及热量或电力消耗。除历史能源消耗值外，还包括天气变量的串联数据。这些天气变量包括空气压力、温度、湿度以及风速、云量百分比和预定位置的太阳辐射。欲了解更多特性，有兴趣的读者可参阅参考文献[1]。[1] Taheri S, Jooshaki M, Moeini-Aghtaie M. 基于深度学习算法的集成本地能源系统长期规划。国际电气电力与能源系统杂志。2021年7月1日；129卷：106855。DOI：https://doi.org/10.1016/j.ijepes.2021.106855