Sub-hourly measurement datasets from 6 real buildings: Energy use and indoor climate

Igor Sartori; Harald Taxt Walnum; Kristian S Skeie; Laurent Georges; Michael D Knudsen; Peder Bacher; José Candanedo; Anna-Maria Sigounis; Anand Krishnan Prakash; Marco Pritoni; Jessica Granderson; Shiyu Yang; Man Pun Wan

doi:10.1016/j.dib.2023.109149

Sub-hourly measurement datasets from 6 real buildings: Energy use and indoor climate

Data Brief. 2023 Apr 13:48:109149. doi: 10.1016/j.dib.2023.109149. eCollection 2023 Jun.

Authors

Affiliations

¹ SINTEF, Department of Architectural Engineering, P.O. Box 124 Blindern, 0314 Oslo, Norway.
² NTNU, Department of Energy and Process Engineering, Kolbjørn Hejes vei 1b, 7034 Trondheim, Norway.
³ Aarhus University, Department of Civil and Architectural Engineering - Building Science,Inge Lehmanns Gade 10, 8000 Aarhus C, Denmark.
⁴ DTU Compute, Bygning 324, 2800 Kongens Lyngby, Denmark.
⁵ Concordia University, Department of Building, Civil and Environmental Engineering, 1455 De Maisonneuve Blvd. W, Montreal, Quebec, Canada.
⁶ CanmetENERGY in Varennes, Energy Efficiency and Technology Sector, 1615 Lionel-Boulet Blvd.,Varennes, QC J3 × 1S6, Canada.
⁷ Lawrence Berkeley National Laboratory, Building Technology and Urban Systems, 1 Cyclotron Road, Berkeley, California 94720, United States.
⁸ Nanyang Technological University, School of Mechanical and Aerospace Engineering, 639798, Singapore.
⁹ Cornell University, Systems Engineering, Ithaca, NY, USA, 14853.

Abstract

The data presented here were collected independently for 6 real buildings by researchers of different institutions and gathered in the context of the IEA EBC Annex 81 Data-driven Smart Buildings, as a joint effort to compile a diverse range of datasets suitable for advanced control applications of indoor climate and energy use in buildings. The data were acquired by energy meters, both consumption and PV generation, and sensors of technical installation and indoor climate variables, such as temperature, flow rate, relative humidity, CO₂ level, illuminance. Weather variables were either acquired by local sensors or obtained from a close by meteorological station. The data were collected either during normal operation of the building, with observation periods between 2 weeks and 2 months, or during experiments designed to excite the thermal mass of the building, with observation periods of approximately one week. The data have a time resolution varying between 1 min and 15 min; in some case the highest resolution data are also averaged at larger intervals, up to 30 min.

Keywords: CSV files; Deep Reinforcement Learning (DRL); Heating; High resolution; Model Predictive Control (MPC); Model identification; Pseudo-Random Binary Sequence (PRBS); Ventilation and Air Conditioning (HVAC).