{"success":true,"data":{"author":"Goldfeder, Dean, Jiang, Wang, Lipson, Sipple et al. (Google and Columbia University)","bucketAccessType":"public","bucketName":"Jgoldfeder/smart-buildings","bucketPrefix":"","category":"Energy","cloudProvider":"huggingface","createdAt":"2026-11-16T15:39:55.863Z","description":"Operational building automation system (BAS) data from 11 buildings, 2018 to 2026, for HVAC energy modelling, fault detection, forecasting and reinforcement-learning control (Goldfeder et al., arXiv 2410.03756). SB1 to SB3 are Google office buildings in Mountain View, CA at 5-minute steps (2019-2024, 3,136 to 13,610 channels each) with RL-style observations, actions, rewards and reward_info; SB4 to SB6 are academic, residential retrofit and laboratory buildings in Syracuse, NY (1 to 5 minute steps); SB7 to SB11 are campus academic, dining and residence-hall buildings in Needham, MA at 15-minute steps. Channels cover sensors, setpoints, commands and equipment status such as zone air temperature, supply air flow, damper and valve positions and chiller and boiler status, recorded in native units without resampling. Layout: buildings.csv, a shared channel table points.parquet, and SBx/timeseries/<table>/<year>.parquet wide tables plus irregular and auxiliary tables, provenance.json and floor plans; 331 files, about 6.3 GB. Read with pandas or the included loader.py. Licensed CC BY 4.0 by the authors; SB1-SB3 derive from the Google Smart Buildings data, which should also be credited.","displayTitle":"Smart Buildings Dataset SB1-SB11: HVAC Building Automation Time Series","huggingFaceUrl":"https://huggingface.co/datasets/Jgoldfeder/smart-buildings","id":"d179f0e1-a063-5118-9f5e-9e3073fc500d","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/Jgoldfeder/smart-buildings","objectCountEstimate":331,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2410.03756","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Jgoldfeder/smart-buildings\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Jgoldfeder/smart-buildings\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Jgoldfeder, license:cc-by-4.0, size_categories:1M<n<10M, format:parquet, downloads=130"],"format":"mixed","generatedAt":"2026-11-16T15:40:00.750Z","layout":{"example":"SB1/metadata/floorplan.npy","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","decoded":{"fields":{"descr":"<f8","dtype":"float64","fortranOrder":false,"ndim":2,"shape":"744,1004"},"format":"npy","summary":"NPY float64 [744, 1004]"},"encoding":"hex","key":"SB1/metadata/floorplan.npy","truncatedAt":512}],"sampleObjects":["SB1/metadata/device_info.json","SB1/metadata/device_layout_map.json","SB1/metadata/floorplan.npy","SB1/metadata/zone_info.json","SB1/points.csv"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\npretty_name: Smart Buildings Dataset (SB1–SB11)\nlanguage:\n- en\ntags:\n- buildings\n- hvac\n- building-automation\n- energy\n- time-series\n- reinforcement-learning\n- smart-buildings\ntask_categories:\n- time-series-forecasting\n- tabular-regression\n- reinforcement-learning\narxiv: 2410.03756\nsize_categories:\n- 100M<n<1B\nconfigs:\n- config_name: buildings\n  default: true\n  data_files:\n  - split: train\n    path: \"buildings.parquet\"\n- config_name: points\n  data_files:\n  - split: train\n    path: \"points.parquet\"\n- config_name: SB1_actions\n  data_files:\n  - split: train\n    path: \"SB1/timeseries/actions/????.parquet\"\n- config_name: SB1_observations\n  data_files:\n  - split: train\n    path: \"SB1/timeseries/observations/????.parquet\"\n- config_name: SB1_reward\n  data_files:\n  - split: train\n    path: \"SB1/timeseries/reward/????.parquet\"\n- config_name: SB1_reward_info\n  data_files:\n  - split: train\n    path: \"SB1/timeseries/reward_info/????.parquet\"\n- config_name: SB2_actions\n  data_files:\n  - split: train\n    path: \"SB2/timeseries/actions/????.parquet\"\n- config_name: SB2_observations\n  data_files:\n  - split: train\n    path: \"SB2/timeseries/observations/????.parquet\"\n- config_name: SB2_reward\n  data_files:\n  - split: train\n    path: \"SB2/timeseries/reward/????.parquet\"\n- config_name: SB2_reward_info\n  data_files:\n  - split: train\n    path: \"SB2/timeseries/reward_info/????.parquet\"\n- config_name: SB3_actions\n  data_files:\n  - split: train\n    path: \"SB3/timeseries/actions/????.parquet\"\n- config_name: SB3_observations\n  data_files:\n  - split: train\n    path: \"SB3/timeseries/observations/????.parquet\"\n- config_name: SB3_reward\n  data_files:\n  - split: train\n    path: \"SB3/timeseries/reward/????.parquet\"\n- config_name: SB3_reward_info\n  data_files:\n  - split: train\n    path: \"SB3/timeseries/reward_info/????.parquet\"\n- config_name: SB4_observations\n  data_files:\n  - split: train\n    path: \"SB4/timeseries/observations/????.parquet\"\n- config_name: SB5_observations\n  data_files:\n  - split: train\n    path: \"SB5/timeseries/observations/????.parquet\"\n- config_name: SB6_observations\n  data_files:\n  - split: train\n    path: \"SB6/timeseries/observations/????.parquet\"\n- config_name: SB7_observations\n  data_files:\n  - split: train\n    path: \"SB7/timeseries/observations/????.parquet\"\n- config_name: SB8_observations\n  data_files:\n  - split: train\n    path: \"SB8/timeseries/observations/????.parquet\"\n- config_name: SB9_observations\n  data_files:\n  - split: train\n    path: \"SB9/timeseries/observations/????.parquet\"\n- config_name: SB10_observations\n  data_files:\n  - split: train\n    path: \"SB10/timeseries/observations/????.parquet\"\n- config_name: SB11_observations\n  data_files:\n  - split: train\n    path: \"SB11/timeseries/observations/????.parquet\"\n---\n\n# Smart Buildings Dataset (SB1–SB11)\n\nOperational data from 11 buildings, 3 sources, 2018–2026: building automation system (BAS)\nsensors, setpoints, commands and status, plus RL-style actions and rewards for the three Google\nbuildings. Every building is stored at its **native time resolution** with values **exactly as\nrecorded, in native units**. A single channel table (`points.parquet`) describes every channel\nin the same vocabulary across buildings.\n\n## Buildings\n\n| Building | Source | Type | Location | Native step | Span (UTC) | Channels |\n|---|---|---|---|---|---|---|\n| SB1 | Google Smart Buildings | office | Mountain View, CA | 5 min | 2019-01 → 2024-07 | 4,470 |\n| SB2 | Google Smart Buildings | office | Mountain View, CA | 5 min | 2019-01 → 2024-07 | 3,136 |\n| SB3 | Google Smart Buildings | office | Mountain View, CA | 5 min | 2020 | 13,610 |\n| SB4 | University collaboration | academic / research | Syracuse, NY | 5 min | 2023-12 → 2026-04 | 8,600 |\n| SB5 | University collaboration | residential (retrofit study) | Syracuse, NY | 1 min | 2021-08 → 2023-05 | 477 |\n| SB6 | University collaboration | laboratory | Syracuse, NY | 5 min | 2022-10 → 2025-01 | 1,078 |\n| SB7 | Campus BAS | academic | Needham, MA | 15 min | 2019-06 → 2024-07 | 1,005 |\n| SB8 | Campus BAS | student ","encoding":"utf8","key":"README.md","name":"README.md","size":12595,"truncated":true}],"sourceObjectKey":"SB1/metadata/floorplan.npy","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"Jgoldfeder/smart-buildings\", filename=\"SB1/metadata/floorplan.npy\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"SB1/metadata/floorplan.npy","totalObjects":331},"summary":"Operational building automation system (BAS) data from 11 buildings, 2018 to 2026, for HVAC energy modelling, fault detection, forecasting and reinforcement-learning control…","title":"Smart Buildings Dataset SB1-SB11: HVAC Building Automation Time Series","updatedAt":"2026-11-17T17:05:01.228Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/Jgoldfeder/smart-buildings"}}