Smart Grid Energy Consumption
This dataset provides synthetic, household-level smart grid energy consumption records with detailed temporal, environmental, and demographic attributes. It is ideal for testing and benchmarking demand response algorithms, energy-saving models, and utility sector analytics, offering rich context for both time-series and cross-sectional analysis.
Sample rows
preview · 8 of 200 rows · all 16 columns| record_idstring | household_typestring | household_sizeinteger | peak_usageboolean | address_statestring | household_idstring | timestampdatetime | energy_consumption_kwhfloat | temperature_celsiusfloat | humidity_percentfloat | address_streetstring | address_citystring | address_postal_codestring | address_countrystring | solar_panel_installedboolean | smart_appliances_countinteger |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| REC00001 | apartment | 2 | true | TX | HH001 | 2024-03-11T18:03:00 | 8.7 | 16.1 | 52.1 | Oakridge Ave | Houston | 77002 | USA | false | 1 |
| REC00002 | detached_house | 6 | true | TX | HH002 | 2024-03-11T13:24:00 | 34.2 | 22.3 | 60.2 | Maplewood Dr | Dallas | 75001 | USA | true | 7 |
| REC00003 | apartment | 1 | false | ENG | HH003 | 2024-03-09T08:48:00 | 2.5 | 0.2 | 37.9 | Kingsway Rd | London | M14 5WE | UK | false | 0 |
| REC00004 | detached_house | 5 | true | FL | HH004 | 2024-03-08T17:55:00 | 27.6 | 33.4 | 49 | Sunshine Blvd | Miami | 33101 | USA | true | 8 |
| REC00005 | townhouse | 3 | false | ON | HH005 | 2024-03-07T19:44:00 | 11.9 | 5.8 | 41.3 | Pinecrest St | Toronto | M4B 1B3 | Canada | false | 2 |
| REC00006 | apartment | 2 | false | TX | HH001 | 2024-03-07T07:16:00 | 7.3 | 13.4 | 56.6 | Oakridge Ave | Houston | 77002 | USA | false | 1 |
| REC00007 | townhouse | 2 | true | IL | HH006 | 2024-03-07T17:02:00 | 4.8 | 21.7 | 61.2 | Rosehill Ln | Chicago | 60616 | USA | false | 2 |
| REC00008 | other | 10 | true | LA | HH007 | 2024-03-06T14:28:00 | 55.6 | 29.1 | 73.8 | Broadview Rd | Lagos | 101001 | Nigeria | false | 1 |
| REC00009 | detached_house | 7 | true | BC | HH008 | 2024-03-06T21:35:00 | 38.2 | 26.6 | 64.5 | Cypress St | Vancouver | V5K 0A1 | Canada | true | 9 |
| REC00010 | apartment | 2 | false | ENG | HH009 | 2024-03-06T09:32:00 | 3.9 | 12.2 | 43.9 | Elm St | Manchester | M19 3AA | UK | false | 1 |
| REC00011 | apartment | 1 | true | ST | HH010 | 2024-03-05T16:47:00 | 2.1 | 7.8 | 59.6 | Birch St | Stockholm | 114 55 | Sweden | false | 0 |
| REC00012 | detached_house | 5 | true | CA | HH011 | 2024-03-05T20:03:00 | 21.8 | 11.4 | 65 | Highland Ave | San Diego | 92101 | USA | true | 6 |
| REC00013 | apartment | 2 | false | ON | HH012 | 2024-03-05T10:29:00 | 6.9 | 2.6 | 40.7 | Wellington St | Ottawa | K1A 0B1 | Canada | false | 1 |
| REC00014 | detached_house | 8 | true | QLD | HH013 | 2024-03-04T17:01:00 | 41.2 | 35.2 | 38.3 | Acacia Rd | Brisbane | 4000 | Australia | true | 12 |
| REC00015 | apartment | 1 | false | RU | HH014 | 2024-03-04T08:46:00 | 0.8 | -21.4 | 32.4 | Lenina St | Moscow | 101000 | Russia | false | 0 |
| REC00016 | townhouse | 4 | true | BE | HH015 | 2024-03-03T18:44:00 | 16.4 | 18.2 | 58.8 | Bergstrasse | Berlin | 10115 | Germany | false | 4 |
| REC00017 | other | 11 | false | SA | HH016 | 2024-03-03T11:29:00 | 23.5 | 34.1 | 67.2 | Palm Dr | Riyadh | 11564 | Saudi Arabia | false | 2 |
| REC00018 | townhouse | 3 | true | ST | HH017 | 2024-03-02T17:12:00 | 13.8 | 25.5 | 77.9 | Willow St | Gothenburg | 411 17 | Sweden | false | 3 |
| REC00019 | apartment | 1 | false | BE | HH018 | 2024-03-02T15:09:00 | 2.2 | 9.6 | 62.3 | Winterstrasse | Munich | 80331 | Germany | false | 0 |
| REC00020 | other | 14 | true | ZW | HH019 | 2024-03-02T09:53:00 | 60.8 | 39.7 | 14.5 | Harare Ave | Harare | 00263 | Zimbabwe | false | 1 |
What the 200 rows show
from the 200-row sampleOther (household type) stands out: mean household_
- 53%peak_
usage = true - 4median household_
size - 12address countries
- 49address cities
- 10.2median energy_
consumption_ kwh - 19.5median temperature_
celsius
Median 4, from 1 to 15.
- string 8
- integer 2
- float 3
- datetime 1
- boolean 2
Columns
16 columns in four groups| column | type | description | example |
|---|---|---|---|
| Text 8 columns | |||
record_id | string | Unique identifier for each energy consumption recordunique | REC00001 |
household_id | string | Unique identifier for each household | HH001 |
household_type | string | Type of household (e.g., apartment, detached house, townhouse)apartment · detached_house · townhouse · other · optional | apartment |
address_street | string | Street address of the householdoptional | Oakridge Ave |
address_city | string | City where the household is locatedoptional | Houston |
address_state | string | State or province where the household is locatedoptional | TX |
address_postal_code | string | Postal code of the household addressoptional | 77002 |
address_country | string | Country of the household address12 countries · optional | USA |
| Numbers 5 columns | |||
energy_consumption_kwh | float | Total energy consumed by the household during the recorded interval, measured in kilowatt-hours (kWh)0 or more | 8.7 |
temperature_celsius | float | Ambient temperature at the household location during the recorded interval, in degrees Celsiusoptional | 16.1 |
humidity_percent | float | Relative humidity at the household location during the recorded interval, as a percentage0 to 100 · optional | 52.1 |
household_size | integer | Number of people living in the household1 or more · optional | 2 |
smart_appliances_count | integer | Number of smart appliances in the household0 or more · optional | 1 |
| Dates and times 1 column | |||
timestamp | datetime | Date and time when the energy usage was recorded | 2024-03-11T18:03:00 |
| True or false 2 columns | |||
peak_usage | boolean | Indicates if the recorded interval falls within a designated peak usage period | true |
solar_panel_installed | boolean | Indicates whether the household has solar panels installedoptional | false |
Use it for
An energy dashboard
The peak_
usage rate, household_ size by household_ type and a breakdown of address_ state. Excel, Power BI or Tableau. Why do the 27 other rows have a mean household_
size of 11.3? A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
- Records200REC000012apartmentREC000026detached…REC000031apartment
A software demo
Believable records with household_
id, timestamp and energy_ consumption_ kwh to fill a screen in front of a buyer.
This dataset200 rows16 columns
Yours1,000 rows16 columnsaddress_street: UK only
blueprint · smart-grid-energy-consumption
Behind this dataset
Same schema. As many rows as you need.
These 200 rows came out of a blueprint — 16 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.
Rules it was built with
- Hourly readings per household ID
- Anomalous spikes injected in 3% of homes
- Weather impact simulated for usage variation
- Consumption values in kWh, 0.1-15 kWh/hour
Open the blueprint in Data Factory
1 credit per row. Preview 20 rows free. Buy rows for the full run.
- Exports
- CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
- Licence
- yours to use, including commercially
- API slug
- smart-grid-energy-consumption