Energy
18 columns
110 rows
8 formats

Energy Consumption Forecasting

This dataset provides detailed, time-stamped energy consumption records for both household and industrial entities, enriched with contextual information such as location, weather, occupancy, and demand metrics. It is ideal for utilities and researchers aiming to forecast energy demand, optimize grid operations, and analyze usage patterns across different segments and regions.

last updated 12 Jul 2025
by GoMask

The brief that made it

Short- and long-term energy demand forecasting

Sample rows

preview · 8 of 110 rows · all 18 columns

record_idstring	entity_typestring	consumption_kwhfloat	is_holidayboolean	statestring	entity_idstring	regionstring	citystring	postal_codestring	countrystring	timestampdatetime	peak_demand_kwfloat	temperature_cfloat	humidity_percentfloat	day_of_weekstring	hour_of_dayinteger	entity_sizefloat	entity_occupantsinteger
REC-00001	household	27.2	false	IL	H10001	Midwest	Chicago	60616	USA	2023-01-15T18:00:00Z	3.1	-5.2	74	Sunday	18	120	4
REC-00002	industrial	43852.5	false	blank	I20001	Gauteng	Johannesburg	2001	South Africa	2023-08-02T09:00:00Z	2100	16.7	38	Wednesday	9	150000	840
REC-00003	household	42.9	false	blank	H10002	Île-de-France	Paris	75011	France	2023-03-24T21:00:00Z	4.6	13.2	53	Friday	21	90	5
REC-00004	industrial	68735.2	false	CA	I20002	California	Los Angeles	90017	USA	2023-07-07T14:00:00Z	3440.5	32.1	23	Friday	14	220000	1150
REC-00005	household	36.5	false	NSW	H10003	New South Wales	Sydney	2000	Australia	2023-12-22T19:00:00Z	3.8	27.4	64	Friday	19	98	3
REC-00006	industrial	52134.7	false	ON	I20003	Ontario	Toronto	M5H 2N2	Canada	2023-02-20T12:00:00Z	3120.6	-8.6	81	Monday	12	210000	700
REC-00007	household	32.2	false	blank	H10004	Andalusia	Seville	41001	Spain	2023-08-01T20:00:00Z	2.7	39.5	29	Tuesday	20	110	4
REC-00008	industrial	34500	false	UP	I20004	Uttar Pradesh	Kanpur	208001	India	2023-05-11T16:00:00Z	1580.5	42.8	42	Thursday	16	54000	270
REC-00009	household	19.7	false	BC	H10005	British Columbia	Vancouver	V6B 1V2	Canada	2023-10-10T18:00:00Z	2.3	12	72	Tuesday	18	70	2
REC-00010	industrial	38500	false	SP	I20005	São Paulo	Campinas	13010-111	Brazil	2023-03-14T10:00:00Z	1780	24.9	56	Tuesday	10	110000	670
REC-00011	household	16.3	false	QLD	H10006	Queensland	Brisbane	4000	Australia	2023-02-10T08:00:00Z	1.4	28.2	82	Friday	8	73	3
REC-00012	industrial	59834	false	blank	I20006	Dubai	Dubai	00000	UAE	2023-06-01T17:00:00Z	3520	42	33	Thursday	17	200000	1100
REC-00013	household	35.6	false	blank	H10007	Catalonia	Barcelona	08001	Spain	2023-09-18T17:00:00Z	4.2	27.8	61	Monday	17	105	3
REC-00014	industrial	27800	false	blank	I20007	Hokkaido	Sapporo	060-0807	Japan	2023-01-10T11:00:00Z	1235	-11.5	65	Tuesday	11	48000	175
REC-00015	household	29.9	true	blank	H10008	Île-de-France	Versailles	78000	France	2023-11-11T18:00:00Z	2.6	8.2	69	Saturday	18	78	3
REC-00016	industrial	58020	false	MH	I20008	Maharashtra	Mumbai	400001	India	2023-10-26T13:00:00Z	3241	33.4	71	Thursday	13	180000	1180
REC-00017	household	0	true	blank	H10009	Eastern Cape	Port Elizabeth	6001	South Africa	2023-12-25T00:00:00Z	0	19.8	89	Monday	0	50	1
REC-00018	industrial	0	true	blank	I20009	Central Mexico	Mexico City	06000	Mexico	2023-09-16T00:00:00Z	0	14.3	65	Saturday	0	0	0
REC-00019	household	21.8	true	blank	H10010	Oslo	blank	9000	Norway	2023-01-01T14:00:00Z	2.2	-5.5	86	Sunday	14	86	2
REC-00020	industrial	33500	false	QLD	I20010	Queensland	Townsville	4810	Australia	2023-07-28T11:00:00Z	1660	25.6	77	Friday	11	50000	295

What the 110 rows show

from the 110-row sample

Industrial (entity type) stands out: mean consumption_kwh is 28,113, against 28.4 for the rest.

21%is_holiday = true
36.4median consumption_kwh
7day of weeks
16countries
4.2median peak_demand_kw
21.3median temperature_c

Mean consumption_kwh by entity_type110 rows

consumption_kwh110 rows, in bands of 10k

Median 36.4, from 0.0 to 68,735.

state50 rows with a value · 60 left blank

SP8
NSW7
MH6
QLD5
CA4
ON3
BC3
IL2
UP2
MI2

18 columns by typefrom the column list below

string 9
integer 2
float 5
datetime 1
boolean 1

Columns

18 columns in four groups

blueprint · 18 columns
column	type	description	example
Text 9 columns
`record_id`	string	Unique identifier for each energy consumption recordunique	REC-00001
`entity_type`	string	Type of entity consuming energy (household or industrial)household · industrial	household
`entity_id`	string	Unique identifier for the household or industrial entity	H10001
`region`	string	Geographical region or service area of the entity	Midwest
`city`	string	City where the entity is locatedoptional	Chicago
`state`	string	State or province where the entity is locatedoptional	IL
`postal_code`	string	Postal or ZIP code of the entity's locationoptional	60616
`country`	string	Country where the entity is located	USA
`day_of_week`	string	Day of the week for the timestamp (e.g., Monday, Tuesday)7 values · optional	Sunday
Numbers 7 columns
`consumption_kwh`	float	Energy consumed during the recorded interval, measured in kilowatt-hours (kWh)0 or more	27.2
`peak_demand_kw`	float	Maximum power demand during the interval, measured in kilowatts (kW)0 or more · optional	3.1
`temperature_c`	float	Ambient temperature in degrees Celsius at the time of recordingoptional	-5.2
`humidity_percent`	float	Ambient humidity as a percentage at the time of recording0 to 100 · optional	74
`hour_of_day`	integer	Hour of the day (0-23) when the record was captured0 to 23 · optional	18
`entity_size`	float	Size of the entity, such as household square meters or industrial facility size (optional, if available)0 or more · optional	120
`entity_occupants`	integer	Number of occupants (for households) or employees (for industrial entities)0 or more · optional	4
Dates and times 1 column
`timestamp`	datetime	Date and time when the energy consumption was recorded	2023-01-15T18:00:00Z
True or false 1 column
`is_holiday`	boolean	Indicates whether the date is a public holiday in the regionoptional	false

Use it for

An energy dashboard
The is_holiday rate, consumption_kwh by entity_type and a breakdown of state. Excel, Power BI or Tableau.
Why do the 55 industrial rows have a mean consumption_kwh of 28,113?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Records110
REC-0000127.2household
REC-0001529.9household
REC-000170household
A software demo
Believable records with entity_type, entity_id and region to fill a screen in front of a buyer.

This dataset110 rows18 columns

Yours1,000 rows18 columnsregion: UK only

blueprint · energy-consumption-forecasting

Behind this dataset

Same schema. As many rows as you need.

These 110 rows came out of a blueprint — 18 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

Meter readings must be monthly
Anomalies >20% from previous month flagged
New connections require baseline reading
Data gaps over two readings interpolated

Rows1,000 rows10,000 rows100,000 rows1,000,000 rows

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: energy-consumption-forecasting

What should your data show?

No signup. No card.

Sample rows

What the 110 rows show

Columns

Use it for

An energy dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Energy

What should your data show?