Energy
20 columns
120 rows
8 formats

Smart Building Energy Optimization Metrics

This dataset provides granular, hourly IoT sensor readings from smart buildings, enriched with AI-predicted efficiency scores and actionable insights for energy optimization. It enables building managers and proptech innovators to analyze consumption patterns, estimate costs and emissions, and implement targeted sustainability improvements. Ideal for benchmarking, predictive analytics, and operational decision-making in energy management.

last updated 10 Dec 2025
by GoMask

The brief that made it

Real-time energy usage monitoring and anomaly detection

Sample rows

preview · 8 of 120 rows · all 20 columns

reading_idstring	sensor_typestring	energy_consumption_kwhfloat	insight_categorystring	building_idstring	building_namestring	address_streetstring	address_citystring	address_statestring	address_postal_codestring	address_countrystring	sensor_idstring	reading_timestampdatetime	temperature_celsiusfloat	humidity_percentfloat	occupancy_countinteger	ai_efficiency_scorefloat	cost_estimate_usdfloat	carbon_emission_kgfloat	actionable_insightstring
R001	electricity	24.1	blank	B101	Grant Office Tower	100 Grant Ave	Chicago	IL	60601	USA	S-EL01	2024-06-01T01:00:00Z	blank	blank	blank	74.4	4.31	12.8	blank
R002	temperature	13.5	blank	B102	Madison Research Center	45 Madison St	Boston	MA	02111	USA	S-TP01	2024-06-01T02:00:00Z	21.2	blank	blank	77.8	2.82	7.2	blank
R003	humidity	3.4	blank	B103	Orlando Mall	200 Orange Ave	Orlando	FL	32801	USA	S-HM01	2024-06-01T03:00:00Z	blank	48.7	blank	72.1	0.94	2.1	blank
R004	lighting	17.3	blank	B104	Starlight Factory	600 Industrial Rd	San Jose	CA	95112	USA	S-LG01	2024-06-01T04:00:00Z	blank	blank	blank	81.2	2.42	7.9	blank
R005	occupancy	41.7	scheduling	B105	Mercury Hospital	15 Mercury Blvd	New York	NY	10001	USA	S-OC01	2024-06-01T05:00:00Z	blank	blank	54	66.2	6.45	19.4	Consider scheduled lighting reduction during low occupancy periods.
R006	humidity	2.9	blank	B106	Solis Library	800 Solis Dr	Seattle	WA	98101	USA	S-HM02	2024-06-01T06:00:00Z	blank	62.3	blank	75.4	0.53	1.8	blank
R007	temperature	11.8	blank	B107	Eclipse School	120 Eclipse St	Toronto	ON	M5B1G6	Canada	S-TP02	2024-06-01T07:00:00Z	27.4	blank	blank	79.6	3.08	8.2	blank
R008	humidity	4.7	blank	B108	Phoenix Apartment	300 Desert Dr	Phoenix	AZ	85004	USA	S-HM03	2024-06-01T08:00:00Z	blank	85.9	blank	73.5	1.14	2.7	blank
R009	electricity	38.5	scheduling	B109	Lumen Commercial Plaza	500 Lumen Ave	San Francisco	CA	94103	USA	S-EL02	2024-06-01T09:00:00Z	blank	blank	blank	68.2	7.21	16.2	Review equipment schedules to reduce peak hour consumption.
R010	temperature	18.9	HVAC	B110	Berlin Research Hub	12 Alexanderplatz	Berlin	BE	10178	Germany	S-TP03	2024-06-01T10:00:00Z	54.7	blank	blank	50.2	3.97	11.9	HVAC alert: Unusual temperature spike detected. Check system.
R011	lighting	13.9	blank	B111	Sunrise Plant	250 Sunrise Blvd	Sydney	NSW	2000	Australia	S-LG02	2024-06-01T11:00:00Z	blank	blank	blank	77.4	2.13	5.7	blank
R012	occupancy	19	scheduling	B112	Denver Conference Center	101 Convention Ave	Denver	CO	80202	USA	S-OC02	2024-06-01T12:00:00Z	blank	blank	175	32.6	9.82	41.2	High occupancy: Consider staggered event scheduling to optimize HVAC load.
R013	temperature	16.6	blank	B113	Bright Hotel	300 Bright St	Stockholm	ST	11356	Sweden	S-TP04	2024-06-01T13:00:00Z	0	blank	blank	68.3	3.21	8.3	blank
R014	temperature	14.7	blank	B114	Cape Town School	21 Long St	Cape Town	WC	8001	South Africa	S-TP05	2024-06-01T14:00:00Z	36.6	blank	blank	75.1	3.42	9.5	blank
R015	occupancy	12.3	blank	B115	Rivera School	401 Rivera Rd	Vancouver	BC	V6B1W4	Canada	S-OC03	2024-06-01T15:00:00Z	blank	blank	19	77.9	3.19	7.2	blank
R016	humidity	1.7	blank	B116	Lyon Hotel	24 Rue Lyon	Paris	IDF	75015	France	S-HM04	2024-06-01T16:00:00Z	blank	100	blank	80.2	0.44	1.1	blank
R017	electricity	28.3	blank	B117	Gotham Plaza	600 Gotham Ave	Dallas	TX	75201	USA	S-EL03	2024-06-01T17:00:00Z	blank	blank	blank	70.1	5.35	15.1	blank
R018	electricity	92.2	HVAC	B118	Helios Office Tower	170 Helios Blvd	Miami	FL	33131	USA	S-EL04	2024-06-01T18:00:00Z	blank	blank	blank	62.9	16.72	44	High energy usage detected. Review HVAC operation for efficiency.
R019	lighting	6.1	blank	B119	Aurora Mall	75 Aurora Rd	Denver	CO	80204	USA	S-LG03	2024-06-01T19:00:00Z	blank	blank	blank	86.5	1.29	4.6	blank
R020	occupancy	55.9	scheduling	B120	Harbor Conference Center	900 Harbor St	San Diego	CA	92101	USA	S-OC04	2024-06-01T20:00:00Z	blank	blank	41	39.7	9.21	20.2	Occupancy high: Consider dynamic lighting and HVAC scheduling.

What the 120 rows show

from the 120-row sample

Electricity (sensor type) stands out: mean energy_consumption_kwh is 54.2, against 17.6 for the rest.

15.3median energy_consumption_kwh
8address countries
32address states
26.6median temperature_celsius
60.3median humidity_percent
41median occupancy_count

Mean energy_consumption_kwh by sensor_type120 rows

energy_consumption_kwh120 rows, in bands of 25

Median 15.3, from 0.0 to 250.0.

insight_category32 rows with a value · 88 left blank

scheduling9
HVAC9
other8
lighting6

20 columns by typefrom the column list below

string 12
integer 1
float 6
datetime 1

Columns

20 columns in three groups

blueprint · 20 columns
column	type	description	example
Text 12 columns
`reading_id`	string	Unique identifier for each hourly sensor reading recordunique	R001
`building_id`	string	Unique identifier for the building where the reading was taken	B101
`building_name`	string	Name of the buildingoptional	Grant Office Tower
`address_street`	string	Street address of the buildingoptional	100 Grant Ave
`address_city`	string	City where the building is locatedoptional	Chicago
`address_state`	string	State or province of the building locationoptional	IL
`address_postal_code`	string	Postal code of the building locationoptional	60601
`address_country`	string	Country of the building location8 countries · optional	USA
`sensor_id`	string	Unique identifier for the IoT sensor	S-EL01
`sensor_type`	string	Type of sensor (e.g., electricity, temperature, humidity, occupancy)electricity · temperature · humidity · occupancy · other	electricity
`actionable_insight`	string	AI-generated recommendation or insight for sustainability or cost reductionoptional	Consider scheduled lighti…
`insight_category`	string	Category of actionable insight (e.g., HVAC, lighting, occupancy, scheduling)HVAC · lighting · occupancy · scheduling · other · optional	scheduling
Numbers 7 columns
`energy_consumption_kwh`	float	Measured energy consumption in kilowatt-hours for the hour0 or more	24.1
`temperature_celsius`	float	Measured temperature in degrees Celsius (if applicable)-50 to 60 · optional	21.2
`humidity_percent`	float	Measured relative humidity percentage (if applicable)0 to 100 · optional	48.7
`occupancy_count`	integer	Number of occupants detected by sensors (if applicable)0 or more · optional	54
`ai_efficiency_score`	float	AI-predicted energy efficiency score for the hour (0-100 scale)0 to 100	74.4
`cost_estimate_usd`	float	Estimated energy cost in USD for the hour0 or more · optional	4.31
`carbon_emission_kg`	float	Estimated carbon emissions in kilograms for the hour0 or more · optional	12.8
Dates and times 1 column
`reading_timestamp`	datetime	Timestamp of the hourly sensor reading	2024-06-01T01:00:00Z

Use it for

An energy dashboard
Energy_consumption_kwh by sensor_type and a breakdown of insight_category. Excel, Power BI or Tableau.
Why do the 30 electricity rows have a mean energy_consumption_kwh of 54.2?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Readings120
R00124.1electric…
R00213.5temperat…
R0033.4humidity
A software demo
Believable readings with building_id, building_name and address_street to fill a screen in front of a buyer.

This dataset120 rows20 columns

Yours1,000 rows20 columnsaddress_street: UK only

blueprint · smart-building-energy-optimization-metrics

Behind this dataset

Same schema. As many rows as you need.

These 120 rows came out of a blueprint — 20 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

Sensor readings must include temperature, humidity, occupancy, and energy consumption.
Hourly data is aggregated daily for trend analysis.
AI-predicted energy efficiency scores are calculated only when occupancy exceeds 10 persons.
Actionable recommendations are generated for readings that exceed baseline consumption by 15%.
Maintenance alerts are triggered if sensor anomalies persist for three consecutive hours.

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: smart-building-energy-optimization-metrics

What should your data show?

No signup. No card.

Sample rows

What the 120 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?