• Energy
  • 21 columns
  • 201 rows
  • 8 formats

Smart Grid Fault Detection Dataset

This dataset provides detailed synthetic logs of sensor readings, outage events, and fault detections across smart grid substations. It enables comprehensive analysis of grid reliability, fault diagnosis, and response strategies, supporting research and development in smart grid resilience and automation. The flat schema ensures compatibility with a wide range of analytics and machine learning applications.

  • opened 13 times
  • last updated 29 Jul 2025
  • by GoMask
The brief that made it

Automated fault detection and diagnosis in smart grid networks

Sample rows

preview · 8 of 201 rows · all 21 columns
substation_idstringsensor_typestringsensor_readingfloatfault_detectedbooleanoutage_typestringsubstation_namestringlocation_latitudefloatlocation_longitudefloatsensor_idstringreading_unitstringreading_timestampdatetimeoutage_idstringoutage_start_timedatetimeoutage_end_timedatetimeoutage_duration_minutesfloatfault_typestringfault_severityintegerresponse_actionstringresponse_timestampdatetimeoperator_idstringremarksstring
SS-1001voltage412.9falseblankGrand Oak North38.8977-77.0365SEN-10001V2023-01-15T10:23:12ZblankblankblankblanknoneblanknoneblankblankVoltage reading within normal operating range. Routine inspection.
SS-1002current215.3falseblankSilver Valley51.5099-0.1181SEN-10023A2023-01-15T11:05:44ZblankblankblankblanknoneblanknoneblankblankRoutine current sensor check completed. All values nominal.
SS-2001breaker_status1falseblankLakeside Relay Station-33.8679151.2073SEN-10011status2023-01-15T12:17:22ZblankblankblankblanknoneblanknoneblankblankBreaker status is closed. System operating as expected.
SS-3001temperature28.5falseblankCoral Coast Substation-23.698133.8807SEN-10009°C2023-01-15T13:45:01ZblankblankblankblanknoneblanknoneblankblankAmbient temperature within expected daytime range.
SS-4001frequency60.01falseblankAurora Gateway60.169524.9354SEN-10014Hz2023-01-15T14:08:30ZblankblankblankblanknoneblanknoneblankblankFrequency steady at 60 Hz setpoint. No anomalies detected.
SS-5001other0falseblankEquator City036.8219SEN-10101unitless2023-01-15T14:59:17ZblankblankblankblanknoneblanknoneblankblankEdge case: sensor at equator reporting zero reading for calibration.
SS-6001voltage780.5falseblankPolar Outpost89.9999-135SEN-10007V2023-01-15T15:11:32ZblankblankblankblanknoneblanknoneblankblankRoutine voltage reading at northernmost substation.
SS-7001temperature44.1falseblankDesert Ridge25.27698755.296249SEN-10012°C2023-01-15T16:56:10ZblankblankblankblanknoneblanknoneblankblankHigh ambient temperature due to midday desert conditions.

What the 201 rows show

from the 201-row sample

Other (sensor type) stands out: mean sensor_reading is 36,529, against 136.2 for the rest.

  • 16%fault_detected = true
  • 35.0median sensor_reading
  • 5response actions
  • 6fault types
  • 7reading units
  • 25median outage_duration_minutes
Mean sensor_reading by sensor_type201 rows
020k40k424.1volt…36 ro…226.3curr…31 ro…21.0temp…33 ro…0.53brea…30 ro…60.3freq…23 ro…5.0power27 ro…36,529other21 ro…
sensor_reading201 rows, in bands of 20k
095190121810107-20k40k100ksensor_reading →

Median 35.0, from -55.0 to 100,000.

outage_type21 rows with a value · 180 left blank
  1. planned_maintenance7
  2. equipment_failure6
  3. unknown5
  4. weather3
21 columns by typefrom the column list below
  • string 11
  • integer 1
  • float 4
  • datetime 4
  • boolean 1

Columns

21 columns in four groups
blueprint · 21 columns
columntypedescriptionexample
Text 11 columns
substation_idstringUnique identifier for the smart grid substation where the data was recorded.SS-1001
substation_namestringDescriptive name of the substation.optionalGrand Oak North
sensor_idstringUnique identifier for the sensor within the substation.SEN-10001
sensor_typestringType or category of the sensor (e.g., voltage, current, temperature, breaker status).7 valuesvoltage
reading_unitstringUnit of measurement for the sensor reading (e.g., V, A, °C, Hz, MW).7 unitsV
outage_idstringUnique identifier for the outage event, if applicable.optionalOUT-2033
outage_typestringType of outage event (e.g., equipment_failure, weather, planned_maintenance, unknown).5 values · optionalplanned_maintenance
fault_typestringType of fault detected (e.g., short_circuit, overload, open_circuit, ground_fault, unknown).7 values · optionalnone
response_actionstringAction taken in response to the detected fault or outage (e.g., isolation, reroute, manual_reset, none).isolation · reroute · manual_reset · none · other · optionalnone
operator_idstringIdentifier for the operator or system that initiated the response.optionalOP-14
remarksstringAdditional notes or comments related to the event, sensor reading, or response.optionalVoltage reading within no…
Numbers 5 columns
location_latitudefloatLatitude coordinate of the substation.-90 to 90 · optional38.8977
location_longitudefloatLongitude coordinate of the substation.-180 to 180 · optional-77.0365
sensor_readingfloatValue recorded by the sensor at the given timestamp.412.9
outage_duration_minutesfloatDuration of the outage in minutes.0 or more · optional120
fault_severityintegerSeverity rating of the detected fault (e.g., 1=Low, 5=Critical).1 to 5 · optional5
Dates and times 4 columns
reading_timestampdatetimeDate and time when the sensor reading was recorded.2023-01-15T10:23:12Z
outage_start_timedatetimeTimestamp when the outage started.optional2023-01-16T01:00:00Z
outage_end_timedatetimeTimestamp when the outage ended.optional2023-01-16T03:00:00Z
response_timestampdatetimeTimestamp when the response action was initiated.optional2023-01-16T03:02:00Z
True or false 1 column
fault_detectedbooleanIndicates whether a fault was detected in this record.false

15 SQL practice questions for the Smart Grid Fault Detection Dataset

Written for this data and checked against it: 12 SQL and 3 Power BI exercises from beginner to advanced. Try the first three free; the practice kit has all 15, a starter .sql file and an answer key with every expected result.

  1. 01BeginnerFreeSELECT · WHERE · ORDER BY

    Faulty readings list

    Return the columns sensor_id, sensor_type, sensor_reading and fault_type for every row where fault_detected = 1. Order the results by sensor_id ascending, then by reading_timestamp ascending.

    Tables: smart_grid_fault_detection_dataset · your result: 4 columns, 32 rows
  2. 02BeginnerFreeDISTINCT · WHERE

    Distinct fault types

    Return the distinct fault_type values among rows where fault_detected = 1, as a single column named fault_type, ordered alphabetically.

    Tables: smart_grid_fault_detection_dataset · your result: 1 columns, 5 rows
  3. 03BeginnerFreeGROUP BY · COUNT

    Readings per sensor type

    Return sensor_type and the number of rows for each type as reading_count. Order by reading_count descending, then by sensor_type ascending.

    Tables: smart_grid_fault_detection_dataset · your result: 2 columns, 7 rows
  1. 04Average outage duration by typeBeginner
  2. 05Fault count bar chart by fault typePower BI
  3. 06Substations with multiple faultsIntermediate
  4. 07Outage duration bucketsIntermediate
  5. 08Readings per monthIntermediate
  6. 09Outages longer than averageIntermediate
  7. 10Average outage minutes by causePower BI
  8. 11Rank faults by severityAdvanced
  9. 12Gap since previous readingAdvanced
  10. 13Running total of outage minutesAdvanced
  11. 14Share of faults by sensor typeAdvanced
  12. 15Fault share by sensor type visualPower BI

Get the practice kit: the full dataset, all 15 exercises, a starter .sql and the answer key. One-time $3.99.

Get the practice kit · $3.99

Use it for

  • fault detected16%32 of 201 rowsmean sensor reading b…424.1volt…226.3curr…21.0temp…0.53brea…

    An energy dashboard

    The fault_detected rate, sensor_reading by sensor_type and a breakdown of outage_type. Excel, Power BI or Tableau.

  • Why do the 21 other rows have a mean sensor_reading of 36,529?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable substations with substation_name, location_latitude and location_longitude to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 21 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset201 rows21 columns
Yours1,000 rows21 columnslocation_latitude: UK only

blueprint · smart-grid-fault-detection-dataset

Behind this dataset

Same schema. As many rows as you need.

These 201 rows came out of a blueprint — 21 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
  • Substations have unique IDs and geo-coordinates
  • Fault events timestamped and classified
  • Sensor readings spike during faults
  • Weather conditions recorded for each event
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-grid-fault-detection-dataset

What should your data show?

Preview 20 rows free
No signup. No card.