System-Wide Hourly Load Profile and Forecasting
This dataset provides comprehensive, system-wide hourly load profiles including actual measured loads, day-ahead forecasts, weather-normalized curves, and peak demand indicators for capacity planning and generation scheduling. It is enriched with weather data and flags for peak events, making it ideal for grid reliability analysis, forecasting, and operational decision support.
Sample rows
preview · 8 of 150 rows · all 11 columns| record_idstring | peak_demand_typestring | forecast_load_mwfloat | peak_demand_flagboolean | service_territorystring | timestampdatetime | actual_load_mwfloat | weather_normalized_load_mwfloat | temperature_cfloat | humidity_percentfloat | notesstring |
|---|---|---|---|---|---|---|---|---|---|---|
| rec-0001 | monthly_peak | 1698.5 | true | TX-North | 2024-07-01T17:00:00Z | 1754.2 | 1577.9 | 40.2 | 57.1 | July peak, heatwave across North Texas |
| rec-0002 | seasonal_peak | 1645 | true | NYC-East | 2024-07-01T18:00:00Z | 1702.6 | 1502.4 | 36.4 | 69.9 | Summer peak, high humidity after thunderstorm |
| rec-0003 | monthly_peak | 1632.5 | true | CA-Central | 2024-07-01T19:00:00Z | 1689.1 | 1588.2 | 39 | 33.2 | Central CA July peak, grid adjustments |
| rec-0004 | none | 436.8 | false | FL-South | 2024-07-02T06:00:00Z | 412.9 | 418.5 | 26.7 | 81.2 | blank |
| rec-0005 | none | 570.5 | false | WA-Puget | 2024-07-02T07:00:00Z | 551.2 | 590.1 | 14.9 | 61.8 | Morning baseline |
| rec-0006 | none | 0 | false | NY-Upstate | 2024-07-02T08:00:00Z | 0 | 0 | blank | blank | System outage, transmission fault |
| rec-0007 | none | blank | false | CO-Rockies | 2024-07-02T09:00:00Z | 633.4 | blank | 12.1 | 38.4 | Forecast data unavailable |
| rec-0008 | none | 864.2 | false | CA-Central | 2024-07-02T10:00:00Z | 851.6 | 825.7 | 25.3 | 44 | Typical mid-morning ramp |
| rec-0009 | none | blank | false | TX-North | 2024-07-02T11:00:00Z | 1102.9 | blank | 32.8 | 50.1 | Sensor error, no forecast |
| rec-0010 | seasonal_peak | 1478.4 | true | FL-South | 2024-07-02T12:00:00Z | 1505 | 1435.2 | 37.8 | 68.4 | Summer peak, high cooling demand |
| rec-0011 | monthly_peak | 1392.3 | true | CO-Rockies | 2024-07-02T13:00:00Z | 1418.7 | 1322.8 | 33.6 | 21.2 | July peak, Rockies heat event |
| rec-0012 | seasonal_peak | 1479.2 | true | WA-Puget | 2024-07-02T14:00:00Z | 1532.4 | 1501.9 | 31.1 | 30.7 | Unusually warm Puget summer peak |
| rec-0013 | monthly_peak | 1265.3 | true | NYC-East | 2024-07-02T15:00:00Z | 1303.6 | 1222.6 | 32.7 | 67 | Peak demand: NYC heat & humidity |
| rec-0014 | none | 812.2 | false | TX-North | 2024-07-02T16:00:00Z | 784.4 | 760.6 | 30.5 | 58.9 | Afternoon baseline |
| rec-0015 | annual_peak | 1699.4 | true | NYC-East | 2024-07-02T17:00:00Z | 1722.2 | 1589.3 | 40.9 | 60.2 | Annual system peak, record NYC heat |
| rec-0016 | annual_peak | 1721.5 | true | TX-North | 2024-07-02T18:00:00Z | 1757.8 | 1590.2 | 44.1 | 36.5 | Annual peak, extreme heat alert |
| rec-0017 | none | 811.8 | false | NY-Upstate | 2024-07-02T19:00:00Z | 835.2 | 799.9 | 21.2 | 53.3 | blank |
| rec-0018 | none | 399.9 | false | CA-Central | 2024-07-03T06:00:00Z | 405.6 | 380 | 23.3 | 41.7 | Spring baseline |
| rec-0019 | none | 661 | false | WA-Puget | 2024-07-03T07:00:00Z | 667.1 | 648.9 | 13.4 | 60.2 | Typical morning |
| rec-0020 | none | blank | false | CO-Rockies | 2024-07-03T08:00:00Z | 0 | blank | blank | blank | Sensor test, all loads zero |
What the 150 rows show
from the 150-row sampleNone (peak demand type) stands out: mean forecast_
- 41%peak_
demand_ flag = true - 912.0median forecast_
load_ mw - 902.4median actual_
load_ mw - 910.3median weather_
normalized_ load_ mw - 27.7median temperature_
c - 51.0median humidity_
percent
Median 912.0, from 0.0 to 1,750.
- string 4
- float 5
- datetime 1
- boolean 1
Columns
11 columns in four groups| column | type | description | example |
|---|---|---|---|
| Text 4 columns | |||
record_id | string | Unique identifier for each hourly load recordunique | rec-0001 |
peak_demand_type | string | Type of peak demand (e.g., annual_peak, monthly_peak, seasonal_peak, none)annual_peak · monthly_peak · seasonal_peak · none · optional | monthly_peak |
service_territory | string | Name or code of the service territory covered by this record7 territories | TX-North |
notes | string | Additional notes or comments about the record (e.g., anomalies, events, adjustments)optional | Morning baseline |
| Numbers 5 columns | |||
actual_load_mw | float | Actual measured load in megawatts (MW) for the hour0 or more | 1754.2 |
forecast_load_mw | float | Day-ahead forecasted load in megawatts (MW) for the hour0 or more · optional | 1698.5 |
weather_normalized_load_mw | float | Weather-normalized load in megawatts (MW) for the hour, adjusted for typical weather conditions0 or more · optional | 1577.9 |
temperature_c | float | Average temperature in Celsius for the hour in the service territoryoptional | 40.2 |
humidity_percent | float | Average relative humidity percentage for the hour in the service territory0 to 100 · optional | 57.1 |
| Dates and times 1 column | |||
timestamp | datetime | Date and hour for which the load data is recorded (UTC) | 2024-07-01T17:00:00Z |
| True or false 1 column | |||
peak_demand_flag | boolean | Indicates if this hour is a system peak demand hour (true/false) | true |
Use it for
An energy dashboard
The peak_
demand_ flag rate, forecast_ load_ mw by peak_ demand_ type and a breakdown of service_ territory. Excel, Power BI or Tableau. Why do the 79 none rows have a mean forecast_
load_ mw of 654.8? A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
- Records150rec-00011698.5monthly_…rec-00021645seasonal…rec-0004436.8none
A software demo
Believable records with timestamp, actual_
load_ mw and forecast_ load_ mw to fill a screen in front of a buyer.
This dataset150 rows11 columns
Yours1,000 rows11 columnsservice_territory: UK only
blueprint · system-wide-hourly-load-profile-and-forecasting
Behind this dataset
Same schema. As many rows as you need.
These 150 rows came out of a blueprint — 11 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
- Timestamp hourly intervals with DST handling
- Actual load (MW) and reactive load (MVAR)
- Day-ahead forecast and forecast error (actual - forecast)
- Weather variables: temperature, humidity, wind speed, cloud cover
- Load factor = average load / peak load
- Peak demand timestamp and magnitude for planning reserve margin
- Weather normalization using regression models
- Seasonal patterns (summer cooling, winter heating peaks)
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
- system-wide-hourly-load-profile-and-forecasting