Residential Load Curve Clustering and Segmentation
This dataset provides detailed segmentation of residential electricity customers based on their load curve profiles, using clustering algorithms to identify distinct usage patterns such as daytime-at-home, evening-peak, overnight-charging, flat, and seasonal vacationers. It includes key consumption metrics, cluster assignments, and optional geographic information, making it ideal for targeted energy management, demand response planning, and customer behavior analysis.
Sample rows
preview · 8 of 200 rows · all 15 columns| customer_idstring | cluster_labelstring | peak_hourinteger | is_seasonal_vacationerboolean | address_countrystring | cluster_idinteger | clustering_methodstring | profile_start_datedate | profile_end_datedate | avg_daily_consumption_kwhfloat | peak_consumption_kwhfloat | address_streetstring | address_citystring | address_statestring | address_postal_codestring |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CUST101 | daytime-at-home | 11 | false | Canada | 1 | k-means | 2021-03-01 | 2021-08-31 | 15.9 | 5.4 | 892 Oakridge Ave | Victoria | BC | V8W 1A1 |
| user-204 | evening-peak | 20 | false | USA | 2 | hierarchical | 2022-01-15 | 2022-07-15 | 31.2 | 18.2 | 4559 Willow St | Chicago | IL | 60636 |
| A7_bT45x | overnight-charging | 2 | false | USA | 3 | k-means | 2020-11-01 | 2021-01-31 | 42.7 | 22.5 | 3016 Elmwood Dr | Dallas | TX | 75224 |
| client405 | flat | 12 | false | UK | 4 | hierarchical | 2023-05-01 | 2023-06-30 | 10.2 | 1.4 | 18 Stratton Rd | Manchester | Greater Manchester | M1 2AB |
| guest312 | seasonal-vacationer | 15 | true | France | 5 | k-means | 2022-07-01 | 2022-08-31 | 2.1 | 0.25 | 33 Côte d'Azur | Nice | Provence-Alpes-Côte d'Azur | 06200 |
| US_302_pwr | evening-peak | 21 | false | USA | 2 | k-means | 2022-06-01 | 2022-12-01 | 19.8 | 7.7 | 5501 Pine St | Atlanta | GA | 30318 |
| CUST102 | daytime-at-home | 14 | false | Canada | 1 | hierarchical | 2023-02-01 | 2023-07-31 | 13.7 | 4.8 | 98 Silver Birch Ave | Toronto | ON | M4E 1A1 |
| user-305 | overnight-charging | 0 | false | USA | 3 | hierarchical | 2021-09-01 | 2021-12-01 | 35.6 | 13.8 | 7081 Parkside Ln | Seattle | WA | 98115 |
| A9_cB67w | flat | 13 | false | Canada | 4 | k-means | 2022-10-01 | 2022-11-30 | 9.1 | 1.2 | 165 Wellington Ave | Ottawa | ON | K1A 0A9 |
| client506 | seasonal-vacationer | 8 | true | Switzerland | 5 | hierarchical | 2023-01-01 | 2023-03-31 | 1.6 | 0.07 | 27 Rue des Alpes | Geneva | Geneva | 1201 |
| CUST103 | daytime-at-home | 13 | false | Canada | 1 | k-means | 2024-02-01 | 2024-06-30 | 12.4 | 6.1 | 487 Maplewood Rd | Halifax | NS | B3H 1A1 |
| user-407 | evening-peak | 22 | false | USA | 2 | hierarchical | 2021-03-15 | 2021-09-15 | 27.3 | 9.4 | 7920 Mission St | San Jose | CA | 95125 |
| A3_bX78z | overnight-charging | 1 | false | USA | 3 | hierarchical | 2022-04-01 | 2022-07-01 | 150 | 75.5 | 1125 Main St | Houston | TX | 77002 |
| client607 | flat | 11 | false | UK | 4 | k-means | 2023-07-01 | 2023-08-31 | 12.7 | 2.1 | 241 King St | London | London | WC2N 5DU |
| guest413 | seasonal-vacationer | 7 | true | USA | 5 | hierarchical | 2021-12-01 | 2022-01-31 | 0.3 | 0.05 | 15 Oceanview Dr | Miami Beach | FL | 33139 |
| EU_410_pwr | evening-peak | 19 | false | France | 2 | k-means | 2020-03-01 | 2020-08-31 | 23.6 | 6.8 | 12 Rue Lafayette | Paris | Île-de-France | 75009 |
| CUST104 | daytime-at-home | 12 | false | Canada | 1 | hierarchical | 2022-09-01 | 2022-12-01 | 17.5 | 7.3 | 721 Spruce St | Montreal | QC | H3A 2B2 |
| user-508 | overnight-charging | 3 | false | USA | 3 | k-means | 2023-02-01 | 2023-05-01 | 28.2 | 12.3 | 8884 Lakeland Blvd | Orlando | FL | 32810 |
| A6_bZ82m | flat | 12 | false | Canada | 4 | hierarchical | 2022-05-01 | 2022-06-30 | 8.8 | 0.9 | 4200 Queen St | Vancouver | BC | V5K 1T8 |
| client708 | seasonal-vacationer | 17 | true | Canada | 5 | k-means | 2022-12-01 | 2023-01-31 | 0.1 | 0.09 | 44 Aspen Ridge | Whistler | BC | V0N 1B4 |
What the 200 rows show
from the 200-row sampleOvernight-charging (cluster label) stands out: mean peak_
- 20%is_
seasonal_ vacationer = true - 12median peak_
hour - 2clustering methods
- 55address states
- 15.4median avg_
daily_ consumption_ kwh - 5.7median peak_
consumption_ kwh
Median 12, from 0 to 23.
- string 8
- integer 2
- float 2
- date 2
- boolean 1
Columns
15 columns in four groups| column | type | description | example |
|---|---|---|---|
| Text 8 columns | |||
customer_id | string | Unique identifier for each residential electricity customerunique | CUST101 |
cluster_label | string | Descriptive label for the cluster (e.g., 'daytime-at-home', 'evening-peak', 'overnight-charging', 'flat', 'seasonal-vacationer')5 values | daytime-at-home |
clustering_method | string | Clustering algorithm used for segmentation (e.g., 'k-means', 'hierarchical')k-means · hierarchical | k-means |
address_street | string | Street address of the customeroptional | 892 Oakridge Ave |
address_city | string | City of the customeroptional | Victoria |
address_state | string | State or province of the customeroptional | BC |
address_postal_code | string | Postal or ZIP code of the customeroptional | V8W 1A1 |
address_country | string | Country of the customer7 countries · optional | Canada |
| Numbers 4 columns | |||
cluster_id | integer | Numeric identifier for the load profile cluster assigned to the customer1 or more | 1 |
avg_daily_consumption_kwh | float | Average daily electricity consumption in kilowatt-hours (kWh) during the profile period0 or more | 15.9 |
peak_hour | integer | Hour of the day (0-23) when the customer's electricity usage typically peaks0 to 23 | 11 |
peak_consumption_kwh | float | Maximum hourly electricity consumption in kilowatt-hours (kWh) during the profile period0 or more | 5.4 |
| Dates and times 2 columns | |||
profile_start_date | date | Start date of the load profile period analyzed for clustering | 2021-03-01 |
profile_end_date | date | End date of the load profile period analyzed for clustering | 2021-08-31 |
| True or false 1 column | |||
is_seasonal_vacationer | boolean | Indicates if the customer exhibits seasonal vacationer usage patterns | false |
Use it for
An energy dashboard
The is_
seasonal_ vacationer rate, peak_ hour by cluster_ label and a breakdown of address_ country. Excel, Power BI or Tableau. Why do the 40 overnight-charging rows have a mean peak_
hour of 1.4? A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
- Customers200CUST10111daytime-…guest31215seasonal…client5068seasonal…
A software demo
Believable customers with cluster_
id, cluster_ label and clustering_ method to fill a screen in front of a buyer.
This dataset200 rows15 columns
Yours1,000 rows15 columnsaddress_street: UK only
blueprint · residential-load-curve-clustering-and-segmentation
Behind this dataset
Same schema. As many rows as you need.
These 200 rows came out of a blueprint — 15 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
- Account number and customer demographic attributes
- Load profile cluster assignment (cluster 1-10)
- Cluster characteristics: peak hour, load factor, variability
- Average daily consumption (kWh) and peak demand (kW)
- Time-of-use behavior (morning, afternoon, evening, overnight)
- Seasonal variation (summer AC load, winter heat load)
- Electric vehicle (EV) charging signature detection
- Demand response program eligibility based on cluster
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
- residential-load-curve-clustering-and-segmentation