All demo datasets

Water — Large Utility

Sunbelt Regional Water (synthetic)
Guided tour Sample data · no sign-up
Aggregation Weather normalization M&V savings Benchmarking (EUI) Load & demand Seasonal & outdoor use Distribution & inequality Energy burden Map & clustering Class × time Differential privacy Data quality
Disclosure control Suppression k = 15 1 customer ≤ 15% complementary on Methods & formulas
Restore industry minimums
Weather-sensitive
0.0%
weather-insensitive
Base load / month
310
base consumption / account
Degree days
2473 HDD
2158 CDD
Fit quality (R²)
0.668
over 11 months

Consumption vs. degree days, by month

energy vs. °F·days

Each point is one month: average consumption per account against that month's heating + cooling degree days. A steeper rise means more weather-sensitive load.

The model

E = 310 + -0.3252·HDD

  • Heating slope: -0.3252 / HDD
  • Gas — heating-only model (no cooling term)
  • Weather-normalized annual: needs a full year
Method: base-65°F degree days (US EIA / NOAA); degree-day regression (ASHRAE Guideline 14; PRISM (Princeton Scorekeeping Method)).