Mini-project
Energy, Power & Utilities
Household energy use forecaster
Forecast a home's electricity use and show where the energy goes.
The brief
An electricity distribution company wants to help households cut their bills. Using smart-meter style readings, forecast tomorrow's consumption hour by hour and show which appliances and times drive the most use. Good looks like: a forecast that beats a simple seasonal baseline, and charts a household would understand.
What you will build
- Clean the readings and resample to hourly
- Explore daily and weekly patterns
- Build a baseline and a machine-learning forecast
- Compare errors (MAE, MAPE) against the baseline
- Make a simple dashboard with tips based on the patterns
Free, open data to build it with
- Individual Household Electric Power Consumption ↗ UCI Machine Learning Repository
- Appliances Energy Prediction ↗ UCI Machine Learning Repository
Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.