An R Shiny application that analyzes smart meter energy data through quality control, anomaly detection, pattern recognition, and cost optimization.
- Quality Control: Outlier detection, missing value analysis, and quality scoring
- Anomaly Detection: Four algorithms (IQR, Z-Score, STL, Moving Average) with configurable sensitivity
- Pattern Recognition: Daily/weekly patterns and k-means load curve clustering
- Cost Optimization: Rate plan comparison (TOU, Tiered, EV rates) with savings recommendations
- Export: One-click Excel report with all analyses
git clone https://github.com/SumedhSankhe/PG-E-Data-Visualizer.git
cd PG-E-Data-Visualizerrenv::restore() # Install dependencies
shiny::runApp('.') # Launch the appUpload CSV/TSV files with these required columns:
| Column | Type | Description |
|---|---|---|
dttm_start |
DateTime | Timestamp (YYYY-MM-DD HH:MM:SS) |
hour |
Numeric | Hour of day (0-23) |
value |
Numeric | Energy consumption (kWh) |
day |
Numeric | Day identifier |
day2 |
Numeric | Secondary day identifier |
Sample data is included at data/meterData.rds.
PG&E customers can automate daily data fetching from smart meters. See docs/automation/ for setup instructions.
Quick option - Process manual PGE downloads:
Rscript scripts/automation/convert_pge_download_v2.RMIT License - see LICENSE for details.
Author: Sumedh Sankhe