Skip to content

Production-ready R/Shiny application for smart meter analytics featuring multi-algorithm anomaly detection (IQR, Z-Score, STL, Moving Average), k-means pattern clustering, and rate plan cost optimization with automated Excel reporting.

Notifications You must be signed in to change notification settings

SumedhSankhe/PG-E-Data-Visualizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

97 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PG&E Data Visualizer

CI Status R Version License

An R Shiny application that analyzes smart meter energy data through quality control, anomaly detection, pattern recognition, and cost optimization.

Live Demo | Contributing


Architecture

Architecture


Features

  • 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

Quick Start

git clone https://github.com/SumedhSankhe/PG-E-Data-Visualizer.git
cd PG-E-Data-Visualizer
renv::restore()        # Install dependencies
shiny::runApp('.')     # Launch the app

Data Format

Upload 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.


Automated Data Updates

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.R

License

MIT License - see LICENSE for details.


Author: Sumedh Sankhe

About

Production-ready R/Shiny application for smart meter analytics featuring multi-algorithm anomaly detection (IQR, Z-Score, STL, Moving Average), k-means pattern clustering, and rate plan cost optimization with automated Excel reporting.

Topics

Resources

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 5