Skip to content

deepu7d/solarwise

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

73 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Solarwise – Solar Potential Estimator

Solarwise is a tool that helps users calculate the solar potential of their roofs using AI/ML models and geolocation data. It predicts solar energy generation over time and estimates the break-even period and environmental impact.


🚀 Features

1. Solar Potential Calculation

  • Users select a location and enter the roof area estimate.
  • AI/ML models predict solar radiation (SDLR) over the next 6–10 years based on historic data.
  • Converts predicted SDLR from W/m² to kWh adjusted for sunlight hours.
  • Displays results through interactive graphs.

2. Investment Payback Estimation

  • Estimates the break-even period based on initial investment and energy savings.
  • Example: A ₹1.5 lakh investment generating energy worth ₹1.5 lakh in 8 years = 8-year break-even point.

3. Environmental Impact

  • Shows the estimated CO₂ offset from generated solar energy.
  • Displays the equivalent number of trees saved based on offset data.

🛠️ Tech Stack

Frontend:

  • Next.js
  • TailwindCSS
  • Shadcn/ui

Backend:

  • Flask (Python)

AI/ML Model:

  • SARIMA model (trained on historic SDLR data from the CLARA weather dataset)

📦 Installation

  1. Clone the repository:
git clone https://github.com/RakshitRabugotra/solarwise.git
  1. Install dependencies:
cd solarwise  
npm install  
  1. Start the app:
cd web
npm run dev  
  1. Start the backend:
cd api  
python run.py 

🧪 Testing

  • Tested with real-time weather data.
  • Verified energy estimates and payback period accuracy.

👥 Contributors

  • Rakshit Rabugotra
  • Subhajit Das
  • Deepanshu Saini
  • Arjun Singh

📄 License

This project is licensed under the MIT License.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • TypeScript 73.3%
  • Python 24.2%
  • CSS 2.1%
  • Other 0.4%