An intelligent platform that helps users optimize their electricity consumption using AI-powered analytics, Non-Intrusive Load Monitoring (NILM), and personalized recommendations.
- Time Series Analysis: Advanced consumption prediction using foundation models
- Device Detection: OCR-based automatic device identification and power estimation
- NILM Technology: Individual appliance load disaggregation
- AI Chatbot: Personalized optimization suggestions with multi-language support
- Real-time Analytics: Live consumption monitoring and statistics
- Multi-language Support: TTS/STT in Hindi, Bengali, Tamil, Telugu, and more
UrjaBandhu/
├── frontend/ # Next.js React application
├── backend/ # FastAPI Python backend
├── ml-models/ # ML models and training scripts
├── docs/ # Documentation and API specs
└── docker/ # Docker configuration files
- Framework: Next.js 14 with TypeScript
- UI: Tailwind CSS + Shadcn/UI
- State Management: Zustand
- Charts: Chart.js + D3.js
- PWA: Next-PWA
- Backend: Supabase (PostgreSQL + Auth + Real-time + Storage)
- Authentication: Supabase Auth with Google OAuth
- Database: Supabase PostgreSQL with Row Level Security
- Real-time: Supabase Real-time subscriptions
- File Storage: Supabase Storage (for device images)
- Time Series: Prophet, LSTM, Transformers
- NILM: HMM, Neural Networks
- OCR: Tesseract, Google Vision API
- NLP: Transformers, OpenAI GPT
- TTS/STT: Azure Cognitive Services
- Time Series Analytics: InfluxDB (optional)
- Node.js 18+
- Supabase Account (free tier available)
- Docker (optional, for additional services)
- Clone the repository
git clone https://github.com/SrivarsanK/UrjaBandhu.git
cd urjabandhu- Setup Supabase
- Create a new project at supabase.com
- Copy your project URL and anon key
- Run the SQL schema from
supabase/schema.sqlin your Supabase SQL editor
- Setup Frontend
cd frontend
npm install
cp .env.local.example .env.local
# Edit .env.local with your Supabase credentials
npm run dev- Access the Application
- Frontend: http://localhost:3000
- Supabase Dashboard: Your project dashboard
- Optional: Setup Additional Services
# For advanced analytics with InfluxDB
docker-compose --profile analytics up -d
# For caching with Redis
docker-compose --profile cache up -d- Project structure setup
- Basic UI mockups
- Sample data integration
- OCR device detection
- Time series data handling
- Basic analytics
- NILM implementation
- Time series foundation models
- Advanced visualizations
- AI chatbot
- Personalized recommendations
- Multi-language TTS/STT
This project is licensed under the MIT License - see the LICENSE file for details.
- Time Series Foundation Models research community
- NILM algorithm developers
- Open source ML/AI libraries
- Indian language processing tools
Note: This project is under active development. Check the Plan.md for detailed development timeline and progress updates.