Adaptive Smart Queue System is a cloud-native application that monitors real-time queue data, predicts waiting times, and dynamically optimizes service allocation.
The system demonstrates how cloud computing enables:
- Real-time data processing
- Scalable architecture
- Intelligent decision-making
Frontend (React) → API Gateway → FastAPI Backend → DynamoDB
↓
ML Prediction Module
- Backend deployed via Docker on EC2
- Serverless functions (optional) for event-driven processing
- NoSQL database for scalable storage
- Real-time queue monitoring
- Waiting time prediction (ML-based)
- Dynamic service optimization (decision engine)
- Scalable cloud deployment
- Simulation support for testing scenarios
Frontend
- React
Backend
- FastAPI
- Docker
Machine Learning
- Python (scikit-learn / simple regression)
- Model serialization (pickle)
Cloud
- EC2 (compute)
- DynamoDB (database)
- Lambda (optional event processing)
frontend/→ User interfacebackend/→ API and core logicml/→ Machine learning pipelineinfrastructure/→ Cloud deployment configsscripts/→ Simulation & utilitiesdocs/→ System design & diagrams
-
Data Simulation
Queue events are generated via scripts or user input. -
Data Processing
Backend ingests and stores queue data in DynamoDB. -
Prediction
ML model estimates waiting time based on:- queue length
- service rate
- arrival patterns
-
Decision Engine
System evaluates load and suggests:- opening new counters
- redistributing queues
-
Visualization
Frontend displays real-time queue insights.
- Clone repository
- Configure environment variables
- Run backend (Docker)
- Run frontend
- Deploy to cloud (EC2)
- Real-time streaming (Kafka/Kinesis)
- Advanced ML (time-series forecasting)
- Auto-scaling integration
- Multi-location queue optimization
MIT License