AI Traffic Optimisation System

AI-Driven Predictive Traffic Flow Optimisation System

👥 Research Team

📈 Performance Targets

Project Goal: Target 15-20% reduction in urban traffic congestion for the Athlone "Orange Loop" using Reinforcement Learning.

Average Travel Time (ATT): Target -15%

Mean Queue Length (MQL): Target -20%

Data Integrity: TLS 1.3 secured telemetry pipeline

🔗 Quick Links

🌐 API Gateway	🤖 Inference Service	🧠 LSTM Predictor
App	App	App
Swagger UI Docs	Fast API Docs	Fast API Docs
Local: `8080`	Local: `8000`	Local: `8001`

🏗️ System Architecture

This repository implements a Cloud-Native Microservices Pipeline designed for the Athlone "Orange Loop" case study.

Traffic Monitoring Gateway (Java/Spring Boot): Manages secure telemetry ingestion and orchestrates service communication with JWT authentication.
RL-Inference Service (Python/FastAPI): Hosts a trained PPO (Proximal Policy Optimization) model to predict optimal signal timings based on real-time traffic density.
LSTM Traffic Predictor (Python/FastAPI): Forecasts vehicle flow 15 minutes ahead using historical SUMO data for context-aware decision making.
Simulation Layer (SUMO): Integrated high-fidelity environment for testing adaptive signal logic against baseline fixed-time controllers.

This system is specifically modeled to address the saturation flow rates and signal-timing patterns of the Athlone 'Orange Loop' corridor, providing a scalable template for Smart City traffic management.

For more details see System Architecture page.

📚 Service Documentation

Java API Gateway — JWT authentication, traffic prediction endpoints, circuit breaker resilience
Python Inference Service — PPO model inference, GRU hidden state management
LSTM Traffic Predictor — Time-series forecasting, SUMO data integration
SUMO Simulator — Road network, traffic flows, output data generation

🔐 Security

JWT authentication is integrated into the API Gateway. See Java API Gateway Authentication Guide for configuration and usage.