AI-Powered Smart Traffic Signal System with Emergency Vehicle Priority and Power Optimization

Traffic congestion and delayed emergency responses are pressing issues in modern urban environments. Conventional traffic signal systems operate on pre-set timers, lacking the flexibility to adapt to real-time traffic flow. This results in unnecessary waiting times, increased fuel consumption, and severe delays for emergency vehicles such as ambulances and fire trucks. To address these challenges, this paper proposes an AI-powered smart traffic signal system that integrates Artificial Intelligence (AI), wireless sensor networks (WSN), and renewable energy solutions. The system employs Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models to predict traffic density and adjust signal timings dynamically. Vehicle-to- Everything (V2X) communication enables emergency vehicles to transmit real-time priority requests, creating “green corridors” for faster transit. Additionally, the traffic lights are powered by solar panels, reducing grid dependency by 85 percentage. Simulation results show a 35 percentage reduction in congestion, a 40 percentage improvement in emergency response times, and significant energy savings. This paper presents the design, methodology, and real-world implications of integrating AI, V2X technology, and renewable energy into a single, scalable traffic management system, offering a sustainable solution for future smart cities.