Research on Optimal Path Algorithms for Urban Traffic Systems Based on the Internet of Things

Background: With the rapid pace of global urbanization, urban traffic congestion critically restricts development. Traditional systems struggle with increasing demands, especially during peak periods. The study proposes a dynamic path planning algorithm based on deep learning, which leverages comprehensive analysis of real-time data from multiple sources, such as vehicle position, speed, and direction, along with historical traffic flow patterns and prediction models. The algorithm is designed to quickly respond to changes in the complex traffic environment and provide drivers with optimal driving routes. Results Achieved: Experimental results indicate that the proposed algorithm significantly reduces the average travel time of vehicles compared to traditional static path planning methods. It also improves the efficiency of road resources, demonstrating its potential in practical applications. The dynamic path planning method achieved an average travel time reduction from 32.5 minutes to 27.8 minutes during the morning rush hour. Concluding Remarks: The IoT-based optimal path algorithm effectively alleviates traffic pressure and enhances road network efficiency. Real-time adjustments and personalized path options increase flexibility and user satisfaction.