Neural Network based Route Guidance Strategy in intelligent transportation systems

Abstract

Traffic congestion in urban areas presents a significant challenge to efficient transportation and sustainable urban development. This paper introduces a Neural Network based Route Guidance Strategy to address the non-linear complexities of urban traffic flow. The strategy demonstrates its capability to optimize traffic flow in real-time by predicting the travel times of candidate routes. A comprehensive simulation study compares the performance of the Neural Network Strategy with traditional traffic management strategies, focusing on traffic flow efficiency, vehicle count stability, and route choice optimization. The results indicate that the Neural Network Strategy significantly enhances traffic management by stabilizing vehicle counts, reducing fluctuations in traffic flux, and achieving a more uniform distribution of vehicles. The paper concludes with an analysis of the experimental results, highlighting the integration of neural networks into traffic management systems as a promising approach to mitigating urban traffic congestion. Future research directions are discussed, emphasizing the potential for real-world implementation and the exploration of advanced neural network models.