Advanced Artificial Intelligence Strategy for Optimizing Urban Rail Network Design using Nature-Inspired Algorithms
Hariram Sampath Kumar, Archana Singh, Manish Kumar Ojha
TL;DR
The paper tackles urban rail network design in fast-changing cities by integrating a modified Ant Colony Optimization with GIS and real-time data to optimize routes and station stops. It demonstrates superiority of the modified ACO over other nature-inspired algorithms, and applies the approach to Chennai to derive a Tambaram–Sholingnallur route with intermediate stops while comparing against the existing network. The study reports substantial operational gains, including reduced workforce, planning time, and project cost, and also verifies consistency with existing routes through comparative testing. The framework leverages land-use, demographic, and POI data via Google Maps in a Jupyter-Python environment, offering a data-driven, scalable tool for sustainable urban transport planning with potential applicability to other modes and cities.
Abstract
This study introduces an innovative methodology for the planning of metro network routes within the urban environment of Chennai, Tamil Nadu, India. A comparative analysis of the modified Ant Colony Optimization (ACO) method (previously developed) with recent breakthroughs in nature-inspired algorithms demonstrates the modified ACO's superiority over modern techniques. By utilizing the modified ACO algorithm, the most efficient routes connecting the origin and destination of the metro route are generated. Additionally, the model is applied to the existing metro network to highlight variations between the model's results and the current network. The Google Maps platform, integrated with Python, handles real-time data, including land utilization, Geographical Information Systems (GIS) data, census information, and points of interest. This processing enables the identification of stops within the city and along the chosen routes. The resulting metro network showcases substantial benefits compared to conventional route planning methods, with noteworthy enhancements in workforce productivity, decreased planning time, and cost-efficiency. This study significantly enhances the efficiency of urban transport systems, specifically in rapidly changing metropolitan settings such as chennai.