Determining the Optimal Restricted Driving Zone Using Genetic Algorithm in a Smart City

Area of Science:

• Urban Planning and Traffic Management
• Computational Intelligence and Optimization Algorithms
• Environmental Science and Public Health

Background:

• Metropolitan traffic congestion poses significant challenges, impacting public health, emergency services, and citizen satisfaction.
• Current traffic control methods, such as restricting private vehicle access, face a trade-off between reducing traffic load and maintaining citizen mobility.
• Optimizing restricted traffic zones is a complex problem requiring intelligent solutions to balance competing objectives.

Purpose of the Study:

• To propose an intelligent method for selecting optimal restricted driving zones (ORDZ) to manage traffic congestion and air pollution.
• To enhance citizen satisfaction by intelligently balancing traffic load reduction with mobility.
• To develop a dynamic optimization approach for urban traffic management.

Main Methods:

• Utilized an augmented Genetic Algorithm combined with determinant theory to generate and evaluate potential restricted driving zones.
• Developed a fitness function that quantifies the trade-off between traffic load reduction and citizen satisfaction.
• Conducted simulation studies to compare ORDZ performance against existing traffic control methods.

Main Results:

• The proposed ORDZ method demonstrated superior performance in optimizing restricted traffic zones compared to current methods.
• Achieved significant improvements, exceeding 30.6% in a combined metric of reduced traffic load and enhanced citizen satisfaction.
• Effectively balanced the competing objectives of traffic control and citizen mobility.

Conclusions:

• ORDZ provides an effective intelligent solution for optimizing restricted driving zones in urban traffic management.
• The method offers a promising approach to mitigate traffic congestion and air pollution while improving citizen satisfaction.
• Highlights the potential of genetic algorithms in solving complex urban planning and traffic optimization problems.