A multi objective optimization framework for smart parking using digital twin pareto front MDP and PSO for smart...

Area of Science:

• Urban Planning and Smart City Technology
• Optimization Algorithms and Artificial Intelligence
• Traffic Management Systems

Background:

• Existing smart parking systems struggle with resource management, scalability, and real-time adaptation.
• Inefficient parking management contributes to traffic congestion and increased energy consumption in urban areas.

Purpose of the Study:

• To propose a Multi-Objective Optimization Framework for Smart Parking (MOFPSP) integrating Digital Twin, Pareto Front Optimization, Markov Decision Process (MDP), and Particle Swarm Optimization (PSO).
• To enhance the efficiency of smart parking systems by minimizing search time, energy consumption, and traffic disruption while maximizing parking space availability.

Main Methods:

• Digital Twin Technology: Creation of a virtual model for real-time system estimation.
• Pareto Front Optimization: Multi-objective optimization to balance competing goals (e.g., minimize search time, maximize availability).
• Markov Decision Process (MDP) and Particle Swarm Optimization (PSO): For real-time decision-making and refining solutions for global distribution.

Main Results:

• The proposed framework demonstrated significant improvements over existing algorithms.
• Achieved a 25% reduction in search time, 18% improvement in energy usage, and 30% decrease in traffic congestion.
• Evaluated across key metrics including search time, energy consumption, congestion level, scalability, and utilization.

Conclusions:

• The hybrid optimization and real-time decision-making framework offers a promising solution for advanced smart parking management.
• The study highlights the potential of integrating advanced computational techniques to improve urban mobility and resource efficiency in smart cities.