CPFT-MOSA: A Comprehensive Parallel Fault-Tolerant Multi-Objective Simulated Annealing Framework for UAV-Assisted Edge Computing in Smart City Traffic Management

UAV-assisted edge computingis increasingly being used in modern smart city traffic management systems for real-time monitoring and control. While the precicontext of these systems may vary depending on the availability of computational resources, a key challenge is managing the effective distribution of computational tasks amongstits various edge nodes while ensuring system reliability and performance. In this paper, we propose CPFT-MOSA (Comprehensive Parallel Fault-Tolerant Multi-Objective Simulated Annealing), a newtask allocation optimization framework for UAV-assisted edge computing scenarios. We combine parallel processing techniques and fault-tolerant mechanisms as well as identify a multi-objective simulated annealingtechnique to simultaneously optimize conflicting requirements in the system. The framework then decouplesYOLO-based object detection tasks into several parallelmodules within eachUAV processing block, and a dynamic resource management mechanism is implemented in that aims to balance the processing efficacy and reliability for a UAV system. An experimental evaluation, conducted across 17 nodes managing 45 full layers and comprising 270 total layer assignments, demonstrates CPFT-MOSA superior performance compared to traditional methods. Our results show that CPFT-MOSA maintains efficient resource utilization with an average of 16.8 active nodes, achieves a 21% improvement in energy distribution efficiency with a value of 0.063, and reduces execution time by 8.5% to 1.6 units compared to conventional approaches. The framework ability to balance multiple competing objectives while maintaining fault tolerance makes it particularly suitable for real-world traffic management applications where reliability and performance are crucial.