Energy Consumption Optimization Of Proximity Detection Based On Mobile Edge Computing

With the development of intelligent transportation and autonomous driving,proximity detection of road networks has become a key technology for measuring the proximity relationship between vehicle users,which is of great significance for ensuring road safety and improving travel efficiency.However,proximity detection of road networks is a computationally intensive application with time delay constraints.As more and more vehicle users access the mobile edge computing proximity detection system,energy consumption becomes particularly prominent.To address this problem,this paper conducts in-depth research on the energy optimization of mobile edge computing proximity detection systems.First,the system structure of proximity detection is studied,and the state of the proximity detection system is represented by parameters.The delay and energy consumption of proximity detection tasks are analyzed,and the energy optimization problem model of the proximity detection system is established,and the objective function and constraints of the energy optimization problem are given.Secondly,an energy optimization algorithm based on genetic algorithm,particle swarm optimization,and deep Q-network is proposed to solve the energy optimization problem of the mobile edge computing proximity detection system.The energy optimization algorithm based on genetic algorithm simulates the process of natural selection through gene crossover and mutation operations,achieving traversal of the solution space.The energy optimization algorithm based on particle swarm optimization finds the optimal solution through iterative search,using the idea of particle swarm for global search and combining it with local search strategy.The energy optimization algorithm based on deep Q-network establishes the state-action-reward model of the system through deep reinforcement learning,and uses neural networks to learn the value function to achieve energy optimization.Simulation results show that compared with other algorithms,the proposed algorithms have faster convergence speed and better energy optimization effect.Finally,the proposed algorithms are applied to mobile edge computing proximity detection system and cloud-edge collaborative proximity detection system scenarios.Through simulation experiments,the proposed algorithms are verified to be significantly superior to other algorithms in terms of convergence speed and energy optimization effect,effectively solving the energy optimization problem.This research significantly alleviates the energy pressure of proximity detection systems,expands the application scenarios of proximity detection,and provides a new perspective and solution for energy optimization problems in the field of mobile edge computing proximity detection,providing strong support for achieving more efficient intelligent transportation and autonomous driving,with high practical value and broad application prospects.