Research On WSN Network Coverage Optimization Control Based On Improved Particle Swarm Optimization Algorithm

One of the core research issues of wireless sensor networks is network coverage optimization control.The coverage rate reflects the network performance and service quality of WSN to a certain extent.However,in the actual environment,most of the nodes are randomly deployed in a sprinkling method,which may cause problems such as monitoring blind spots and node redundancy.The monitoring task cannot be successfully completed and is not conducive to prolonging the network life cycle.Therefore,it is crucial to deploy nodes with an efficient coverage optimization plan.important.With the maturity and development of intelligent algorithms in the optimization problem,it can be used as an effective means to solve the coverage optimization problem of wireless sensor networks.Therefore,this paper conducts research on WSN network node deployment based on particle swarm algorithm.The main work is as follows:(1)A fruit fly particle swarm hybrid optimization algorithm FFPSO(Fruit Fly and particle swarm hybrid optimization algorithm,FFPSO)is proposed.In the objective function optimization model,the network coverage rate is used as the optimization factor.In the initial stage of the iteration,the initial particles are mapped through chaos and multi-directional learning,which effectively enriches the diversity of the initial population,and uses the set optimization coefficient to judge the search of the particle swarm State,update the inertia weight coefficient in real time,and introduce the update mechanism of the fruit fly algorithm during the update of the particles,which balances the ability of the algorithm for global and local exploration at different stages.Finally,the proposed algorithms are compared with similar algorithms in a two-dimensional barrier-free environment and a mixed environment with heterogeneous obstacles.The simulation experiment proves that the FFPSO algorithm is superior to the comparison algorithm in coverage,and can effectively improve the effective coverage of the WSN network.(2)A hybrid optimization algorithm(Glowworm Swarm Optimization and particle swarm hybrid optimization algorithm,GSOPSO)is proposed,which is a combination of Glowworm Swarm Optimization and particle swarm hybrid optimization algorithm.In the early iteration of the algorithm,multiple initial solutions are generated through chaotic mapping and multi-directional learning,and then evaluated Select excellent particles as the initial population,adjust the population inertia weight to non-linear decline through the evolution state of the population,take into account the global optimization and local search of the algorithm,and introduce the optimization mechanism of the firefly algorithm to make up for the weak local search ability of the particle swarm algorithm,Use the perturbation operation to adjust the speed and position of the particles,increase the diversity of the population at the later stage of the iteration,and prevent the particles from "premature".Finally,the experiment shows that the GSOPSO algorithm is better than the comparison algorithm in both environments,and it can effectively improve the node coverage.Finally,the proposed algorithm is compared with similar algorithms in a two-dimensional barrier-free environment and a mixed environment of heterogeneous obstacles.Simulation experiments prove that the GSOPSO algorithm can effectively improve the coverage of network nodes.