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

With the benefits of low costs,self-organisation and can be used for a long time,WSN has a wide range of applications,such as forest surveillance,marine research,resource development,disease treatment and other areas.However,The execution task scenario for WSN is intricate and variable,and the energy of the sensor is fixed,which is difficult to supplement,This is why the key research issue for WSN is to control network coverage optimization.Network coverage is a direct determinant of network performance and quality of service of WSN.An efficiency and excellence network coverage strategy can optimise the use of sensor nodes so that WSN can serve users better.This paper mainly studies the node layout and coverage optimization of WSN in two-dimensional network environment.The research contents are as follows:(1)Aiming at the coverage optimization problem of WSN in barrier free environment,the DEPSO algorithm is proposed.In this algorithm,the coverage is used as the optimization factor in constructing the objective function optimization model,and use fitness values as effective coverage.In the initial stage,chaos multi-directional learning strategy is used to improve the diversity of the initial population,The velocity is regulated by defining the state coefficient of the particle.The weight of inertia in the modified formula does not decrease linearly and the learning factor is optimized by combining the ratio between iteration times and inertia weight.Finally,Mutation and crossover strategies are introduced into the DEA,Compare six basic functions with similar multidimensional algorithms,and is applied to the optimization of barrier free node coverage.Simulation results show that the DEPSO algorithm is more efficient than the comparison algorithm,thus increasing the convergence,The optimization precision and coverage of WSN nodes are improved..(2)In order to effectively improve the coverage of sensing nodes in complex environment,GWPSO algorithm is proposed and applied to the network with trapezoidal obstacles and heterogeneous nodes.The optimization goal is to deploy nodes for coverage.In the initial stage of the algorithm,chaos multi-directional learning strategy is used to enrich the diversity population.By dynamically adjusting the convergence strategy,the result is a balanced global search algorithm and local optimization.The guiding ideology of grey Wolf population is introduced,and the optimal layer,velocity and position GWPSO is introduced,which increases the convergence and optimality of the algorithm,and is compared with other four algorithms.Test functions are used to compare the convergence of the algorithm,and then the node deployment is optimized under obstacle free and trapezoidal obstacles.Experimental results show that GWPSO algorithm is better than the contrast algorithm in both environments,and can effectively improve the node coverage.