Research On WSN Coverage Optimization Of Improved Swarm Intelligence Algorithm

In recent years,with the rapid development of wireless communication technology,Wireless Sensor Networks(WSNs)have a wide range of applications in environmental detection,intelligent transportation and industrial fields,The problem of network coverage optimization is an important research area for WSN.With the widespread use of swarm intelligence algorithms in optimization problems,most of the research in recent years has been on the dynamic deployment of nodes with intelligent optimization algorithms.In this paper,the coverage optimization problem of WSN nodes in a twodimensional planar deployment environment is targeted,and the corresponding intelligent optimization algorithm is designed.An improved differential evolution algorithm(IDEA)based on the differential evolution algorithm(DEA)is proposed for deployment optimization in two-dimensional plane environments.In the face of complex environment deployment problems,an improved grey wolf optimizer(IGWO)is proposed based on the grey wolf optimizer(GWO),The details are as follows.1.In order to improve the effective coverage of WSN nodes in an accessible environment,an improved differential evolution algorithm is proposed and applied to the coverage optimization of WSN nodes.Using the effective coverage of the node as an optimization factor to construct an objective function optimization model,the coverage problem of WSN nodes is transformed into an objective function optimization problem using the network coverage as an adaptation function value.In the optimization phase,the diversity of the initial population is enriched by the chaotic inverse learning initialization strategy,and mechanisms such as elite population-guided variance vectors and parameter adaption are set up to improve the algorithm to speed up convergence and improve the coverage of WSN nodes.The improved algorithm is experimentally compared with three clustered smart algorithms from other literature in different dimensions on six benchmarking functions,and applied to the coverage optimization of WSN nodes in the accessibility situation.The simulation results show that the improved differential evolution algorithm can effectively accelerate the convergence speed,improve the computational accuracy,optimize the deployment strategy of WSN nodes in a barrier-free environment,and enhance the coverage of wireless sensor networks.2.An improved grey wolf optimization algorithm is proposed for the coverage optimization of WSN nodes in complex environments,and applied to the coverage optimization of WSN nodes in ladder obstacle environments.Deployed with coverage as an optimization goal,a nonlinear convergence factor is designed to balance global search with local search;an elite strategy is added to speed up the convergence of the algorithm;dynamic weights are proposed to improve the iterative rationality of poorly positioned individuals;adaptive variation strategy is introduced to increase the efficiency of the global optimal solution in the search region to avoid the algorithm falling into a local optimal situation.The improved algorithm is compared with the preimproved algorithm and with three intelligent optimization algorithms from other literature.Firstly,the convergence performance of these algorithms is compared with the test function,and then the algorithm is applied to WSN optimal deployment in barrier free environment and trapezoid obstacle environment.The simulation results show that compared with the other four algorithms,IGWO algorithm can effectively improve the node coverage of WSN in the case of trapezoid obstacles,and can provide a better solution for WSN deployment.