WSN Coverage Optimization Based On Improved Sparrow Search Algorithm

In Wireless Sensor Network(WSN),coverage is an important indicator of the quality of service of sensor networks.It is important to optimize the deployment of wireless sensor networks to achieve higher coverage and more uniform distribution,thus extending network lifetime and improving network reliability.At present,the optimal deployment of WSNs is mainly achieved by swarm intelligence optimization algorithms,but the existing swarm intelligence optimization algorithms have insufficient search capability,which leads to poor coverage optimization of WSN nodes.Sparrow Search Algorithm(SSA)is widely used in many fields because of its simple and easy to implement algorithm.However,SSA still has much room for improvement in terms of algorithm population diversity and search accuracy.In this paper,we optimize WSN coverage by SSA based on chaotic mapping,antlion random wandering mechanism and elite backward learning,and the main work is as follows.(1)The sparrow algorithm uses a randomized approach to initialize poor population diversity.To address this problem,this paper proposes to invoke Bernoulli chaos mapping to implement population initialization in order to improve the diversity of initialized populations and the convergence speed of the algorithm.To address the problem of poor search accuracy of the sparrow algorithm,this paper proposes a location updating strategy incorporating the random wandering of ant-lions.The positions of the sparrow individuals selected by the roulette method and the current global optimal sparrow individuals are updated by the ant-lion random walk strategy respectively to achieve the position update of the whole population in order to improve the search accuracy of the sparrow algorithm.For the problem that the sparrow algorithm is easy to fall into local optimum in the late iteration,this paper reduces the probability of the algorithm falling into local optimum by elite backward learning.(2)The algorithm ablation experiment is conducted by controlling the improvement strategy.to verify the necessity of the corresponding improvement strategy.The experimental results show that each improvement strategy proposed in this paper has a significant improvement on the optimization performance of the algorithm.The algorithm optimization experiments of CRASSA proposed in this paper are conducted by benchmarking test functions,and compared with the classical optimization algorithm and the variant of SSA,respectively,to verify the superiority of the algorithm performance.The experimental results show that the CRASSA algorithm proposed in this paper has significant advantages over other algorithms in terms of convergence speed and convergence accuracy.the Wilcoxon rank sum test results show that there is a significant difference between the optimization performance of the CRASSA algorithm and other algorithms.(3)The CRASSA proposed in this paper is implemented for WSN coverage optimization,and the WSN coverage metrics are compared to verify the superiority of the algorithm.The experimental results show that the CRASSA algorithm proposed in this paper has 14.24%,12.01%,5.94%,14.24%,4.74% and 12.48% higher coverage for the PSO algorithm,WOA algorithm,HHO algorithm,SSA algorithm,CSSA algorithm and ESSA algorithm after coverage optimization of WSN,and for the hybrid WSN after coverage optimization of coverage is 13.63%,11%,5.65%,15%,4.38%,and 14.91%higher,while obtaining better node uniformity and shorter average node travel distance with significant optimization effects.Figure [41] table [37] reference [72]...