Research On 3D Wireless Sensor Networks Coverage Optimization Based On Improved Marine Predator Algorithm

Wireless sensor networks(WSN),as an important part of the Internet of Things,is widely used in daily life.The problem of WSN coverage is the basic problem faced by the WSN network configuration,which directly affects the service quality of the network.Therefore,the research on WSN coverage algorithms has high research value and important practical significance.In recent years,with the deepening of WSN coverage optimization algorithm research,the coverage of traditional two-dimensional planes is not applicable in a complex three-dimensional(3D)environment.As a result,research on WSN coverage technology based on 3D environment has attracted more and more researchers.In this paper,we focus on the coverage optimization problem of WSN on 3D surfaces,and propose two types of coverage optimization technologies.The main work and innovation points are as follows:(1)Aiming at the problem of 3D surface WSN coverage,we propose a coverage technology based on multi-strategy integrated marine predator algorithm(IMPA).First of all,in order to improve the defects of the Boolean perception model,a probability coverage model suitable for 3D surface WSN coverage was proposed.Secondly,to address the shortcomings of the Marine Predator Algorithm(MPA)in optimizing the WSN coverage problem with low solution accuracy and poor local exploitation capability,this article introduces a random opposition-based learning strategy and differential evolution operator to enrich the population diversity.The grouping idea of the Shuffled Frog Leaping Algorithm is introduced,and a local search strategy is proposed to improve the local exploitation ability of the algorithm.At the same time,a quasi-reflected reverse learning mechanism and an improved population boundary strategy are proposed to accelerate the convergence speed of the algorithm.Finally,the proposed IMPA algorithm is used to solve the 3D surface WSN coverage problem.The simulation results show that compared with the other four similar algorithms,the coverage optimization result of the IMPA algorithm is the best,the terrain adaptation capacity and network life cycle is stronger and longer.(2)A coverage technique based on reinforcement learning-based modified marine predator algorithm(RLMMPA)is proposed for the 3D real terrain WSN coverage problem.Firstly,a coverage model based on Line of Sight(LOS)model combined with the probabilistic perception model is proposed in order to closely match the real WSN application environment.Secondly,the marine predator algorithm is prone to premature convergence when dealing with the complex problem of 3D WSN coverage optimization,this paper combines reinforcement learning with the MPA and adaptively adjusts the algorithm to take the corresponding optimization stages through the advantage of reinforcement learning.At the same time,a Gaussian mutation strategy,a Fitness-distance balance(FDB)selection method,and a learning strategy based on a combination of lensing imaging learning and quasi-reflected reverse learning are introduced for enhancing the performance of the algorithm.Finally,the RLMMPA algorithm is applied to the WSN coverage optimization of the 3D real terrain.Simulation results show that the proposed algorithm can achieve higher network coverage with fewer sensor nodes compared to the other eight algorithms.