Research On Adaptive Quantum-behaved Particle Swarm Algorithm And Its Application In WSN Coverage Optimization

The era of the Internet of Things(IoT),where everything is connected,and people and things are interacting,is already on the horizon,and perceptions of things are everywhere.As the technical support and "nerve end" of the IoT,the Wireless Sensor Network(WSN)is a bridge connecting the physical world and the information world.It is a core technology that enables the interaction between people and things,and has a wide range of application prospects and huge research value.The application service of the WSN depends on the coverage quality of the network.The coverage problem of the WSN has always been one of the core issues that have been extensively studied.Due to the limitation of objective conditions,the sensor nodes are usually deployed in a random manner.However,the WSN adopting this deployment mode often has defects such as uneven distribution of nodes,high redundancy,and blind coverage.The deployment of dynamic nodes,through the coverage optimization algorithm to optimize the initial deployment of the node position and adjustment can be achieved better results.This thesis focuses on the study of network coverage optimization problems with randomly deployed WSN,maintaining the connectivity,durability,and stability,reducing network redundancy and monitoring blind spots,increasing network coverage,extending network lifetime,and ultimately improving the quality of service(QoS)of the WSN is the goal of this study.Randomly deployed WSN coverage optimization problem is often an uncertain optimization problem.Multi-objective constrained optimization problems and combinatorial optimization problems that meet certain conditions are usually NP-hard complete problems,which poses a great challenge to traditional optimization methods.The swarm intelligence algorithm brings a new idea to solve WSN coverage optimization.As a typical swarm intelligence algorithm,the particle swarm optimization algorithm(PSO)has the characteristics of less control parameters,simple calculation,and easy implementation It has been applied to the research of WSN coverage optimization and achieved certain results.However,the PSO still has the disadvantages of low convergence accuracy,poor robustness,and easy to fall into local extremes.In order to improve the coverage performance of the WSN,this thesis has done the following work:(1)For the deficiency of the PSO,based on Quantum-Behaved PSO(QPSO),a Dynamic Adaptive Chaotic QPSO(DACQPSO)is proposed.The algorithm introduces two quantitative indicators of population distribution entropy and average particle distance for measuring population diversity,and uses the population distribution entropy to control the evolution of the key parameter—the contraction expansion coefficient ? to improve the global search ability of the algorithm,which reflects its adaptive.In addition,combined with the characteristics and advantages of chaos search,the average particle distance is used as a criterion to perform chaotic refinement search to improve the local search ability,and generate chaotic disturbance at the same time,which increases the population diversity.The DACQPSO algorithm is applied to the coverage optimization of the WSN.The experimental results show that compared with other algorithms,the network coverage and node utilization have been improved to a certain extent and have better coverage effect.(2)Introducing the cloud model theory into the improvement of the PSO,an Adaptive QPSO based on Normal Cloud Model(CMAQPSO)is proposed.The algorithm uses the X-condition cloud generator to calculate the degree of membership of each particle and adjusts the contraction expansion coefficient ? adaptively.Y-condition cloud generator is used to construct cloud mutation operators to increase population diversity and the self-adaptive adjustment strategy of the quantum trap center is proposed.The simulation results show that the CMAQPSO algorithm has obvious advantages in terms of global optimization ability,search accuracy and convergence speed compared with other algorithms.The CMAQPSO algorithm is applied to the coverage optimization of WSN,and the experiment verifies the effectiveness of the algorithm.