Research On WSN Routing Algorithm Based On Improved Genetic Particle Swarm Optimization

Wireless Sensor Network(WSN)is an important infrastructure of the Internet of Things.Most of the nodes in WSN use batteries to provide energy.When the energy of the nodes is exhausted,they will be separated from the WSN,which will affect the performance of WSN.Therefore,it is necessary to reduce the power consumption of nodes as much as possible and prolong their life cycle.In the case of limited resources,it is very important to design energy-efficient routing algorithms.Low Energy Adaptive Clustering Hierarchy(LEACH)and LEACH-C(LEACH’s improved protocol)are two routing algorithms commonly used in existing routing schemes.However,these two algorithms do not fully consider the energy and distance of nodes,and do not integrate the data.As a result,the energy distribution of nodes is unbalanced,which leads to fast energy consumption of related nodes and affects the performance of WSN.To solve these problems,through the systematic research and analysis of the characteristics of WSN,it is found that the swarm intelligence algorithm and BP neural network can effectively improve the performance of WSN related nodes.In this paper,an improved genetic algorithm is used to select the cluster head node of WSN.The cluster head node fuses the data of nodes in the cluster through BP neural network based on improved particle swarm optimization algorithm,which can effectively reduce the amount of relevant data and reduce the energy consumption of cluster head in data communication.The research content of this paper is as follows:(1)In view of the influence of cluster head node selection on WSN performance,the improved genetic algorithm is used to optimize the cluster head node,and the selection,crossover and mutation operations in the improved genetic algorithm are used to select the cluster head node,and the crossover operator and mutation operator are dynamically adjusted according to the running situation of the algorithm.The nodes with high energy relative to other nodes and close to the base station are effectively selected as the cluster head nodes,and the nodes with low energy are avoided to be used up as the cluster head nodes.(2)Aiming at the situation that LEACH does not converge and fuse the data monitored by sensor nodes,which leads to the poor performance of WSN,a new data fusion scheme based on BP neural network based on improved particle swarm optimization algorithm is proposed under the condition that improved genetic algorithm is used to select the best cluster head node.The improved particle swarm optimization algorithm can dynamically adjust the relevant weight value according to the running situation,which makes the BP neural network model more fast and efficient training,to solve the local optimal problem caused by the random setting of the initial parameters of the BP neural network.(3)Combined with the above improved methods and applied to WSN,a WSN routing algorithm based on improved genetic particle swarm optimization is proposed.Experimental results show that the proposed method can effectively reduce the amount of monitoring data transmission,greatly reduce the energy consumption of cluster head nodes,prolong the lifetime of nodes,and thus improve the performance of WSN.