Research On WSN Mobile Agent Path Planning Algorithm Based On Improved Particle Swarm

As one of the most popular technologies in this century,the Wireless Sensor Network is capable of real-time data monitoring of specific areas,which greatly expands the perception of human beings,and is thus widely used in various fields.However,because the nodes used for monitoring are often located in a complex and dangerous environment,it is difficult for the node energy to be artificially supplemented or the cost of supplementing energy is too high,so the WSN network energy is strictly limited.Since the mobile agent MA(Mobile Agent)has strong autonomy and can process information independently,its application in network communication can effectively improve network performance,so it is very important to adopt an efficient MA migration path in WSN.This dissertation mainly studies MA.Aiming at the problems of too long MA path,uneven node energy consumption and low search solution accuracy,the following studies are carried out:(1)A mobile agent routing algorithm based on optimal location(MABOPSO)is proposed.This algorithm considers the relationship between the location of MA collected data and energy consumption in WSN.Based on the hexagonal division of the network area,it calculates the optimal number of partitions and finds the optimal location for MA to collect data.Use optimization factor and learning factor to improve the inertia weight of PSO,and verify its effectiveness through simulation and comparison.(2)A Path planning algorithm for WSN mobile agent based on Voronoi diagram partition(VPDM)is proposed.In the initial stage,the nodes are given weights based on node density,regional energy and node distance,and the node with the larger weight is selected as the center of the Voronoi unit.Based on this,the network is divided into Voronoi units,combined with node energy consumption,communication delay and MA load balancing is the objective function to find the optimal MA path.The improved PSO algorithm learns from particles that are better than the average fitness value,and the particles that are lower than the fitness value implement the perturbation strategy,and conduct simulation comparison experiments.(3)An adaptive inertia weight of PSO path planning algorithm base on ring partition(AIPSO)is proposed.Divide the network area into several rings with different widths,consider the distance between the node and the base station,and assign different levels to the nodes;then set intermediate nodes in the ring,set the evolution state of the population,and adaptively update the learning factors and Inertia weight,execute jump strategy for the stagnant group,and use AIPSO algorithm to plan the path for MA.The simulation results show that the AIPSO algorithm is superior to similar algorithms in MA path planning.Figure[26]table[4]reference[88].