基于WSN网络覆盖优化问题的群智能优化算法比较分析

Comparative Analysis of Swarm Intelligence Optimization Algorithm Based on WSN Network Coverage Optimization Problem

为了解决无线传感器网络(WSN)随机部署方法导致覆盖率低的问题,本研究对群智能优化算法中粒子群优化算法(PSO)、人工蜂群算法(ABC)、人工萤火虫算法(GSO)、灰狼算法(GWO)、蚁狮优化算法(ALO)、蝠鲼觅食优化算法(MRFO)、麻雀搜索算法(SSA)、人工兔优化算法(ARO)、猎食者优化算法(HPO)和蜣螂算法(DBO)基于WSN网络覆盖问题进行比较和分析,并通过单目标优化和多目标优化两种方式对算法的性能进行比较与分析。仿真结果表明,不同算法在相同条件下的性能存在差异,随着监测区域面积的增大,算法的性能会更优。GWO、MRFO、ARO和HPO算法更适用于解决网络覆盖问题。基于覆盖率、移动距离及连通度的多目标优化比仅仅基于覆盖率的单目标优化在WSN网络覆盖问题上的算法性能更佳。

To address the issue of low coverage rate caused by random deployment method in wireless sensor network(WSN),this study compares and analyzes various swarm intelligence optimization algorithms,including particle swarm optimization(PSO),artificial bee colony algorithm(ABC),glowworm swarm optimization(GSO),grey wolf optimizer(GWO),ant lion optimization(ALO),manta ray foraging optimization(MRFO),sparrow search algorithm(SSA),artificial rabbits optimization(ARO),hunter-prey optimization(HPO),and dung beetle optimizer(DBO)based on WSN network coverage problem.The performance of the algorithms is compared and analyzed through single-objective optimization and multi-objective optimization.The simulation results show that the performance of different algorithms is different under the same conditions and the performance of the algorithms is better as the area of the monitored region increases.Among the above algorithms,GWO,MRFO,ARO and HPO algorithms are more suitable for solving the WSN network coverage problem.Multi-objective optimization based on coverage,movement distance,and connectivity is better than single-objective optimization based on coverage alone in terms of algorithm performance for the WSN network coverage problem.