混合粒子群和差分进化的定位算法

针对传统无线传感器网络(wireless sensor network,WSN)中节点定位精度不高的问题,提出了一种混合粒子群(particle swarm optimization,PSO)和差分进化优化(differential evolution,DE)算法。首先在PSO中引入惯性权重的自适应更新策略,以兼顾开发和勘探能力,在种群经过PSO进化后,然后根据提前设定的阈值,将其分为适应度值较大的Su种群和适应度值较小的In种群,In中的粒子使用DE算法继续优化。HPSO-DE算法结合PSO算法和DE算法的优点,达到较好的性能。然后用标准测试函数来检测该算法的性能,验证结果表明所提出的HPSO-DE在寻优速度和收敛精度较PSO和DE而言都有了较大提高。接下来将HPSO-DE方法应用到WSN网络节点定位场景上,从实验测试结果可以看出,其精度相比PSO平均提高了0.5 m左右,在定位上具有更大的优势。

Localization Algorithm based on Hybrid Particle Swarm Optimization and Differential Evolution

Aiming at the low accuracy of node location in traditional WSN(wireless sensor network),a hybrid PSO(particle swarm optimization)and DE(differential evolution)algorithm are proposed.Firstly,an adaptive update strategy for inertia weights is introduced into the PSO to balance development and exploration capabilities.After the population has undergone PSO evolution,it is divided into a Su population with a large fitness value and an In population with a small fitness value according to the threshold set in advance.The particles in In continue to be optimized using the DE algorithm.HPSO-DE algorithm combines the advantages of PSO algorithm and DE algorithm to achieve better performance.The performance of the algorithm is tested by using standard test functions,and the verification results show that the proposed HPSO-DE has greatly improved the optimization speed and convergence accuracy compared with PSO and DE.Finally,the HPSO-DE method is applied to the WSN network node location scenario.The experimental results indicate that the accuracy is improved by about 0.5 m on average compared to PSO,which has a greater advantage in positioning.