混合策略改进阿奎拉鹰优化算法求解多目标红外WSN节点覆盖

Multi-objective Infrared Wireless Sensor Networks Node Coverage Based on Hybrid Strategy Improved Aquila Optimizer

关键词:  无线传感器网络  网络覆盖  阿奎拉鹰优化器  瞬态搜索  无迹变异  准对立学习

Key words:  wireless sensor network  network coverage  Aquila optimizer  transient search  traceless variation  quasi-opposition learning

摘要:

为了提高无线传感器网络节点对目标区域的覆盖率，提出一种混合策略改进阿奎拉鹰优化算法的WSN节点覆盖优化算法。为了提高节点目标位置的搜索精度，引入准对立学习提升初始种群多样性和个体质量，设计伯努利混沌映射高空飞行提升算法全局搜索能力，并利用瞬态搜索低空飞行丰富个体攻击行为多样性，同时采用自适应随机无迹sigma变异避免迭代后期的搜索盲区，避免位置搜索出现停滞钝化，提高收敛精度。综合考虑WSN节点覆盖率、覆盖冗余及节点移动能耗建立网络覆盖的多目标适应度函数，通过改进阿奎拉鹰优化算法对多目标WSN覆盖问题迭代求解。实验结果表明，改进算法能有效降低节点冗余和提高网络覆盖率，生成的自组网能延长传感器网络的有效工作时间。

Abstract:

In order to improve the coverage of wireless sensor network nodes to the target area, a hybrid strategy improved Aquila Eagle optimizer is proposed to improve the WSN node coverage. In order to improve the search accuracy of the node target position, a quasi-oppositional learning is introduced to improve the diversity and individual quality of the initial population. Bernoulli chaotic mapping high-altitude flight is designed to improve the global search capability of the algorithm. A transient search low-altitude flight is used to enrich the diversity of individual attack behaviors.And, an adaptive random traceless sigma variation is used to avoid the search blind area in the late iteration, avoid falling into the local optimal and improve the convergence accuracy. The multi-objective fitness function of network coverage was established by considering node coverage, coverage redundancy and node movement energy consumption. The multi-objective WSN coverage problem was solved iteratively by improving the Aquila Eagle optimizer.Experimental results show that the improved algorithm can effectively improve network coverage, reduce node redundancy.The generated ad hoc network can extend the effective working time of the sensor network.