基于混合策略改进阿奎拉鹰优化算法的多目标红外WSN节点覆盖优化

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

关键词:  无线传感器网络(WSN)  网络覆盖  阿奎拉鹰优化算法(AO)  瞬态搜索  无迹sigma点变异  准对立学习

Key words:  Wireless Sensor Network (WSN)  network coverage  Aquila Optimizer (AO)  transient search  traceless sigma point variation  quasi-opposition-based learning

摘要:

为了提高无线传感器网络(Wireless Sensor Network,WSN)节点对目标区域的覆盖率，提出一种多目标红外WSN节点覆盖优化算法——混合策略改进阿奎拉鹰优化算法(Hybrid Strategy Improved Aquila Optimizer,HSIAO)。为提高节点目标位置的搜索精度，引入准对立学习机制提升初始种群多样性和个体质量，设计伯努利(Bernoulli)混沌映射高空飞行机制提升算法全局搜索能力，并利用瞬态搜索低空飞行机制丰富个体攻击行为的多样性，同时采用自适应随机无迹sigma点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节点的覆盖率、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，通过改进的阿奎拉鹰优化算法对多目标红外WSN节点覆盖问题迭代求解。实验结果表明，该改进算法能有效降低节点冗余率和提高网络覆盖率，生成的自组网能延长传感器网络的有效工作时间。

Abstract:

To improve the coverage of Wireless Sensor Network(WSN)nodes in the target area,a Hybrid Strategy Improved Aquila Optimizer (HSIAO) is proposed.A quasi-opposition-based learning is introduced to improve the diversity and individual quality of the initial population,thereby improving the search accuracy for the target position of the node.Bernoulli chaotic mapping is designed to improve the global search capability of the algorithm in high-altitude flight.A transient search is used to enrich the diversity of individual attack behaviors in low-altitude flight.An adaptive random traceless sigma point variation is employed to avoid the search blind area in the late iteration,avoid falling into the local optimum,and improve the convergence accuracy.The multi-objective fitness function of network coverage is established by considering the coverage, coverage redundancy,and movement energy consumption of WSN nodes.The multi-objective WSN coverage problem is solved iteratively by HSIAO.Experimental results show that the improved algorithm can effectively improve network coverage and reduce node redundancy.The generated ad hoc network can extend the effective working time of the sensor network.