基于改进PSO的视频传感器网络覆盖增强算法

An Effective Coverage Enhancement Method for Video Sensor Network Based on Improved PSO

摘要: 感知覆盖反映了网络的感知服务质量，是进行其它研究的基础和先决条件。针对传统粒子群优化算法(PSO: Particle Swarm Optimization)，算法模型采用固定的参数，使得算法收敛速度较慢或无法收敛到最优解的问题，本文将改进的PSO算法应用于视频传感器网络感知覆盖中，通过改进PSO模型的惯性因子和学习因子，使得算法在初期具有较大的惯性，在节点局部范围内大幅度搜索，可以提高收敛速度；在末期惯性较小，以较小的步长在全局最优位置附近搜索，可以使算法最终收敛于全局最优，提高网络覆盖率。实验表明，本文算法收敛速度快，覆盖率明显提升。

Abstract: Coverage rate can reflect the sensing quality of sensor networks. It is the foundation and precondition for other related researches. The unchangeable parameters of traditional PSO algorithm may lead to slow convergent speed or being unable to converge to the optimal solution. In this paper, an improved PSO is proposed and applied to the coverage enhancement of video sensor network. By improving the inertia weight and learning factors, the algorithm has larger inertia at starting period. The nodes search in the local region with bigger steps and improve the convergent speed. At later stage, smaller inertia will lead to the algorithm searches near the optimal point with small steps. Then, the algorithm has high possibility to converge to the global optimal solution and improve the coverage rate. Experimental results show that the proposed method has high converging speed, and the coverage rate is improved effectively.