云粒子群优化算法在无线传感器网络中的应用

无线传感器网络中节点计算能力和存储存能量有限的问题一直制约着无线传感器网络的发展.为此,本文提出了一种基于云PSO（particle swarm optimization）算法的无线传感器网络能量优化方法,主要包括网络分簇、网络能量模型建立、云PSO算法迭代优化等步骤.其中云PSO算法采用云理论模型优选惯性权重可以提高PSO算法的收敛速度,典型函数测试结果表明其效果优于常规PSO算法和遗传算法;在网络建模中采用二分功率控制算法可以降低网络能耗、延长节点寿命.最后经仿真试验和对比分析表明本文提出的方法在优化无线传感器网络中具有速度快、节点生存能力强的优点,并能有效地控制网络能耗.

Optimal wireless sensor network using cloud adaptive particle-swarm-optimization algorithm

The poor computation ability and limited storage of power of the nodes of wireless sensor network(WSN) have seriously restricted the development of WSN. Based on the cloud adaptive particle swarm optimization(CAPSO) algorithm, an optimal approach for WSN is proposed, which includes the network clustering, network modeling, and the iterative optimization with CAPSO algorithm, etc. The convergence for CAPSO algorithm can be accelerated by using cloud model to optimally select the inertia weight. The test results of typical function show that the CPSO algorithm is superior to the conventional PSO and Genetic Algorithms(GA). In addition, the power consumption of the whole network can be reduced and the lifespan of nodes can be prolonged by using the binary power control algorithm in network modeling. The simulation experiment and comparison analysis show that the proposed approach possesses advantages of high speed in optimization, strong survival ability of nodes, and effective reduction of power consumption in control.