WSN中利用熵权自适应分簇和改进PSO的路由优化算法

ROUTING OPTIMIZATION ALGORITHM BASED ON ENTROPY WEIGHT ADAPTIVE CLUSTERING AND IMPROVED PSO IN WSN

针对无线传感器网络(Wireless sensor network, WSN)能耗不均以及使用生命周期较短等问题,提出一种利用熵权自适应分簇和改进粒子群优化的WSN路由优化算法(FNNPSO)。运用模糊神经网络推理选取簇头,利用熵权法明确簇头指标的权重,基于模糊神经网络评估标准得到簇头的转发概率,并且将概率较高的簇头设为中继节点,逐层完成信息传输;采用改进粒子群优化算法优化网络路由,通过考虑中继节点的数量、网关到基站之间的距离和网络的中继负载因子,来设计新型适应度函数。提出的方案融合两种算法的优势,通过模糊神经网络提高了簇内结构的稳定性,利用优化后的粒子群算法增强了簇间路由的鲁棒性和可靠性。实验结果表明,相比其他几种较新的路由优化算法,所提算法有效减少了网络能耗并且延长了其生命周期。

Aimed at the problems of uneven energy consumption and short life cycle of WSN,a WSN routing optimization algorithm based on entropy weight adaptive clustering and improved PSO is proposed.The cluster head was selected by fuzzy neural network reasoning,the weight of cluster head node index was determined by entropy weight method,and the forwarding probability value of cluster head was obtained by using fuzzy neural network comprehensive evaluation criterion.The cluster head node with large probability value was selected as the forwarding node to complete the information transmission layer by layer.PSO was improved to optimize the network routing.A new fitness function was designed by considering the number of relay nodes,the distance between the gateway and the base station and the relay load factor of the network.The proposed scheme combined the advantages of the two algorithms.It improved the stability of the structure in the cluster through fuzzy neural network,and used the improved PSO to enhance the robustness and reliability of inter cluster routing.The experimental results show that compared with other new routing optimization algorithms,The proposed algorithm effectively reduces the network energy consumption and prolongs its life cycle.