基于改进PSO的铁路监测线性无线传感器网络路由算法

Routing algorithm for railway monitoring linear WSN based on improved PSO

为了解决铁路监测场景中线性无线传感器网络的节点间能耗不均衡导致的网络生命周期短、数据传输时延大的问题,提出了一种基于粒子群优化理论和广度优先搜索的路由算法。以候选簇头节点的相对能耗、簇头间距和簇头负载为指标构建适应度函数,通过调整惯性权重系数增强粒子群算法局部搜索能力,获得簇头最优解集;构建能耗与时延驱动的路径成本函数,基于广度优先搜索获得源节点到sink节点的最优主路径;设计基于Markov决策过程(MDP)模型的Q-learning备选路径更新与路由维护机制。仿真结果表明,所提算法能够有效均衡节点间能耗,在延长网络生命周期和降低数据传输时延方面具有较优的性能。

To solve the problems of short network lifetime and large data transmission delay,caused by unbalanced node energy consumption of linear wireless sensor network in railway monitoring scenario,a routing algorithm based on particle swarm optimization theory and breadth first search was proposed.The fitness function was constructed based on the relative energy consumption,spacing and load of candidate cluster heads.The local search ability of particle swarm algorithm was enhanced by adjusting the inertia weight coefficient to set up the cluster head optimal set.Meanwhile,a path cost function driven by energy consumption and delay was built up,and the optimal main path from the source node to the sink node was obtained by breadth first search.Lastly,a Q-learning alternative path updating and route maintenance mechanism based on discrete Markov decision process(MDP)was designed.Simulation results show that the proposed algorithm can balance the node energy consumption effectively,and has also advantages in prolonging the network lifetime and reducing the data transmission delay.