论文部分内容阅读
为优化无线传感器网络(Wireless Sensor Network,WSN)中各节点的部署与定位,常常需要采取一定的自适应轮换调度算法。传统的调度算法大都采用基于信息度增益控制的节点定位技术进行设计,算法性能随着迭代次数的增加而下降。为此提出了一种基于遗传控制的传感器节点自适应轮换调度算法,该算法利用遗传适应度函数对群体中的每个特征量进行自适应计算,结合变异遗传散布控制量与LSSVM训练模型对传感器节点进行优化部署,实现了对传感器节点的自适应轮换调度。经过实验仿真,结果表明,采用该算法实现对传感器网络节点的自适应轮换调度,能有效提高传感器网络定位的准确性,并提高传感器网络的生命周期,节省能量开销,提高网络的生存能力。
In order to optimize the deployment and location of each node in the Wireless Sensor Network (WSN), some adaptive round robin scheduling algorithms are often required. Most of the traditional scheduling algorithms are based on the information location gain control node positioning technology design, the performance of the algorithm decreases with the increase of the number of iterations. Therefore, an adaptive rotation scheduling algorithm for sensor nodes based on genetic control is proposed. This algorithm uses genetic fitness function to adaptively calculate each feature in the population. Combining the genetic variation control variable and LSSVM training model, Node optimization deployment, to achieve the sensor node adaptive rotation scheduling. The experimental results show that this algorithm can realize the adaptive rotation scheduling of sensor network nodes, which can effectively improve the accuracy of sensor network positioning, improve the life cycle of sensor networks, save energy overhead and improve the survivability of the network.