基于多步预测的无线传感网络自适应采样技术研究

Reasearch on Adaptive Sampling Algorithm Based on Multi-step Prediction for Wireless Sensor Networks

针对现有无线传感网节能算法计算量大、终端节点能耗高以及上位机数据更新实时性低的问题,提出一种基于多步预测的传感网络自适应采样算法。该算法在上位机和终端节点间建立自回归预测模型进行同步预测,同时通过比较预测模型的前向多步预测值与数据变化趋势拟合值,达到自适应改变采样步长的效果。为验证算法的节能性,基于ZigBee的船舶下水气囊气压监测系统平台进行实验。结果表明:所提算法在均方根误差为0.089 2的情况下,比固定周期采样节能36.252%,比传统自适应通信算法节能26.912%,具有更好的能耗表现。

Aiming at the problems of the existing energy-saving algorithms for wireless sensor networks that have large calculations, high energy consumption of terminal nodes, and low real-time data update of the upper computer, an adaptive sampling algorithm for sensor networks based on multi-step prediction was proposed. An autoregressive prediction model between the upper computer and the terminal node for simultaneous prediction was established. At the same time, the effect of adaptively changing the sampling step was achieved by comparing the forward multi-step prediction value of the prediction model with the data change trend fitting value. In order to verify the energy saving of the algorithm, the experiments were carried out on the ZigBee-based ship launching airbag pressure monitoring system platform. The results show that with the root mean square error of 0.089 2, the proposed algorithm saves 36.252% energy compared with fixed-period sampling, and saves 26.912% energy compared with traditional adaptive communication algorithms, and has better energy performance.