A Model-Aided Data Gathering Approach for Wireless Sensor Networks

How to collect data energy-efficiently from sensor nodes is an important research issue in wireless sensor networks. In this paper, we address the problem of gathering data from sensor nodes using a model-aided data gathering approach. In our approach, a model is maintained by a node and a replica of the model is maintained the base station. The base station uses the replica model to estimate the actual measurement data of the sensor node in usual time, and an actual measurement datum is sent to the base station only when the error of the model’s corresponding estimation exceeds allowable error bound. In such a way, energy can be saved by reducing the transmission of actual measurement data. Experimental results show the effectiveness of our approach.