GEP-Based Temporal Data Aggregation in Wireless Sensor Networks

In order to decrease the traffic in the wireless sensor networks, a gene expression programming based temporal data aggregation technique (GEP-WSNDA) is presented. Two matching predictors with the same GEP-WSNDA models are deployed at the server and the node respectively, which predict the next immediate sampling value simultaneously. The sampling value and new model are sent to the server only when the difference between the actual and the predicted value at the node exceeds a certain threshold. Besides, since its own intrinsic characteristics, GEP-WSNDA solves the problem that the traditional time series methods can´t make an accurate prediction without the pre-knowledge. By employing GEP-WSNDA, the experiments on ocean air temperature data 2007 reached the expectation and made a precise prediction. When error threshold is 0.05deg, it can filter about 80% data and remain high precision.