An improved adaptive dual prediction scheme for reducing data transmission in wireless sensor networks

Currently one of the main problem for wireless networks is the medium access control. Hence, the number of data transmissions in wireless sensor networks should be optimized to support more applications and a higher diversity of sensed parameters. In addition, minimizing energy consumption of sensor nodes constitutes one of the main ways to prolong network lifetime. One way to achieve this objective is the exploitation of data prediction technique. This paper presents an innovative idea improving the adaptive dual prediction algorithm without recourse to the data history table to update the model parameters when it drifts. The idea is to exploit immediately the new model parameters performed from the stored ones corresponding to the models used previously during the past prediction phases and eliminated when the threshold imposed by the user exceeded. We carried out simulations using real data of meteorological parameters. We show that our approach achieves up to 99% communication reduction with no significant loss in accuracy.