A Self-Adaptive Spatial-Temporal Correlation Prediction Algorithm To Reduce Data Transmission In Wireless Sensor Networks

In this work, we propose a self-adaptive spatial-temporal correlation (SASTC) prediction algorithm, which combines temporal correlation and spatial correlation to prediction sensing data in wireless sensor networks. Adaptive grey prediction model is used to measure the temporal correlation of sensing data, and then Delaunay triangulation is introduced to measure the spatial correlation of sensing data. The adaptive grey prediction model runs between member nodes and cluster heads, using the temporal correlation of data within these nodes and heads to reduce the amount of data transmission. The spatial correlation model runs between cluster heads and sink nodes, using the spatial correlation of data within the member nodes to reduce the amount of data transmission. The simulation results show that the algorithm has higher prediction accuracy, which can effectively reduce the amount of data transmission in the network and save the energy consumption of data transmission.