Poster: Channel Prediction Based on BP Neural Network for Backscatter Communication Networks

Due to the large amount of sensor data in the backscatter network, parallel transmission and rate adaptation are constrained by channel quality. In this paper, we propose a channel prediction scheme for backscatter networks. The scheme consists of two parts: a monitoring module and a prediction module. The monitoring module, which uses the data of the acceleration sensor to monitor the movement of the node itself, and uses the link burstiness metric to monitor the burstiness caused by the environmental change, thereby determining that new data of channel quality is needed, and the prediction module predicts the channel quality of the next stage by using the BP neural network algorithm. The experimental results show that the channel prediction accuracy is high and the relatively stable read rate can be maintained.