Multi-Step Data Prediction in Wireless Sensor Networks Based on One-Dimensional CNN and Bidirectional LSTM

Abstract

The increase of network size and sensory data leads to many serious problems to the wireless sensor networks due to the limited energy. Data prediction method is helpful to reduce network traffic and increase the network lifetime accordingly, especially by exploring data correlation among the sensory data. Data prediction can also be used to recover abnormal/lost data in case these sensor nodes fail to work. The current prediction methods in wireless sensor networks do not make full usage of the spatial-temporal correlation between wireless sensor nodes, and thus leads to higher prediction error relatively. This paper proposes a novel model for multi-step sensory data prediction in wireless sensor network. Firstly, we introduce the artificial neural networks based on 1-D CNN (One-Dimensional Convolutional Neural Network) and Bi-LSTM (Bidirectional Long and Short-Term Memory) to get the abstract features of different attributes via the pre-processed sensory data. Then, these abstract features are used to obtain one-step prediction. Finally, the multi-step prediction is introduced by using historical data and the prediction results of the previous step iteratively. Experiment results show that after selecting suitable node combinations in which the spatial-temporal correlation is highlighted, the proposed multi-step predictive model can predict multi-step (short and medium term) sensory data, and its performance is better compared with other related methods.