Research On Data Aggregation Technology Of Wireless Sensor Network In Railway

With the rapid development of high-speed railway and Internet of Things,the wireless sensor monitoring network is of great significance to ensure the safety of railway system.At present,wireless sensor network in railway can provide massive real-time sensing information.At the same time there are still some problems to be solved:(1)There is a large amount of data redundancy in the WSN,it will consume a large amount of energy to transmit the original data.(2)There is a problem of energy hole in the WSN,and the energy consumption of the sensor nodes is not balanced.Therefore,this paper studies the data collection process of energy-limited WSN.This paper uses data aggregation technology to reduce redundant data and realize efficient and balanced energy consumption.The main work of the paper includes the following two aspects:(1)This paper focuses on event-based data aggregation algorithms using principal component analysis and support vector regression.The algorithm determines the occurrence of events through the state checker.When the state is normal,the data aggregation nodes perform PCA on the data with the correlation to achieve dimension reduction,then send the aggregated data to the sink node,and the sink node reconstructs the data.When the state is urgent,the data aggregation nodes send an emergency message to the sink node and perform SVR prediction on the irrelevant data.Under the condition of ensuring the prediction accuracy,the data aggregation nodes send the data to the sink node according to the prediction accuracy.The simulation results show that the accuracy of SVR prediction is high,and the event-based PCA-SVR data aggregation algorithm proposed in this paper reduces the amount of transmitted data and saves energy consumption compared with the Adaptive-PCA data aggregation algorithm.(2)This paper proposes a deployment of relay nodes data aggregation protocol based on the degree of energy hole,which can realize balanced energy consumption in WSN.In order to balance the energy consumption of sensor nodes in the cluster,each cluster selects the cluster head according to the cluster head selection factor,and the cluster head selection factor is related to the remaining energy and the distance from the node to the center of the next hop cluster.In order to balance the energy consumption between clusters,this paper proposes degree of energy hole.The number of relay nodes to be deployed is calculated according to the degree of energy hole and a corresponding number of high energy relay nodes are deployed in the cluster center where energy hole occurs.The relay nodes send data to the next hop relay node or sink node.The performance of this EH-RND data aggregation protocol is simulated and compared with the Centralized-Uneven Clustering Routing Protocol(C-EEUC)and Feedback Mechanism protocol(FMUC).The simulation results show that the lifetime of each cluster in the proposed data aggregation protocol is similar,EH-RND can balance cluster energy consumption and improve the network lifetime.Finally,this paper summarizes the proposed data aggregation technology for wireless sensor networks in railway and makes a prospect for several aspects of future work.