Research on Link Quality Estimation Mechanism for Wireless Sensor Networks Based on Support Vector Machine. Issue 2 (1st March 2017)

• Record Type: Journal Article
• Authors: Shu, Jian; Liu, Song; Liu, Linlan; Zhan, Liqin; Hu, Gang
• Is Part Of: Chinese journal of electronics. Volume 26:Issue 2(2017)
• Page Start: 377
• Page End: 384
• Publication Date: 2017-03-01
• Subjects: Wireless sensor networks (WSNs) -- Link quality estimation -- Support vector machine (SVM); decision trees -- parameter estimation -- protocols -- RSSI -- support vector machines -- wireless sensor networks; energy consumption -- decision tree -- packet reception rate -- estimation parameters -- link quality indicator -- receive signal strength indicator -- wireless link characteristics -- multiclass classification -- network protocol -- data transmission -- WSN -- support vector machine -- wireless sensor networks -- link quality estimation mechanism; Electronics -- Periodicals; Electronics -- China -- Periodicals; Electronics; China; Periodicals; 621.38105
• DOI: 10.1049/cje.2017.01.013
• Languages: English
• ISSNs: 1022-4653

Abstract

Abstract : In the application of Wireless sensor networks (WSNs), effective estimation for link quality is a basic issue in guarantying reliable data transmission and upper network protocol performance. A link quality estimation mechanism is proposed, which is based on Support vector machine (SVM) with multi‐class classification. Under the analysis of the wireless link characteristics, two physical parameters of communication, Receive signal strength indicator (RSSI) and Link quality indicator (LQI), are chosen as estimation parameters. The link quality is divided into five levels according to Packet reception rate (PRR). A link quality estimation model based on SVM with decision tree is established. The model is built on kernel functions of radial basis and polynomial respectively, in which RSSI, LQI are the input parameters. The experimental results show that the model is reasonable. Compared with the recent published link quality estimation models, our model can estimate the current link quality accurately with a relative small number of probe packets, so that it costs less energy consumption than the one caused by sending a large number of probe packets. So this model which is high efficiency and energy saving can prolong the network life.