Title: STCS: a practical solar radiation based temperature correction scheme in meteorological WSN

Authors: Baowei Wang; Xiaodu Gu; Shuangshuang Yan

Addresses: School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China; Engineering Research Center of Electronic Information and Control from Fujian Provincial Education Department, Fuzhou, 350108 China; Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing 210044, China; Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science and Technology, Nanjing 210044, China ' School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China; Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science and Technology, Nanjing 210044, China ' School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China; Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science and Technology, Nanjing 210044, China

Abstract: Wireless sensor network (WSN) has been used to construct intelligent meteorological observation network to achieve fine observation data. But the accuracy of the low-cost onboard temperature sensor is too low to meet demand in some applications. To resolve this problem, some pioneer methods have been proposed. But the precision always cannot reach the ideal effect. We propose a solar radiation based air temperature error correction scheme (STCS). After some pretreatments such as interpolation, and time transformation, the relationship between solar radiation and temperature error is established by training GA-BP (Back Propagation neural network optimised by Genetic Algorithm). Then the trained neural network is applied to the temperature correction. Finally, it is the smoothing process to the corrected data. Expermental results show that STCS achieves an average error of smaller than 0.34°C. Consider to three core indicators, our results can be improved by 14%, 6% and 12% respectively.

Keywords: WSN; wireless sensor network; data correction; artificial neural network; solar radiation; meteorological observation.

DOI: 10.1504/IJSNET.2018.094709

International Journal of Sensor Networks, 2018 Vol.28 No.1, pp.22 - 33

Received: 26 Sep 2017
Accepted: 22 Nov 2017

Published online: 08 Sep 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article