IoT 18(14): e4

Research Article

Condition Monitoring for Wireless Sensor Network-Based Automatic Weather Stations

Download91 downloads
  • @ARTICLE{10.4108/eai.20-12-2018.156083,
        author={Mary Nsabagwa and Julianne Sansa Otim and Roseline Nyongarwizi Akol and Grace Ninsiima and Robert Mwesigye and Maximus Byamukama and Bj\o{}rn Pehrson},
        title={Condition Monitoring for Wireless Sensor Network-Based Automatic Weather Stations},
        journal={EAI Endorsed Transactions on Internet of Things},
        volume={4},
        number={14},
        publisher={EAI},
        journal_a={IOT},
        year={2018},
        month={12},
        keywords={Automatic Weather Station (AWS), condition monitoring, queuing, Wireless Sensor Networks},
        doi={10.4108/eai.20-12-2018.156083}
    }
    
  • Mary Nsabagwa
    Julianne Sansa Otim
    Roseline Nyongarwizi Akol
    Grace Ninsiima
    Robert Mwesigye
    Maximus Byamukama
    Björn Pehrson
    Year: 2018
    Condition Monitoring for Wireless Sensor Network-Based Automatic Weather Stations
    IOT
    EAI
    DOI: 10.4108/eai.20-12-2018.156083
Mary Nsabagwa1,*, Julianne Sansa Otim1, Roseline Nyongarwizi Akol2, Grace Ninsiima1, Robert Mwesigye1, Maximus Byamukama2, Björn Pehrson3
  • 1: Department of Networks, Makerere University, Kampala, Uganda
  • 2: Department of Electrical & Computer Engineering
  • 3: KTH Royal Institute of Technology, Stockholm, Sweden
*Contact email: mnsabagwa@cit.a.ug

Abstract

Wireless Sensor Network (WSN)-based Automatic Weather Stations (AWSs) perform automatic collection and transmission of weather data. These AWSs face challenges, which lower their performance. Hence, a need for regular monitoring to reduce down time. We propose condition monitoring, comprised of a data receiver, analyser, problem classifier and reporter and visualizer, to mine data relationships, identify possible causes of problems and perform reporting of AWS status. The data receiver uses an M/M/1/k queuing model. We use Successive Pairwise REcord Differences (SPREDs) algorithm to compare arrival rates and packet content so as to establish sensor, node and AWS level performance. We also perform a hybrid of Grubb outlier detection and correlations amongst related variables for data validation. Problems take on one of four states. One connection can receive data at a rate as low as 1ms, without loss while problem identification especially in high density network is improved.