About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
ew 23(1):

Research Article

Analysis of Improved Particle Swarm Algorithm in Wireless Sensor Network Localization

Download107 downloads
Cite
BibTeX Plain Text
  • @ARTICLE{10.4108/ew.3431,
        author={Yafeng Chen},
        title={Analysis of Improved Particle Swarm Algorithm in Wireless Sensor Network Localization},
        journal={EAI Endorsed Transactions on Energy Web},
        volume={10},
        number={1},
        publisher={EAI},
        journal_a={EW},
        year={2023},
        month={9},
        keywords={improved partical swarm algorithm, WSN, backward learning, chaotic search, linear fitting},
        doi={10.4108/ew.3431}
    }
    
  • Yafeng Chen
    Year: 2023
    Analysis of Improved Particle Swarm Algorithm in Wireless Sensor Network Localization
    EW
    EAI
    DOI: 10.4108/ew.3431
Yafeng Chen,*
    *Contact email: Yafeng_Chen2023@outlook.com

    Abstract

    WSN localization occupies an important position in the practical application of WSN. To complete WSN localization efficiently and accurately, the article constructs the objective function based on the target node location constraints and maximum likelihood function. It avoids premature convergence through the PSO algorithm based on chaos search and backward learning. Based on linear fitting, the node-flipping fuzzy detection method is proposed to perform the judgment of node flipping fuzzy phenomenon. And the detection method is combined with the localization algorithm, and the final WSN localization algorithm is obtained after multi-threshold processing. After analysis, it is found that compared with other PSO algorithms, the MTLFPSO algorithm used in the paper has better performance with the highest accuracy of 83.1%. Different threshold values will affect the favorable and error detection rates of different WSNs. For type 1 WSNs, the positive detection rate of the 3-node network is the highest under the same threshold value, followed by the 4-node network; when the threshold value is 7.5 (3 ), the positive detection rate of the 3-node network is 97.8%. Different numbers of anchor nodes and communication radius will have specific effects on the number of definable nodes and relative localization error, in which the lowest relative localization error of the MTLFPSO algorithm is 3.4% under different numbers of anchor nodes; the lowest relative localization error of MTLFPSO algorithm is 2.5% under different communication radius. The article adopts the method to achieve accurate and efficient localization of WSNs.

    Keywords
    improved partical swarm algorithm, WSN, backward learning, chaotic search, linear fitting
    Received
    2023-06-09
    Accepted
    2023-08-24
    Published
    2023-09-11
    Publisher
    EAI
    http://dx.doi.org/10.4108/ew.3431

    Copyright © 2023 Chen., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.

    EBSCOProQuestDBLPDOAJPortico
    EAI Logo

    About EAI

    • Who We Are
    • Leadership
    • Research Areas
    • Partners
    • Media Center

    Community

    • Membership
    • Conference
    • Recognition
    • Sponsor Us

    Publish with EAI

    • Publishing
    • Journals
    • Proceedings
    • Books
    • EUDL