Optimal deployment of large-scale wireless sensor networks based on graph clustering and matrix factorization

Abstract It is undeniable that there are a large number of redundant nodes in wireless sensor network. These cause colossal waste resources and seriously threaten the life In this paper, we provide optimization selection algorithm based on graph for large-scale Firstly, propose representation-clustering joint Graph Neural Network to partition into several subgraphs. Then, use Singular-Value-QR Decomposition node each subgraph achieve optimal deployment We conduct experiments CIMIS dataset. The results show mean square error between reconstructed network original as low 0.02433. Meanwhile, also compare our with classical algorithm. imply proposed lower distribution more uniform. Further, verify scalability