A graph invariant is a number that can be easily and uniquely calculated through a graph. Recently, part of mathematical graph invariants has been portrayed and utilized for relationship examination. Nevertheless, no reliable appraisal has been embraced to pick, how much these invariants are associated with a network graph in interconnection networks of various fields of computer science, physics, and chemistry. In this paper, the study talks about sudoku networks will be networks of fractal nature having some applications in computer science like sudoku puzzle game, intelligent systems, Local area network (LAN) development and parallel processors interconnections, music composition creation, physics like power generation interconnections, Photovoltaic (PV) cells and chemistry, synthesis of chemical compounds. These networks are generally utilized in disorder, fractals, recursive groupings, and complex frameworks. Our outcomes are the normal speculations of currently accessible outcomes for specific classes of such kinds of networks of two unmistakable sorts with two invariants K-banhatti sombor (KBSO) invariants, Irregularity sombor (ISO) index, Contraharmonic-quadratic invariants (CQIs) and dharwad invariants with their reduced forms. The study solved the Sudoku network used in mentioned systems to improve the performance and find irregularities present in them. The calculated outcomes can be utilized for the modeling, scalability, introduction of new architectures of sudoku puzzle games, intelligent systems, PV cells, interconnection networks, chemical compounds, and extremely huge scope in very large-scale integrated circuits (VLSI) of processors.