Three Bio-Inspired Approaches to Telecommunications Defect-Tracking and Reliability-Estimation

Three alternative bio-inspired approaches are proposed to investigate telecommunication system reliability and defect tracking. They employ a recent model for the failure discovery in the associated system software. These are: half-sibling and a clone (HSAC) genetic algorithm; a recurrent dynamic neural network (RDNN) requiring parametric adjustments and using wavelets as basis; another RDNN with Adaptive parameters to incoming stream of input data, such that the error in failure intensity is minimized, subject to the model constraints. Each approach aims to improve speed of convergence, reliability, noise tolerance, and suitability for hardware implementation. Simulation results seem to favor the ARDNN since it iterates (about 10) on the shape of the wavelet basis and provide adequate recovery of the data in the form of piecewise linear differential.