Towards Fault-Tolerant Systems based on Adaptive Cellular Genetic Algorithms

This paper presents an adaptive cellular genetic algorithm (cGA) which aims at realizing a fault tolerant platform that determines the attitude parameters of a vehicle, based on Global Positioning System (GPS) technology. This research work investigates the inherent ability of cGAs to deal with single hardware errors (SHEs) that could permanently affect the operation of a system. The proposed approach is based on measuring the genetic diversity behaviour during the evolutionary process and thus to control the exploitation/exploration tradeoff via the grid to neighbourhood ratio, a parameter specific to cGAs topologies. By appropriately controlling this parameter, the complex search space (presenting multi-peak fitness-function) associated with attitude determination, is conveniently explored in terms of efficiency and efficacy.