Feasibility of applying genetic algorithms in space-time block coded multiuser detection systems

A genetic algorithm (GA) for sub-optimal detection applied in space-time block coded (STBC) multiuser detection (MUD) systems in a Rayleigh flat-fading channel is reported for the first time. The technique yields a computational complexity which is two orders lower than that of conventional maximal likelihood (ML) detection. The simulation results confirmed the feasibility of applying GA to solve STBC MUD problems. The bit error rate (BER) performance of the proposed receiver can approach that of the ML detection after sufficient generations.