基于遗传算法的最小误码率线性多用户检测

Minimum-BER Linear Multiuser Detection Based on Genetic Algorithm

本文提出了一种多用户检测算法,算法基于最小误码率准则,应用内核密度估计方法来估计误码率函数,并采用基于实数编码的遗传算法来搜索误码率函数全局最小点。该算法解决了由于误码率函数存在局部最小点而难以用普通的梯度算法来求解全局最优点的问题。算法对初值的选取无特殊要求,可随机选取。仿真结果表明,梯度算法求解最小误码率检测器由于可能收敛到次优的局部极小点,故检测器不能达到最小误码率性能;而本文基于遗传算法的多用户检测由于能很好的避免收敛到次优的局部极小点,因而得到的检测器性能逼近最小误码率。

In this paper, a minimum bit-error rate (MBER) multiuser detection algorithm is proposed. Because the bit-error rate (BER) function is highly nonlinear, a specially designed genetic algorithm (GA) is used to solve this optimization problem. Simulation results show that the algorithm has high convergence speed and its performance approaches the exact minimum bit error rate, whereas existing gradient descendant method may capture a local minimum.