基于最优保存并行混合遗传算法的直接盲信号检测

Direct blind signal detection based on a parallel hybrid genetic algorithm using optimal save strategy

针对现有的盲均衡遗传算法适应度函数构造复杂,辨识信道结构简单,只能在连续空间搜索的问题,本文借助接收数据阵补投影算子对待测发送序列向量的零化作用,把信号盲检测问题转化为整数约束下的二次规划问题,提出了基于最优保存并行混合遗传算法的直接盲信号检测的方法。本文所用遗传算法的特点是:适应度函数是针对被检测序列直接构造的,编码空间与遗传空间一致,搜索是离散、有限的,最优保存策略保证算法每一步搜索能够保存最佳基因。仿真结果表明,该算法收敛速度快,性能稳定。

Focusing on the problerms existed in some blind equalization genetic algorithms that the fitness functions is too intricate, only equalize simple channels and search continuous space, this paper takes complementary projection operator of a received data matrix as annihilator of a transmitted sequence vector to be detected , and then formulates the blind detection problem into a quadratic optimization with integral constraints. A novel direct blind signal detection based on a parallel hybrid genetic algorithm using optimal save strategy is proposed. The characteristic of this algorithm is that the fitness function is formatted with the transmitted sequences, the encodeing space is identical to the genetic space, and the searching space is discrete and finite, the optimal save strategy ensures that the algorithm can save the best gene by every searching steps. Simulations show that the algorithm achieves good astringency and satisfactory performance.