改进磷虾群与NBN联合优化神经网络的HPA预失真方法  

HPA Predistortion Method Based on Neural Network Optimized by the Joint Algorithm of Improved Krill Herd and NBN

作　　者：吴林煌[1] 陈志峰[1] 苏凯雄[1] 郭里婷[1] 王卫星[1] 

机构地区：[1]福州大学物理与信息工程学院,福建福州350116

出　　处：《四川大学学报（工程科学版）》2016年第6期149-159,共11页Journal of Sichuan University (Engineering Science Edition)

基　　金：国家自然科学基金资助项目(61401099;61401100)

摘　　要：为克服现有神经网络预失真方法复杂度高、易陷入局域最小等缺陷,提出一种正交差分进化磷虾群(ODEKH)与neuron-by-neuron(NBN)算法联合优化实数固定延时全连接级联神经网络(RVFTDFCCNN)的高功率放大器预失真方法。采用RVFTDFCCNN对预失真系统中的预失真器和逆估计器进行建模,通过ODEKH算法进行全局搜索获得RVFTDFCCNN的初始化参数,再用NBN算法对RVFTDFCCNN进行训练,同时根据复合函数求偏导数的链式规则,从2个层次对NBN算法中的Jacobian矩阵元素计算进行优化。采用宽带DTMB信号作为输入信号,对预失真系统进行仿真。结果表明:当训练误差和泛化误差均在同一数量级时,RVFTDFCCNN的NBN算法计算量比单隐层(SHL)神经网络明显降低;ODEKH算法比传统磷虾群算法具有更快的收敛速度,ODEKH-NBN联合算法的训练精度比Levenberg-Marquardt(LM)算法提高一个数量级,预失真后的邻道功率比(ACPR)比LM算法改善了2 d B。说明本文的预失真方法具有较低的复杂度和良好的预失真性能。In order to overcome the defects of high complexity and probability of falling into the local minimum occurred in the present neural network （NN） based predistortion methods,a new predistortion method based on real-valued focused time-delay fully connected cascade neural network （RVFTDFCCNN） trained by the joint algorithm of orthogonal differential evolution krill herd （ODEKH） and neuron-by-neuron （NBN） was proposed. Both the predistorter and the inverse estimator in the predistortion system were modeled by RVFTDFCCNN. The initial parameters of RVFTDFCCNN were first obtained by the ODEKH algorithm with strong global search ability. Then the RVFTDFCCNN was further trained by NBN algorithm. According to the chain rule of complex function partial derivative, the calculation of the Jacobian matrix in the NBN algorithm was optimized at two levels. In the simulation, the DTMB wideband signal was used as the input signal of the predistortion system. The simulation results showed that with the same requirement of the training error and the generalization error, the computation amount of the NBN algorithm in training RVFTDFCCNN was considerably reduced than that in SHL neural network. The ODEKH algorithm converged faster than the traditional krill herd algorithm. The joint ODEKH-NBN training algorithm had higher training accuracy than the Levenberg-Marquardt （LM） training algorithm by one amplitude order, and out- performed the latter algorithm by 2 dB in terms of adjacent channel power ratio （ACPR） of the HPA output signal after predistortion. Thus it was concluded that the proposed predistortion method owned low complexity and good predistortion performance.

关 键 词：高功率放大器 预失真 磷虾群算法 神经网络 NBN算法 

分 类 号：TN919.72[电子电信—通信与信息系统]