CAJ | 학술논문

射频功率放大器工作在近饱和点时产生的非线性效应是制约其性能提升的主要因素.提出了一种基于支持向量机的预失真算法.通过引入核函数,可以在高维空间中线性地实现相对于输入空间为非线性的问题,达到更好的预失真效果.采用基于傅立叶核函数与多项式核函数的混合核函数并运用于预失真函数的估计中,提高了算法的学习能力和泛化能力.仿真结果表明,所提算法性能优于传统的基于最小均方的数字预失真算法.
사빈공솔방대기공작재근포화점시산생적비선성효응시제약기성능제승적주요인소.제출료일충기우지지향량궤적예실진산법.통과인입핵함수,가이재고유공간중선성지실현상대우수입공간위비선성적문제,체도경호적예실진효과.채용기우부립협핵함수여다항식핵함수적혼합핵함수병운용우예실진함수적고계중,제고료산법적학습능력화범화능력.방진결과표명,소제산법성능우우전통적기우최소균방적수자예실진산법.
@@@@The nonlinear effect of power amplifier working near the saturation point becomes the main factor that degrades its performance. This paper proposes a DPD (Digital Predistortion) algorithm based on the support vector machine (SVM). By introducing the kernel function, a complex nonlinear problem existing in the input space could be transformed to a linear problem, which is mapped to a high-dimension space, thus to achieve a better predistortion. With the new hybrid kernel function described in this paper, which is a combination of the Fourier kernel function and the polynomial kernel function, the learning and generalization ability of the algorithm for the estimation of predistortion function is improved. The simulation results indicate that the performance of the proposed algorithm is better than that of the traditional DPD algorithm based on LMS (Least Mean Square).