A Digital Pre-distortion Scheme for CMMB Repeater System Based On Dynamic Neural Networks - Details

author：

Lin, Zebiao (Lin, Zebiao.) ^[1] | Huang, Chunhui (Huang, Chunhui.) ^[2] (Scholars：黄春晖)

Indexed by：

CPCI-S EI Scopus

Abstract：

CMMB　technology　employs　Orthogonal　Frequency　Division　Multiplexing　(OFDM)　modulation　with　4096　subcarriers　for　8MHz　bandwidth　mode,　HPA　in　the　CMMB　repeater　will　cause　significant　distortion　and　spectral　extension.　To　compensate　HPA　nonlinearity　and　memory　effect　in　a　CMMB　repeater　system,　this　paper　proposed　a　pre-distortion　scheme　based　on　RNN　and　Bayesian　Regularization　for　the　first　time.　Computer　simulation　is　used　to　confirm　the　validation　of　the　proposed　scheme　and　an　adjacent　channel　leakage　ratio　(ACLR)　improvement　of　20　dB　is　obtained　in　the　paper.

Keyword：

Bayesian Regularization China Mobile Multimedia Broadcasting (CMMB) high-power amplifier (HPA) memory effect recurrent neural network (RNN)

Community：

[ 1 ] [Lin, Zebiao]Fuzhou Univ, Coll Phys & informat Engn, Fuzhou 350108, Peoples R China
[ 2 ] [Huang, Chunhui]Fuzhou Univ, Coll Phys & informat Engn, Fuzhou 350108, Peoples R China

Reprint 's Address：