|
| A Reduction Scheme of PAPR in CO-OFDM System Using Time-Delay Neural Networks |
|
| Abstract: |
| An iterative partial transmission sequence (IPTS) cascading time-delay neural network (TDNN) scheme is proposed to reduce peak-to-average power ratio (PAPR) in the coherent optical orthogonal frequency division multiplexing (CO-OFDM) systems. The IPTS algorithm further reduces computational complexity based on the partial transmission sequence (PTS) algorithm. TDNN is trained by the iterative clipping filtering (ICF) method. Simulation results show that the proposed scheme achieves a PAPR reduction of 5.84 dB when complementary cumulative distribution function (CCDF) is 10-4 and an extra transmission distance of 200 km for 10-3 bit error rate (BER) compared to the original signals. |
| Hits: 0 |
| Download times: 0 |
| The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan) |
| Download reader |
