Neural Network-based scheme for PAPR reduction in OFDM Systems
| Autor: | Felipe Grijalva, Martha Cecilia Paredes Paredes, Diego Javier Reinoso-Chisaguano, Jorge Carvajal-Rodriguez |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Reduction (complexity)
Artificial neural network Computer science Orthogonal frequency-division multiplexing Fast Fourier transform Transmitter Computer Science::Networking and Internet Architecture Bit error rate Data_CODINGANDINFORMATIONTHEORY Algorithm Subcarrier Computer Science::Information Theory Block (data storage) |
| Zdroj: | 2019 IEEE Fourth Ecuador Technical Chapters Meeting (ETCM). |
| DOI: | 10.1109/etcm48019.2019.9014895 |
| Popis: | This paper proposes a neural network-based scheme for Peak-to-Average Power Ratio (PAPR) reduction which also replaces the Inverse Fast Fourier Transform (IFFT) block of an Orthogonal Frequency Division Multiplexing (OFDM) transmitter. The scheme is composed by one neural network per subcarrier, which are implemented only in the transmitter. The training inputs of each neural network are frequency-domain OFDM symbols and the outputs are time-domain PAPR reduced OFDM symbols obtained using a Branch-and-Bound Constellation Extension (BBCE) scheme. The results show that our scheme achieves a PAPR reduction and Bit Error Rate (BER) similar to constellation shaping techniques but with reduced complexity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|