TY - GEN
T1 - Orthogonal neural network based predistortion for OFDM systems
AU - Rodriguez, Nibaldo
AU - Cubillos, Claudio
PY - 2007
Y1 - 2007
N2 - This paper proposes a predistortion scheme based on an orthogonal hidden layer feedforward neural network for reducing nonlinear distortion introduced by a traveling wave tube amplifier (TWTA) over orthogonal frequency division multiplexing (OFDM) signals. In predistorter, the inputs weight are fixed and based on this the output weights are analytically determined. Computer simulation results confirm that once the 16QAM-OFDM signals are predistorted and amplified at an input back-off level of 0 dB there is a bit error rate performance very close to the ideal case of linear amplification.
AB - This paper proposes a predistortion scheme based on an orthogonal hidden layer feedforward neural network for reducing nonlinear distortion introduced by a traveling wave tube amplifier (TWTA) over orthogonal frequency division multiplexing (OFDM) signals. In predistorter, the inputs weight are fixed and based on this the output weights are analytically determined. Computer simulation results confirm that once the 16QAM-OFDM signals are predistorted and amplified at an input back-off level of 0 dB there is a bit error rate performance very close to the ideal case of linear amplification.
UR - http://www.scopus.com/inward/record.url?scp=47349106549&partnerID=8YFLogxK
U2 - 10.1109/CERMA.2007.4367690
DO - 10.1109/CERMA.2007.4367690
M3 - Conference contribution
AN - SCOPUS:47349106549
SN - 0769529747
SN - 9780769529745
T3 - Electronics, Robotics and Automotive Mechanics Conference, CERMA 2007 - Proceedings
SP - 225
EP - 228
BT - Electr., Rob. Autom. Mech. Conf., CERMA - Proc.
T2 - Electronics, Robotics and Automotive Mechanics Conference, CERMA 2007
Y2 - 25 September 2007 through 28 September 2007
ER -