In this work we propose a digital symbol synchronizer for M-PSK modulations based on the Q-Learning algorithm. Through Reinforcement Learning, the system is able to autonomously adapt to environment changes, learning the correct Timing Recovery Loop behavior. The proposed synchronizer has been tested considering a white gaussian noisy channel. We analyzed the modulation error rate and the signal to noise ratio. The obtained results show improved timing recovery capabilities exhibiting a lower locking time.
Cardarilli, G.c., Di Nunzio, L., Fazzolari, R., Giardino, D., Guadagno, M., Re, M., et al. (2022). A M-PSK Timing Recovery Loop Based on Q-Learning. In International Conference on Applications in Electronics Pervading Industry, Environment and Society: ApplePies 2021: Applications in Electronics Pervading Industry, Environment and Society (pp.39-44). Springer Science and Business Media Deutschland GmbH [10.1007/978-3-030-95498-7_6].
A M-PSK Timing Recovery Loop Based on Q-Learning
Cardarilli G. C.;Di Nunzio L.;Fazzolari R.;Re M.;Spano S.
2022-01-01
Abstract
In this work we propose a digital symbol synchronizer for M-PSK modulations based on the Q-Learning algorithm. Through Reinforcement Learning, the system is able to autonomously adapt to environment changes, learning the correct Timing Recovery Loop behavior. The proposed synchronizer has been tested considering a white gaussian noisy channel. We analyzed the modulation error rate and the signal to noise ratio. The obtained results show improved timing recovery capabilities exhibiting a lower locking time.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
