Enhanced deep learning based channel estimation for indoor VLC systems

This paper aims to improve the channel estimation (CE) in the indoor visible light communication (VLC) system. We propose a system that depends on a comparison between Deep Neural Networks (DNN) and Kalman Filter (KF) algorithm for two optical modulation techniques; asymmetrically clipped optical-orthogonal frequency-division multiplexing (ACO-OFDM) and direct current optical-orthogonal frequency division multiplexing (DCO-OFDM). The channel estimation can be evaluated by changing the rate of errors in the received bits, where increased error means a performance decrease of the system and vice versa. Receiving less errors at the receiver indicates improved channel estimation and system performance. Thus, the main aim of our proposal is decreasing the error rate by using different estimators. Using the simulation results with the metric parameter of bit error rate (BER) aims to determine the improvement ratio between different systems. The proposed model is trained with OFDM signal samples with labels, where the labels represent the received signal after applying OFDM travelling across the medium. At a BER = 10–3 with DCO-OFDM, the DNN outperforms KF with 1.6 dB (7.6%) at the bit energy per noise $$({{\varvec{E}}}_{{\varvec{b}}}/{{\varvec{N}}}_{{\varvec{o}}})$$ ( E b / N o ) axis. Also, for ACO-OFDM at BER = 10–3, the DNN achieves better results than KF by about 1.3 dB (8.12%) at the $$({{\varvec{E}}}_{{\varvec{b}}}/{{\varvec{N}}}_{{\varvec{o}}}).$$ ( E b / N o ) . At different values of M in QAM, the DNN outperforms KF for ACO-OFDM by average improvement of ~ 1 dB (~ 11.5%).