Extreme Learning Machines to Combat Phase Noise in RoF-OFDM Schemes

Abstract

Radio-over-fiber (RoF) orthogonal frequency division multiplexing (OFDM) systems have been revealed as the solution to support secure, cost-effective, and high-capacity wireless access for the future telecommunication systems. Unfortunately, the bandwidth-distance product in these schemes is mainly limited by phase noise that comes from the laser linewidth, as well as the chromatic fiber dispersion. On the other hand, the single-hidden layer feedforward neural network subject to the extreme learning machine (ELM) algorithm has been widely studied in regression and classification problems for different research fields, because of its good generalization performance and extremely fast learning speed. In this work, ELMs in the real and complex domains for direct-detection OFDM-based RoF schemes are proposed for the first time. These artificial neural networks are based on the use of pilot subcarriers as training samples and data subcarriers as testing samples, and consequently, their learning stages occur in real-time without decreasing the effective transmission rate. Regarding the feasible pilot-assisted equalization method, the effectiveness and simplicity of the ELM algorithm in the complex domain are highlighted by evaluation of a QPSK-OFDM signal over an additive white Gaussian noise channel at diverse laser linewidths and chromatic fiber dispersion effects and taking into account several OFDM symbol periods. Considering diverse relationships between the fiber transmission distance and the radio frequency (for practical design purposes) and the duration of a single OFDM symbol equal to 64 ns, the fully-complex ELM followed by the real ELM outperform the pilot-based correction channel in terms of the system performance tolerance against the signal-to-noise ratio and the laser linewidth.