Extreme-Learning-Machine-Based Noniterative and Iterative Nonlinearity Mitigation for LED Communication Systems

Abstract

This work concerns receiver design for light emitting diode (LED) communications where the LED nonlinearity can severely degrade the performance of communications. We propose extreme learning machine (ELM) based non-iterative receivers and iterative receivers to effectively handle the LED nonlinearity and memory effects. For the iterative receiver design, we also develop a data-aided receiver, where data is used as virtual training sequence in ELM training. It is shown that the ELM based receivers significantly outperform conventional polynomial based receivers; iterative receivers can achieve huge performance gain compared to non-iterative receivers; and the data-aided receiver can reduce training overhead considerably. This work can also be extended to radio frequency communications, e.g., to deal with the nonlinearity of power amplifiers.

Massive MIMO as an Extreme Learning Machine

“…The parameters to be learned in ELM are the output weights, which boils down to solving a linear system, making ELM fast in learning. ELM has been investigated for light emitting diode (LED) communications in our previous works [7], [8] to tackle LED nonlinearity and/or cross-LED interference. We have designed ELM based non-iterative and iterative receivers [8], and our investigations demonstrate that ELM is very effective to handle nonlinearity, delivering much better performance than polynomial based techniques [9], [10].…”