Auto-Tuning PID Distributed Power Control for Next-Generation Passive Optical Networks

This work proposes an adaptive auto-tuning distributed power control strategy aided by proportional-integral-derivative (PID) and by Adaline artificial neural network (AANN) approaches. The power control mechanism is realized for the upstream of next-generation passive optical networks (NG-PON), primarily deployed in the context of optical code division multiplexing access passive networks. The primary results demonstrate the ability of control and adaptive auto-tuning of the proposed AANN-based DPCA, considering realistic error estimates in the optical channel. For the sake of comparison, an adaptive auto-tuning procedure through the Tyreus-Lyuben method is included, indicating superior Euclidean norm of the NMSE performance combined with the lower complexity of the proposed NN-based DPCA method.