Abstract
This paper demonstrates an unprecedented novel neural network (NN)-based digital predistortion (DPD) solution to overcome the signal impairments and nonlinearities in Analog Optical fronthauls using radio over fiber (RoF) systems. DPD is realized with Volterra-based procedures that utilize indirect learning architecture (ILA) and direct learning architecture (DLA) that becomes quite complex. The proposed method using NNs evades issues associated with ILA and utilizes an NN to first model the RoF link and then trains an NN-based predistorter by backpropagating through the RoF NN model. Furthermore, the experimental evaluation is carried out for Long Term Evolution 20 MHz 256 quadraturre amplitude modulation (QAM) modulation signal using an 850 nm Single Mode VCSEL and Standard Single Mode Fiber to establish a comparison between the NN-based RoF link and Volterra-based Memory Polynomial and Generalized Memory Polynomial using ILA. The efficacy of the DPD is examined by reporting the Adjacent Channel Power Ratio and Error Vector Magnitude. The experimental findings imply that NN-DPD convincingly learns the RoF nonlinearities which may not suit a Volterra-based model, and hence may offer a favorable trade-off in terms of computational overhead and DPD performance.
Highlights
The fifth generation, commonly known as 5G, of mobile networks is envisioned to uplift capacity, efficiency, capacity and latency [1]
This paper presents a novel unprecedented digital predistortion (DPD)-based neural network (NN) architecture and training method for radio over fiber (RoF) link efficiency enhancement
A comparative evaluation study was carried out experimentally between NN- and Volterra (MP/Generalized Memory Polynomial (GMP))-based DPD methods, and system potential was measured in terms of mean squared error (MSE), ACPR and EVM
Summary
The fifth generation, commonly known as 5G, of mobile networks is envisioned to uplift capacity, efficiency, capacity and latency [1]. The Centralized/Cloud Radio Access Network (C-RAN) primarily simplifies the network traffic and enhances the scalability (see Figure 1). In this context, microwave photonics techniques such as radio over fiber (RoF) systems are the backbone of fed analog or digital signals in optical FH using RoF systems. RoF systems provide cost effective and beneficial solutions by escalating the extent of wireless links for short, medium and long reach networks [3,4] Other than their significant highlights, such as impunity to electromagnetic interventions, low-loss and broad bandwidth, RoF links are liable to nonlinearities which can be solved using linearization methods [5,6,7]. A-RoF suffers from nonlinearities, still due to the complexity of the other realizations and advantages in A-RoF that include simplicity, cost effectiveness and already widely spread Photonics 2021, 8, x FOR PEER REVIElWegacy infrastructure, making it a better choice as compared to more efficient and c2osotfl1y6 solutions, such as D-RoF and S-DRoF [12]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
