MultipropNet Advancing OAM-Based FSO Communication for Flexible Multi-Distance Transmissions
Badreddine Merabet, Aleksandr Kireev, Sergey S. Stafeev, Elena S. Kozlova, Zhongyi Guo
Abstract
The escalating data traffic in smart cities, driven by numerous connected devices and data-intensive applications, necessitates advanced communication. Traditional wireless networks are hindered by bandwidth limitations, high latency, and interference. Free Space Optical (FSO) communication leveraging orbital angular momentum (OAM) offers a promising alternative by enabling high-capacity, interference-free data transmission through the atmosphere. This study introduces MultipropNet, a deep learning model based on Convolutional Neural Networks (CNN), designed to address the challenge of varying propagation distances in OAM-based FSO communication. The model supports multi-distance communication and facilitates duplex data transfer between emitters and receivers, overcoming issues caused by differing OAM beam waists. Furthermore, the concept of an Intermediate Node (Relay) is introduced to mitigate the effects of atmospheric turbulence (AT) in long-distance communication links. This approach significantly improves flexibility and resilience compared to traditional fixed-distance, unidirectional systems. Tested under severe AT conditions (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i><sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sub><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 1 × 10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-13</sup><italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-2/3</sup> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i><sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sub><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 7 × 10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-13</sup><italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-2/3</sup>), the model has achieved classification accuracies of 99.66% for four multiplexed OAM beams (resulting in 16 beams) and 96.24% under higher turbulence, alongside low bit error rates (BER) in image transmissions with a value of 0.0067 for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i><sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sub><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 1 × 10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-13</sup> <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-2/3</sup> and 0.1430 for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i><sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sub><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 7 × 10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-13</sup><italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-2/3</sup>. This advancement delves into the ultimate potential of OAM-based FSO systems, establishing a robust foundation for high-speed, reliable wireless communication infrastructures in smart cities.