Efficient Communication Management in Diffractive Optics IoT Networks for Intelligent Video Transmission

Abstract

Dynamic, intelligent video-centric Internet of Things (IoT) networks need strong communication solutions for high data rates, low latency, and energy efficiency. Radio Frequency (RF)-based IoT frameworks are unsuitable for real-time video transmission because of interference, high retransmission costs, and restricted capacity. This paper suggested DOECOM-VID, a novel architecture that employs diffractive optical elements (DOEs) for interference-free parallel data distribution, phase-front shaping, and multi-channel optical beamforming. In crowded IoT situations, DOECOM-VID's Deep Reinforcement Learning (DRL) optimization engine and Fourier-domain diffractive Multiple-Input Multiple-Output (MIMO) channel model can identify paths, direct beams, and dynamically distribute resources. High Definition (HD) video streaming is enabled via phase-coded diffractive waveguides that improve spatial multiplexing and reduce diffraction losses. DOECOM-VID increases spectral efficiency by 31%, end-to-end latency by 34%, and Peak Signal-to-Noise Ratio (PSNR) by 40.6% over existing IoT video transmission systems. Energy-aware routing and adaptive modulation may extend IoT video node lifespan by 25%. DOECOM-VID delivers interference-resistant, high-capacity optical communication for smart city video analytics, autonomous surveillance, and Augmented Reality/Virtual Reality (AR/VR) streaming. Future expansions will investigate quantum-enhanced diffractive computing for ultra-secure real-time video transmission. Received: 24 October 2025 | Revised: 27 April 2026 | Accepted: 5 August 2026 Conflicts of Interest The authors declare that they have no conflicts of interest in this work. Data Availability Statement The data that support the findings of this study are openly available on Kaggle at https://www.kaggle.com/datasets/saurabhshahane/internos-video-popularity-forecasting/data and https://www.kaggle.com/datasets/thedevastator/video-characteristics-and-transcoding-time/data. Author Contribution Statement Mohammed Abdullah Al-Mekhlafi: Conceptualization, Methodology, Validation, Investigation, Writing – original draft, Writing – review & editing, Visualization, Funding acquisition. Mohammad Kamrul Hasan: Conceptualization, Methodology, Validation, Investigation, Writing – original draft, Writing – review & editing, Visualization. Qusai Y. Shambour: Methodology, Validation, Investigation, Writing – original draft, Writing – review & editing, Funding acquisition. Ali Q. Saeed: Methodology, Validation, Investigation, Writing – original draft, Writing – review & editing, Funding acquisition. Saed Adnan Mustafa: Methodology, Validation, Investigation, Writing – original draft, Writing – review & editing, Funding acquisition. Taher M. Ghazal: Conceptualization, Methodology, Validation, Investigation, Writing – original draft, Writing – review & editing, Visualization, Funding acquisition.