Efficient optical network management poses significant importance in backhaul and access network communication for preventing service disruptions and ensuring Quality of Service (QoS) satisfaction. The emerging faults in optical networks introduce challenges that can jeopardize the network with a variety of faults. The existing literature witnessed various partial or inadequate solutions. On the other hand, Machine Learning (ML) has revolutionized as a promising technique for fault detection and prevention. Unlike traditional fault management systems, this research has three-fold contributions. First, this research leverages the ML and Deep Learning (DL) multi-classification system and evaluates their accuracy in detecting six distinct fault types, including fiber cut, fiber eavesdropping, splicing, bad connector, bending, and PC connector. Secondly, this paper assesses the classification delay of each classification algorithm. Finally, this work proposes a fiber optics fault prevention algorithm that determines to mitigate the faults accordingly. This work utilized a publicly available fiber optics dataset named OTDR_Data and applied different ML classifiers, such as Gaussian Naive Bayes (GNB), Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), and Decision Tree (DT). Moreover, Ensemble Learning (EL) techniques are applied to evaluate the accuracy of various classifiers. In addition, this work evaluated the performance of DL-based Convolutional Neural Network and Long-Short Term Memory (CNN-LSTM) hybrid classifier. The findings reveal that the CNN-LSTM hybrid technique achieved the highest accuracy of 99% with a delay of 360 s. On the other hand, EL techniques improved the accuracy in detecting fiber optic faults. Thus, this research comprehensively assesses accuracy and delay metrics for various classifiers and proposes the most efficient attack detection system in fiber optics.

A low-profile reflectarray has been designed in the Ka-band to efficiently generate wideband orbital angular momentum (OAM) vortex beams. The proposed design employs a reflective phase-shifting patch etched onto a dielectric substrate, featuring a three-square loop structure intersected by two transverse dipoles. This unit cell achieves a 440° phase shift at 30 GHz with a minimal magnitude loss of (−0.25 dB), enabling high-efficiency reflectarray performance. The OAM vortex beam supports high-order phase distributions ($l=+1,+2,+3,+4$) modes, though fabrication and experimental validation focused on the $+1$ mode. Measurements confirm that the reflectarray produces a high-purity OAM vortex beam for +1 mode, covering the operational frequency range from 27 to 39 GHz, and achieving a 40% bandwidth with a peak gain of 23.39 dBi at 33 GHz and an aperture efficiency of 17.38%. These results demonstrate the ability of the reflectarray to produce broadband directive OAM beams with robust performance, making it ideal for Ka-band communication systems.

Efficient decentralized power management is crucial for enhancing the reliability, resilience, responsiveness, and sustainability of secondary power distribution systems, thereby preventing major power outages and providing rapid responses. However, existing secondary power distribution networks are prone to failures, thus compromising their operational trustworthiness and efficiency. This work proposes an intelligent, decentralized control system with distributed processing capabilities. The proposed system is designed to automate fault detection and rectification along with optimized power management at secondary distribution nodes. The system enables rapid fault detection (line-to-line, line-to-ground, and overload) and initiates a fault-based response to isolate the load through controlled relays. Additionally, an intelligent power management system automatically rectifies surge faults (short-lived faults) and reports non-surge faults (persistent faults) to the control center. It continuously updates the status of real-time power parameters to the database using a Global System for Mobile Communications (GSM)-based communication system with a frequency of 60 s per sample for power management. The Proteus-based simulation and a scaled-down model validate the efficiency and supremacy of the proposed system over the existing control system for power distribution nodes. The results demonstrate that our model detects critical faults and initiates the response within 100 and 200 milliseconds, respectively. Surge faults are automatically rectified within 90 s, while non-surge faults are reported to the database after 90 s. This approach significantly reduces downtime, enables energy accountability, and supports sustainable energy management through a decentralized and distributed control system.