Overview of the ML-based fiber monitoring process.

Overview of the ML-based fiber monitoring process.

Source publication
Article
Full-text available
Secure and reliable data communication in optical networks is critical for high-speed Internet. However, optical fibers, serving as the data transmission medium providing connectivity to billons of users worldwide, are prone to a variety of anomalies resulting from hard failures (e.g., fiber cuts) and malicious physical attacks [e.g., optical eaves...

Similar publications

Article
Full-text available
This paper studies data‐driven distributed fault diagnosis for large‐scale systems using sensor networks. To be specific, a distributed fault detection scheme based on correlation analysis is first proposed to improve the fault detection performance by minimizing the impact of noise‐induced uncertainty. The core of the method is to implement the co...
Preprint
Full-text available
The rise of Decentralized Federated Learning (DFL) has enabled the training of machine learning models across federated participants, fostering decentralized model aggregation and reducing dependence on a server. However, this approach introduces unique communication security challenges that have yet to be thoroughly addressed in the literature. Th...

Citations

... Optical network logs contain information about the network's operation, recording events, states, and anomalous activities, which can be utilized for tracking network activities, understanding network status, and managing system security [3,4]. Moreover, due to the high frequency of log generation, analyzing logs enables more efficient and accurate network behavior understanding, failure diagnosis, health monitoring, anomaly detection, and root cause analysis [5][6][7][8][9][10][11][12]. This contributes to further network optimization, diagnostics, and maintenance [13][14][15]. ...
Article
Full-text available
The optical network encompasses numerous devices and links, generating a significant volume of logs. Analyzing these logs is significant for network optimization, failure diagnosis, and health monitoring. However, the large-scale and diverse formats of optical network logs present several challenges, including the high cost and difficulty of manual processing, insufficient semantic understanding in existing analysis methods, and the strict requirements for data security and privacy. Generative artificial intelligence (GAI) with powerful language understanding and generation capabilities has the potential to address these challenges. Large language models (LLMs) as a concrete realization of GAI are well-suited for analyzing DCI logs, replacing human experts and enhancing accuracy. Additionally, LLMs enable intelligent interactions with network administrators, automating tasks and improving operational efficiency. Moreover, fine-tuning with open-source LLMs protects data privacy and enhances log analysis accuracy. Therefore, we introduce LLMs and propose a log analysis method with instruction tuning using LLaMA2 for log parsing, anomaly detection and classification, anomaly analysis, and report generation. Real log data extracted from the field-deployed network was used to design and construct instruction tuning datasets. We utilized the dataset for instruction tuning and demonstrated and evaluated the effectiveness of the proposed scheme. The results indicate that this scheme improves the performance of log analysis tasks, especially a 14% improvement in exact match rate for log parsing, a 13% improvement in F1-score for anomaly detection and classification, and a 23% improvement in usability for anomaly analysis, compared with the best baselines.
... These techniques range from performance monitoring and guaranteeing the transmission to optical network control and management in both transport and access networks [25]. Current studies related to fiber monitoring already use the Machine Learning (ML) approach to detect any anomaly in the optical networks [12,14,26,27]. These studies have shown that ML can detect and localize any fiber faults in the ODN. ...
... Commonly, to detect anomalies in the ODN, engineers are using OTDR, which is a technique based on the Rayleigh backscattering [12]. The concept is like a radar, so the OTDR will send a series of optical pulses into the ODN. ...
... The proposed framework for fault detection and localization with intelligent diagnosis is shown in Figure 6, following the study in [12]. There are five main stages to realize the proposed framework, namely, (1) Data collection: The deployed ODN infrastructure is periodically monitored using OTDR and BER Analyzer. ...
Article
Full-text available
To guarantee the reliability of Tactile Internet (TI) applications such as telesurgery, which demand extremely high reliability and are experiencing rapid expansion, we propose a novel smart resilience mechanism for Next-Generation Ethernet Passive Optical Networks (NG-EPONs). Our architecture integrates Artificial Intelligence (AI) and Software-Defined Networking (SDN)-Enabled Broadband Access (SEBA) platform to proactively enhance network reliability and performance. By harnessing the AI’s capabilities, our system automatically detects and localizes fiber faults, establishing backup communication links using Radio Frequency over Glass (RFoG) to prevent service disruptions. This empowers NG-EPONs to maintain uninterrupted, high-quality network service even in the face of unexpected failures, meeting the stringent Quality-of-Service (QoS) requirements of critical TI applications. Our AI model, rigorously validated through 5-fold cross-validation, boasts an average accuracy of 81.49%, with a precision of 84.33%, recall of 78.18%, and F1-score of 81.00%, demonstrating its robust performance in fault detection and prediction. The AI model triggers immediate corrective actions through the SDN controller. Simulation results confirm the efficacy of our proposed mechanism in terms of delay, system throughputs and packet drop rate, and bandwidth waste, ultimately ensuring the delivery of high-quality network services.
... The emergence of AI technologies can improve attack detection accuracy. Abdelli et al. proposed a method based on a combination of ML and an optical timedomain reflectometer (OTDR) [17], where OTDR traces containing records of different faults (fiber cuts and optical eavesdropping attacks) are first acquired. The anomalies can be detected and localized using a bidirectional gated loop cell ML-based algorithm, achieving a 96.86% correct prediction in the experiment. ...
Article
Full-text available
Ensuring the secure and reliable operation of optical networks is crucial for various societal functions. However, optical network infrastructures are susceptible to unauthorized interception, posing a significant security risk at the physical layer. This necessitates the development of effective detection and localization methods of eavesdropping events. To address this challenge, we present a clustering-based method and a comprehensive eavesdropping diagnosis framework tailored for wavelength division multiplexing (WDM) systems. The framework is designed to handle diverse eavesdropping scenarios, including dynamic detection, classification, and localization of eavesdropping events. To mitigate the data dependency issue while detecting and localizing eavesdropping events, we propose a clustering algorithm utilizing basic optical performance monitoring (OPM) data, thus eliminating the need for sophisticated measurement equipment. A coarse localization requires only the OPM data from the receiver, while a finer localization requires the power monitoring data at all nodes as the input. The feasibility of the proposed scheme is validated using simulation-generated data, in which single and multiple eavesdropping can be detected and localized with a 100% label matching rate. Single-point eavesdropping detection and localization are experimentally validated with data collected from a fiber transmission system comprising three spans of 40 km each. Coarse localization with a 99.79% label matching rate and fine localization with 100% accuracy is achieved. As expected, experimental data shows a less concentrated distribution than the simulated data, which leads to inferior clustering results.
... However, the scarcity of labelled data, particularly for rare anomalies, limits supervised ML approaches. Unsupervised ML methods provide a solution by autonomously learning the structure of normal data and detecting anomalies based on deviations, enhancing detection even with limited anomaly data [7][8][9]. ...
Preprint
Full-text available
We propose a novel unsupervised anomaly detection approach using generative adversarial networks and SOP-derived spectrograms. Demonstrating remarkable efficacy, our method achieves over 97% accuracy on SOP datasets from both submarine and terrestrial fiber links, all achieved without the need for labelled data.
... Lollie et al. [57] have used an encryption process integrated with machine learning to secure optical fiber communication. Tomasov et al. [58] and Abdeli et al. [59] have presented a scheme of anomaly analyzers where machine learning improves the detection rate with a polarization analyzer. ...
Article
Full-text available
An advanced network system (ANS) is characterized by extensive communication features that can support a sophisticated collaborative network structure. This is essential to hosting various forms of upcoming modernized and innovative applications. Security is one of the rising concerns associated with ANS deployment. It is also noted that machine learning is one of the preferred cost-effective ways to optimize the security strength and address various ongoing security problems in ANS; however, it is still unknown about its overall effectivity scale. Hence, this paper contributes to a systematic review of existing variants of machine learning approaches to deal with threat identification in ANS. As ANS is a generalized form, this discussion considers the impact of existing machine learning approaches on its practical use cases. The paper also contributes towards critical gap analysis and highlights the study's potential learning outcome.
... Any disruption of different types of anomalies, including a fiber cut or unauthorized access through eavesdropping can be enormous and must be responded to immediately. The manual discovery of these incidents occurring in the fiber requires considerable knowledge and probing time until a fault is identified [16]. ...
... • Data Loss Prevention: Anomaly detection and localization help prevent major data loss by quickly finding and fixing issues like fiber cuts or eavesdropping attempts that can disrupt data transmission in fiber optic networks [16]. ...
... • Service Continuity: By detecting and pinpointing anomalies, network operators can ensure that thousands of customers continue to receive uninterrupted service. Ensuring the reliability of communication networks is crucial, especially during critical situations [16]. ...
Article
Full-text available
The review aims to assess fifteen (15) academic literature sources, highlighting the application of machine learning algorithms in the maintenance operations of optical fiber networks. It exhibits the collection of data using PRISMA methodology—Preferred Reporting Item for Systems Review and Meta-Analyses. The application, results, and performance metrics are discussed based on the collected observations, computations, and statistics in the studies, which revealed records of high accuracy degrees ranging from 86% to 98% on average and quality ML models including Neural Networks (NNs), Support Vector Machines (SVMs), and LSTM, as well as deep learning models that disclosed effective results of determining challenges and problems within the optical fiber lines. The review mainly centralized on superior machine learning technologies that surpass traditional techniques in fault detection and localization for improved optical fiber networks’ operations while providing insights into the limitations and challenges encountered in real-world applications of these models, offering a comprehensive perspective on the optical fiber network’s domain
... Fan Xinyu proposed a phase-noise-compensated Photonics 2024, 11, 523 2 of 16 method by using the hardware-adaptive algorithm, which can realize a real-time OFDR system with a 37.5 km dynamic range and 7 cm spatial resolution [17]. In addition, many researchers have carried out multi-directional research on optical fiber link fault detection, such as machine-learning-based anomaly detection [18], transmission-reflection analysis method [19], etc. All the above methods detect faults by measuring the characteristics of the LP 01 mode, which improves the accuracy and efficiency of SMF link fault detection and location to a certain extent. ...
... Fan Xinyu proposed a phase-noisecompensated method by using the hardware-adaptive algorithm, which can realize a realtime OFDR system with a 37.5 km dynamic range and 7 cm spatial resolution [17]. In addition, many researchers have carried out multi-directional research on optical fiber link fault detection, such as machine-learning-based anomaly detection [18], transmission-reflection analysis method [19], etc. All the above methods detect faults by measuring the characteristics of the LP01 mode, which improves the accuracy and efficiency of SMF link fault detection and location to a certain extent. ...
Article
Full-text available
This paper presents a few-mode fiber (FMF) various fault-detection method for long-reach mode division multiplexing (MDM) based on multi-mode transmission reflection analysis (MM-TRA). By injecting unmodulated continuous light into the FMF, and measuring and quantitatively analyzing the transmitted and reflected or Rayleigh backscattering power of different spatial modes, it is possible to accurately detect and locate reflective and non-reflective fault events. This paper discusses the localization accuracy of fault types such as FMF break, FMF link connector mismatch, and FMF bending. Theoretical analysis and simulation experimental results demonstrate that the proposed MM-TRA can provide an effective characterization of various faults and can achieve high fault localization accuracy. In addition, the influence of mode crosstalk of mode multiplexer/demultiplexer and mode coupling in FMF on the localization accuracy of various faults are considered. The results indicate that when using the combination of LP01 and LP21 modes, the localization errors for the FMF break, connector mismatch, and bending are 3.42 m, 1.97 m, and 3.29 m, respectively, demonstrating good fault localization performance.
... Any disruption of different types of anomalies, including a fiber cut or unauthorized access through eavesdropping can be enormous and must be responded to immediately. The manual discovery of these incidents occurring in the fiber requires considerable knowledge and probing time until a fault is identified [16]. ...
... • Data Loss Prevention: Anomaly detection and localization help prevent major data loss by quickly finding and fixing issues like fiber cuts or eavesdropping attempts that can disrupt data transmission in fiber optic networks [16]. • Service Continuity: By detecting and pinpointing anomalies, network operators can ensure that thousands of customers continue to receive uninterrupted service. ...
... • Service Continuity: By detecting and pinpointing anomalies, network operators can ensure that thousands of customers continue to receive uninterrupted service. Ensuring the reliability of communication networks is crucial, especially during critical situations [16]. • Enhancement of Security: Anomaly detection and localization enhance network security by identifying and addressing potential security breaches like invasions or attacks, protecting sensitive data transmitted across the network [16]. ...
Preprint
Full-text available
The review aims to assess fifteen (15) academic literature sources, highlighting the application of machine learning algorithms in the maintenance operations of optical fiber networks. It exhibits the collection of data using PRISMA methodology—Preferred Reporting Item for Systems Review and Meta-Analyses. The application, results, and performance metrics are discussed based on the collected observations, computations, and statistics in the studies, which revealed records of high accuracy degrees ranging from 86% to 98% on average and quality ML models including Neural Networks (NNs), Support Vector Machines (SVMs), and LSTM, as well as deep learning models that disclosed effective results of determining challenges and problems within the optical fiber lines. The review mainly centralized on superior machine learning technologies that surpass traditional techniques in fault detection and localization for improved optical fiber networks’ operations while providing insights into the limitations and challenges encountered in real-world applications of these models, offering a comprehensive perspective on the optical fiber network’s domain.
... In such situations, the fiber optics network must ensure the Quality of Service (QoS) and provide uninterrupted connectivity worldwide. Despite many promising features of the fiber optics network, it is highly vulnerable to a variety of failures [3], including fiber cut [4], fiber eavesdropping [5], splicing, bad connector [6], fiber bending, and Physical Contact (PC) connector [7]. These faults can lead to diminished data transfer rates and increased latency, directly impacting the end-user experience [8]. ...
... Furthermore, the Single-Layer Perceptron Neural Networks (SLP NN) technique was developed on simple LR to predict the location of the fiber cut in underground cable [25]. Other techniques, including Autoencoder (AE) and Bidirectional Gated Recurrent Unit (BiGRU) algorithms for anomaly detection [3], are incorporated in fiber optics. However, the above-mentioned works used limited ML/DL techniques for fault detection and localization. ...
... This method only detects and localizes the reflective events in a single fiber and is limited to the prediction of reflective events capacity; it needs further improvement for better accuracy. In addition, Abdelli et al. [3] determined two fiber faults, including fiber cut and eavesdropping, using the ML-based Auto Encoder (AE) model. This model detects the fiber faults using a localized fault detection system. ...
Article
Full-text available
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.
... Unfortunately, such approaches prove inefficient for modern optical networks due to their high dynamics and complexity, lacking the requisite adaptability and scalability [5]. Exploring alternative approaches, such as leveraging optical time domain reflectometry (OTDR) reliant on Rayleigh backscattering, offers a potential solution for pinpointing and identifying optical fiber faults [6][7][8][9]. Nevertheless, these approaches encounter challenges in scalability and practicality when dealing with optical communication systems that extend beyond 100 km, making their implementation intricate and costly [10]. ...
Article
Full-text available
Monitoring the state of polarization (SOP) is crucial for tracking vibrations or disturbances in the vicinity of optical fibers, such as precursors to fiber cuts. While SOP data are valuable for machine learning (ML) models in identifying vibrations, acquiring a sufficient amount of data presents a significant challenge. To overcome this hurdle, we introduce an innovative transfer learning framework designed for the identification of vibrations (events) when confronted with limited SOP data. Our methodology leverages the pre-trained convolutional neural network MobileNet as a feature extractor, incorporating the encoding of time series SOP measurements into images for MobileNet input. We explore different time series encoding techniques, including the Gramian Angular Difference Field (GADF) and the Gramian Angular Summation Field (GASF). Different architectures for building our transfer learning framework based on MobileNet are investigated. Validation of our proposed approaches is conducted using experimental data that simulates movements indicative of fiber break precursors. The experimental results clearly demonstrate the superior performance of our approaches compared to other ML algorithms, especially in scenarios with limited data. Furthermore, our framework surpasses pre-trained CNN models in terms of predictive power, affirming its effectiveness in enhancing the accuracy of vibration identification in the presence of constrained SOP data.