DISTRIBUTED FIBER OPTIC SENSING-SUPPORTED ARTIFICIAL INTELLIGENCE-BASED SELF-ADAPTIVE TELECOMMUNICATIONS INFRASTRUCTURE MANAGEMENT SYSTEM

Abstract

The invention relates to a self-adaptive, AI-based telecommunications infrastructure management system with distributed fiber optic sensing support, developed for use in telecommunications and fiber optic communication infrastructures. It utilizes existing fiber optic cables for both data transmission and distributed environmental sensing, performing functions such as physical security, fault prediction, network performance monitoring, and dynamic resource management with AI assistance.

Description

1 TARIFF INTELLIGENCE-BASED SELF-TRACKING SUPPORTED BY DISTRIBUTED FIBER OPTIC SENSING ADAPTED TELECOMMUNICATIONS INFRASTRUCTURE MANAGEMENT SYSTEM Technical Area 5 The invention is intended for use in telecommunications and fiber optic communication infrastructures. The developed system utilizes existing fiber optic cables for both data transmission and distributed environmental sensing. using it for purposes such as physical security, fault prediction, network performance monitoring and dynamics. Distributed fiber optics that perform resource management functions with the help of artificial intelligence. Sensing-assisted AI-based self-adaptive telecommunications infrastructure management 10 It is related to the system. State of the Art Today, telecommunications infrastructure monitoring systems combine network performance data with physical data. Environmental factors are generally evaluated independently. Fiber optics 15 Although distributed sensing systems can detect vibrations, temperature, or mechanical effects, they cannot process this data. network traffic, communication parameters such as latency or packet loss They are unable to correlate the causes of potential malfunctions at an early stage. It cannot be identified, and the ability to take preventive action remains limited. Furthermore, current solutions mostly generate alarms after the event has occurred, fault 20 By performing predictive analysis before a problem occurs, it automatically reassigns network resources. It cannot be configured. Physical security monitoring, network performance management, and resources. Using separate systems for optimization leads to additional hardware costs, high operating expenses. This leads to complexity and delayed decision-making processes. In addition... Traditional monitoring systems operating in a centralized structure provide real-time 25 in large-scale networks. It is not adequately meeting the responsiveness and local decision-making needs. In conclusion, due to the negative aspects described above and the current solutions being the subject of discussion... Due to its shortcomings, it has become necessary to make improvements in the relevant technical field. Purpose of the Invention 30 The invention was created by drawing inspiration from existing situations and overcoming the aforementioned drawbacks. It aims to solve the problem. The main purpose of the invention is to improve the performance of existing telecommunication infrastructures used for data transmission. enabling fiber optic cables to also be used as distributed sensing elements Distributed fiber optic 35 reduces the need for additional sensor infrastructure and lowers installation costs. 2 sensing-assisted AI-based self-adaptive telecommunications infrastructure management The goal is to provide the system. Another aim of the invention is to connect sensing data obtained from physical environmental events with networks. performance parameters are correlated together within an AI-based correlation mechanism. by evaluating, not only can malfunctions be detected, but they can also be predicted before they occur. 5 distributed fiber optic sensing-supported AI-based self-awareness that makes this possible The goal is to provide an adapted telecommunications infrastructure management system. Another purpose of the invention is to protect the cable from vibration, stress, temperature changes, and excavation activities. or the effects of physical events such as external interference on communication performance Artificial intelligence supported by distributed fiber optic sensing that enables real-time analysis. To provide an intelligent, self-adaptive telecommunications infrastructure management system; physical Security monitoring, network performance management, and traffic optimization all within a single integrated architecture. distributed fiber optic sensing-supported artificial intelligence-based self-assembly To provide an adaptable telecommunications infrastructure management system; AI-powered analysis. Thanks to its structure, it learns past event patterns and assigns risk scores for newly emerging situations. Computational distributed fiber optic sensing-assisted AI-based self-adaptive To provide a telecommunications infrastructure management system; network depending on risk level. distributed fiber optics that enable automatic reconfiguration of resources sensing-assisted AI-based self-adaptive telecommunications infrastructure management The system aims to provide; thanks to its variants supporting edge processing architecture, decision 20 enabling processes to be carried out at the local level without being dependent on a central server distributed fiber optic sensing-enabled AI-based self-adaptive telecommunications To provide an infrastructure management system; a federal learning-based model update approach. with collaborative learning for systems located in different regions without sharing data. 25 AI-based systems supported by distributed fiber optic sensing that enable it to be implemented The goal is to provide a self-adapting telecommunications infrastructure management system. The structural and characteristic features and all the advantages of the invention are given in the figures below. Thanks to the detailed explanation written with references to the figures, it becomes clearer. This will be understood, and therefore the evaluation should also take these figures and detailed explanations into account. It must be done by taking 30. Figures that will help understand the invention. Figure 1 shows the general architecture of the system that is the subject of the invention. Figure 2 shows the general architecture of the system that is the subject of the invention. 35 Explanation of Part References 3 1. Main control module 2. Distributed fiber sensing module 3. Artificial intelligence correlation engine 4. Network traffic analysis module 5. Adaptive resource allocation module 5 6. Event classification memory 7. Edge processing node 8. Alarm and security interface 9. Data synchronization layer 10. Federal learning module 10 Detailed Description of the Invention In this detailed explanation, the preferred configurations of the invention are not merely for better understanding the subject. This is intended to facilitate understanding and will not impose any limiting effects. The invention, Developed for use in telecommunications and fiber optic communication infrastructures, 15 Existing fiber optic cables are used for both data transmission and distributed environmental sensing. using physical security, fault prediction, network performance monitoring, and dynamic resource allocation. Distributed fiber optic sensing that performs management functions with the help of artificial intelligence. with a self-adaptive, AI-powered telecommunications infrastructure management system It is related. 20 The operating principle of the system described in the invention is as follows: Fiber optic cables are used during system operation. Environmental effects on the lines are first detected by the distributed fiber sensing module (2). It is detected. At the same time, network traffic data is collected by the network traffic analysis module (4). This data before being transmitted to the main control module (1) by the artificial intelligence correlation engine (3) The engine (3) compares past event records with the event classification memory (6) to determine risk 25 determines the risk level. If the risk level exceeds a certain threshold, the adaptive resource allocation module (5) It intervenes and changes the traffic routing. At the same time, the alarm and security interface (8) Notifications are sent to the operators via the Edge processing node (7), which is delay-sensitive. In these situations, it reduces dependence on the central system by making local decisions. Data synchronization. Layer (9) between edge processing nodes (7) and central system model, parameter and event 30 It ensures the synchronization of data and the federation learning module (10) in different regions The systems continuously update the model accuracy. The main control module (1) of the system in question provides central coordination of the entire system. Fiber sensing data, network performance metrics, and AI outputs are all provided in this module. They are combined; decision-making and system-level control are carried out here. 35 4 The distributed fiber sensing module (2) of the system in question receives feedback over fiber optic lines. It generates environmental physical event data by analyzing scattering (Rayleigh / Brillouin) signals. It detects phenomena such as vibration, temperature, and mechanical interference. The artificial intelligence correlation engine (3) of the system in question combines physical event data with network It establishes relationships between performance parameters. Deep learning and time series analysis 5 It uses event prediction and risk scoring. The network traffic analysis module (4) of the system in question measures packet delay, jitter, and bandwidth. It measures and reports network metrics such as usage and error rate in real time. The adaptive resource allocation module (5) of the system in question, routing on the network, bandwidth It dynamically changes the width and optical path selection. In case of malfunction or risk, traffic is reduced to 10. It is redirected. The event classification memory (6) of the system in question, past physical events and network It hides its behaviors. In the learning and comparison processes of the artificial intelligence engine (3) It is used as a reference dataset. The edge processing node (7) of the system in question processes local data without being dependent on the central system. It performs processing and rapid decision-making operations. It plays a critical role in low-latency applications. He plays. The system in question has an alarm and security interface (8), which detects critical physical events and cyber / physical incidents. It classifies threats and sends notifications to security systems and operators. The data synchronization layer (9) of the system in question consists of edge processing nodes (7) and 20 It enables the synchronization of model, parameter, and event data between the central system. It supports a federal learning infrastructure. The federative learning module (10) of the system in question is located in distributed locations. It enables processing nodes (7) to develop a common artificial intelligence model without sharing raw data.

Claims

REQUESTS 1. Developed for use in telecommunications and fiber optic communication infrastructures, Existing fiber optic cables are used for both data transmission and distributed environmental sensing. using physical security, fault prediction, network performance monitoring, and dynamic resource allocation. Distributed fiber optic sensing 5 that performs management functions with the support of artificial intelligence. AI-powered, self-adaptive telecommunications infrastructure management system Its characteristic is; • Provides centralized coordination of the entire system, including fiber sensing data and network performance. Combining metrics and AI outputs for decision-making and system-level control. main control module (1) which performs 10 • Environmental physical phenomena by analyzing backscattered signals over fiber optic lines distributed systems that generate data and detect events such as vibration, temperature, and mechanical interference. fiber detection module (2), • Deep learning that establishes relationships between physical event data and network performance parameters. and artificial intelligence that predicts events and scores risks using time series analysis 15 correlation engine (3), • Real-time network metrics such as packet latency, jitter, bandwidth usage, and error rate. Network traffic analysis module (4) which measures and reports in real time. • Dynamically changing routing, bandwidth, and optical path selection on the network, Adaptive resource 20 that redirects traffic in case of malfunction or risk. allocation module (5), • the AI ​​engine (3) which stores past physical events and network behaviors Events used as reference data sets in learning and comparison processes. classification memory (6), • Local data processing and rapid decision-making without relying on a central system. 25 edge processing node (7) that performs, • By classifying critical physical events and cyber / physical threats, we can integrate them into security systems and Alarm and security interface that sends notifications to operators (8), • Model, parameter and event between edge processing nodes (7) and the central system Data 30 that enables data synchronization and supports a federated learning infrastructure. synchronization layer (9), • Edge processing nodes (7) located in distributed locations without sharing raw data federative learning module that enables the development of a joint artificial intelligence model (10) It includes.

Images