EDGE AI system for automated fault tracking and resolution in network infrastructure

Abstract

An edge AI system for automated fault tracking and resolution in network infrastructures, consisting of: a large number of IoT sensors distributed across the network infrastructure and configured to continuously collect operational, environmental, and performance data; A data acquisition module is configured to retrieve the collected data from a variety of IoT sensors; a preprocessing module that is connected to the data acquisition module and is configured to filter, normalize, and convert the collected data into structured feature sets; an edge processing unit connected to the preprocessing module and configured to perform artificial intelligence inference processes locally and host trained machine learning models; an automated fault detection module within the edge processing unit, configured to analyze data streams using trained machine learning models to detect anomalies, wherein the automated fault detection module is further configured to classify faults related to overload, latency, packet loss, hardware degradation, environmental stress, or security incidents; a solution recommendation engine connected to the edge processing unit, configured to generate remediation recommendations upon detection of an error based on learned patterns, historical solutions, and predefined guidelines; an automated remediation module that is connected to the solution recommendation engine and configured to execute corrective actions autonomously without manual intervention; and a feedback and learning loop module connected to the automated remediation module and the edge computing unit, wherein the feedback and learning loop module is configured to receive the results after remediation and retrain the trained machine learning models for continuous performance optimization.

Description

AREA OF INVENTION

[0001] The present disclosure relates to an edge AI system for automated fault detection and correction in network infrastructures. More precisely, the invention relates to an edge AI system for automated fault detection, tracking, and correction using AI algorithms in conjunction with IoT devices. The invention lies at the intersection of edge computing, AI-based analytics, network monitoring, and automated system correction, thus enabling real-time decision-making and autonomous network maintenance. BACKGROUND OF THE INVENTION

[0002] Modern network infrastructures such as telecommunications networks, data centers, cloud platforms, and industrial IoT environments are becoming increasingly complex and heterogeneous. These systems generate vast amounts of real-time data and are susceptible to errors and failures such as latency spikes, packet loss, device overheating, signal degradation, configuration errors, and security vulnerabilities.

[0003] Traditional network management techniques largely rely on centralized, cloud-based monitoring and manual troubleshooting by network technicians. These approaches are reactive, suffer from high latency, increased downtime, and scalability limitations. Furthermore, centralized analysis can be impractical in environments requiring immediate response and continuous availability.

[0004] Although AI-based monitoring solutions exist, they often rely on cloud processing and have shortcomings in tight integration with IoT sensors at the network edge, as well as in automated troubleshooting mechanisms. Therefore, there is a clear need for an intelligent, edge-deployed system that proactively detects faults and resolves them autonomously with minimal human intervention.

[0005] The present invention provides an Edge Artificial Intelligence (Edge-AI) system for automated fault detection, tracking and correction using artificial intelligence algorithms in conjunction with Internet of Things (IoT) devices. SUMMARY OF THE INVENTION

[0006] The present disclosure relates to a robust, edge AI-based, automated fault tracking and resolution system that integrates artificial intelligence and IoT devices to enable proactive, real-time network management. By shifting intelligence to the network edge, the system minimizes latency, increases reliability, and reduces operational overhead. The invention is scalable, adaptive, and applicable in a variety of networked environments, including telecommunications, data centers, cloud infrastructures, industrial IoT, and smart cities.

[0007] This disclosure relates to an edge AI system for automated fault detection and correction in network infrastructures. The system comprises: multiple IoT sensors distributed throughout the network infrastructure that continuously collect operational, environmental, and performance data; a data acquisition module for retrieving the collected data from the IoT sensors; a preprocessing module connected to the data acquisition module for filtering, normalizing, and transforming the collected data into structured feature sets; and an edge processing unit connected to the preprocessing module for locally executing AI inference and hosting trained machine learning models.an automated fault detection module within the edge processing unit for analyzing data streams using trained machine learning models to detect anomalies and classify faults related to overload, latency, packet loss, hardware impairment, environmental load, or security incidents; a fault resolution recommendation engine connected to the edge processing unit that generates fault resolution recommendations based on learned patterns, historical solutions, and predefined guidelines as soon as a fault is detected; an automated correction module connected to the solution recommendation engine and configured to execute corrective actions autonomously without manual intervention;and a feedback and learning loop module connected to the automated correction module and the edge computing unit, wherein the feedback and learning loop module is configured to receive the results after correction and retrain the trained machine learning models for continuous performance optimization.

[0008] One objective of the present disclosure is to provide an edge AI system for automated fault tracking and correction in network infrastructures.

[0009] Another objective of the present disclosure is the integration of IoT sensors with AI algorithms for the continuous monitoring of network and environmental conditions.

[0010] Another objective of the present disclosure is to enable the automated classification and prioritization of errors using machine learning models.

[0011] Another objective of the present disclosure is to generate intelligent remedial recommendations based on historical data and best practices.

[0012] Another objective of the present disclosure is the implementation of autonomous corrective actions at the network edge without manual intervention.

[0013] Another objective of the present disclosure is the reduction of network downtime, latency, and operating costs.

[0014] However, another objective of the present disclosure is the continuous improvement of system performance through adaptive learning and feedback loops.

[0015] To further clarify the advantages and features of the present disclosure, the invention is described in more detail with reference to specific embodiments illustrated in the accompanying drawing. It is understood that this drawing merely shows typical embodiments of the invention and is therefore not to be understood as limiting its scope of protection. The invention is described and explained in more detail and with reference to the accompanying drawing. BRIEF DESCRIPTION OF THE IMAGE

[0016] These and other features, aspects and advantages of the present disclosure will be better understood when the following detailed description is read with reference to the accompanying drawing, in which the same symbols represent the same parts, wherein: Fig. Figure 1 shows a block diagram of an n-edge AI system for automated fault tracking and correction in the network infrastructure according to an embodiment of the present disclosure.

[0017] Furthermore, those skilled in the art will recognize that the elements in the drawing are simplified and not necessarily drawn to scale. For example, the flowcharts illustrate the process by highlighting the main steps to facilitate understanding of the present disclosure. With regard to the construction of the device, one or more components may be represented in the drawing by conventional symbols. The drawing may show only the specific details relevant to understanding the embodiments of the present disclosure, so as not to clutter the drawing with details that are already apparent to those skilled in the art from the description contained herein. DETAILED DESCRIPTION:

[0018] To facilitate understanding of the principles of the invention, reference is made below to the embodiment shown in the drawing, which is described using specific terms. It is understood, however, that this does not limit the scope of protection of the invention. Rather, modifications and further developments of the depicted system, as well as further applications of the inventive principles shown therein, are conceivable, insofar as they would normally occur to a person skilled in the art in the field of the invention.

[0019] It will be clear to those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not to be understood as a limitation thereof.

[0020] References to “an aspect”, “another aspect”, or similar phrases in this description mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, phrases such as “in one embodiment”, “in another embodiment”, and similar expressions in this description may, but do not necessarily, all refer to the same embodiment.

[0021] The terms "includes," "comprehensive," or similar expressions denote non-exclusive inclusion. Thus, a procedure or method containing a list of steps does not only include those steps but may also include further steps not explicitly listed or inherent in the procedure or method. Likewise, the statement "includes..." for one or more devices, subsystems, elements, structures, or components, without further limitations, does not preclude the existence of other devices, subsystems, elements, structures, or components.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meanings generally known to those skilled in the art in the field to which this invention belongs. The systems, methods, and examples described herein serve only for illustration and are not to be understood as limiting.

[0023] Embodiments of the present disclosure are described in detail below with reference to the attached drawing.

[0024] The functional units described in this specification are referred to as devices. A device may be implemented in programmable hardware such as processors, digital signal processors, central processing units, FPGAs, PALs, PLDs, cloud processing systems, or similar. Devices may also be implemented in software for execution by various processor types. An identified device may contain executable code and, for example, comprise one or more physical or logical blocks of computer instructions, which may be organized as an object, procedure, function, or other construct. However, the executable files of an identified device need not be physically related; they may consist of different instructions stored in different locations that, when logically combined, constitute the device and fulfill its purpose.

[0025] The executable code of a device or module can consist of a single instruction or multiple instructions and can even extend across different code sections, applications, and storage media. Similarly, operational data within the device can be identified and represented, and can exist in any suitable form and be organized in any data structure. The operational data can be captured as a single data record or distributed across various storage media and may exist, at least partially, as electronic signals within a system or network.

[0026] References to “a selected embodiment”, “an embodiment”, or “an embodiment” in this description mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the disclosed subject matter. Therefore, the phrases “a selected embodiment”, “in an embodiment”, or “in an embodiment” appearing at different points in this description do not necessarily refer to the same embodiment.

[0027] Furthermore, the described features, structures, or properties can be combined in one or more embodiments in any suitable manner. The following description contains numerous specific details to enable a comprehensive understanding of the embodiments of the disclosed subject matter. However, a person skilled in the art will recognize that the disclosed subject matter can also be realized without one or more of the specific details or with other methods, components, materials, etc. In other cases, known structures, materials, or processes are not presented or described in detail so as not to obscure aspects of the disclosed subject matter.

[0028] According to the exemplary embodiments, the disclosed computer programs or modules can be executed in a variety of ways, for example, as an application running in the memory of a device or as a hosted application running on a server and communicating with the device application or browser via various standard protocols such as TCP / IP, HTTP, XML, SOAP, REST, JSON, and other suitable protocols. The disclosed computer programs can be written in programming languages ​​that run either in the device's memory or on a hosted server, such as BASIC, COBOL, C, C++, Java, Pascal, or scripting languages ​​such as JavaScript, Python, Ruby, PHP, Perl, or other suitable programming languages.

[0029] Some of the described embodiments involve data transmission over a network, such as the transmission of various inputs or files. The network may include, for example, the internet, wide area networks (WANs), local area networks (LANs), analog or digital wired and wireless telephone networks (e.g., PSTN, ISDN, cellular networks, and xDSL), radio, television, cable, satellite, and / or other transmission or tunneling mechanisms for data. It may include multiple networks or subnetworks, each of which may, for example, have a wired or wireless data path. The network may include a circuit-switched voice network, a packet-switched data network, or another network for transmitting electronic data. For example, it may be based on the Internet Protocol (IP) or Asynchronous Transfer Mode (ATM) and support voice communication using VoIP, Voice over ATM, or similar protocols.In one embodiment, the network comprises a mobile network configured for the exchange of text or SMS messages.

[0030] Examples of networks include Personal Area Networks (PAN), Storage Area Networks (SAN), Home Area Networks (HAN), Campus Area Networks (CAN), Local Area Networks (LAN), Wide Area Networks (WAN), Metropolitan Area Networks (MAN), Virtual Private Networks (VPN), Enterprise Private Networks (EPN), the Internet, Global Area Networks (GAN), and so on.

[0031] Fig. Figure 1 shows a block diagram of an n-edge AI system for automated fault tracking and correction in the network infrastructure according to an embodiment of the present disclosure.

[0032] The Edge AI system (100) according to Fig.1 comprises: a multitude of IoT sensors (102) distributed across the network infrastructure that continuously collect operational, environmental, and performance data; a data acquisition module (104) that retrieves the collected data from the IoT sensors (102); a preprocessing module (106) connected to the data acquisition module (104) that filters, normalizes, and transforms the collected data into structured feature sets; an edge processing unit (108) connected to the preprocessing module (106) that performs AI inference locally and hosts trained machine learning models;An automated fault detection module (110) within the edge processing unit (108) that analyzes data streams using trained machine learning models to detect anomalies, wherein the automated fault detection module (110) classifies faults related to overload, latency, packet loss, hardware impairment, environmental load, or security incidents; a solution recommendation engine (112) connected to the edge processing unit (108) and configured to generate remediation recommendations upon fault detection based on learned patterns, historical solutions, and predefined guidelines; an automated remediation module (114) connected to the solution recommendation engine (112) and configured to autonomously execute corrective actions without manual intervention;and a feedback and learning loop module (116) connected to the automated remediation module (114) and the edge computing unit (108), wherein the feedback and learning loop module (116) is configured to receive the results after remediation and retrain the trained machine learning models for continuous performance optimization.

[0033] In one embodiment, the aforementioned plurality of IoT sensors (102) comprises temperature sensors, camera modules, network probes, and fiber optic photodetectors. The temperature sensors comprise at least one of the following components: thermocouples or thermistors configured to monitor environmental parameters, while the network probes are configured to monitor signal loss and packets in the network infrastructure.

[0034] In one embodiment, the trained machine learning models implemented by the edge processing unit (108) include support vector machines, decision trees and random forests configured for anomaly detection and fault classification.

[0035] In one embodiment, the automatic fault detection module (110) is further configured to: determine whether a detected anomaly corresponds to a previously known fault; link the detected anomaly to an existing fault record if the detected anomaly corresponds to a previously known fault; and create a new fault report if the detected anomaly does not correspond to a previously known fault.

[0036] In one embodiment, the system (100) further comprises: a central bug tracking system (110a) configured to receive bug information from the automated bug detection module (110) and configured to assign the bug to a development team and generate analytical insights for reporting dashboards.

[0037] In one embodiment, the automatic fault detection module (110) is configured to analyze at least one of the following types of data in real time: network performance data, environmental parameters, and device logs.

[0038] In one embodiment, the corrective actions performed by the automated remediation module (114) include: device reset, adjustment of network parameters, software updates, configuration updates, and isolation of faulty components. The system is further configured to monitor performance after a patch is deployed to verify the remediation and to close the fault report once the remediation is confirmed.

[0039] In one embodiment, the multitude of IoT sensors (102), the edge processing unit (108), the data acquisition module (104), the preprocessing module (106), the automatic fault detection module (110), the central fault tracking system (110a), the solution recommendation engine (112), the automatic fault correction module (114), and the feedback and learning loop module (116) can be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field-programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like.

[0040] The present invention relates to an edge AI system for automated fault detection and resolution in network infrastructures. The system integrates AI-powered analytics with IoT sensors at the network edge to enable real-time monitoring, detection, classification, and autonomous resolution of faults and operational anomalies. The system includes IoT sensors such as temperature sensors, camera modules, network probes, and fiber optic photodetectors that continuously collect operational and environmental data. An edge processing unit locally executes machine learning models to analyze data streams and detect anomalies related to congestion, latency, packet loss, hardware degradation, environmental stress, or security incidents. Upon fault detection, the system generates recommendations for troubleshooting and autonomously performs corrective actions such as device resets, network parameter adjustments, software updates, or component isolation.A feedback loop enables continuous learning and refinement of the model, thereby improving system performance over time. By performing AI inference at the network edge, the invention significantly reduces latency, minimizes reliance on centralized cloud systems, and enables proactive network maintenance without manual intervention.

[0041] The present invention discloses an edge AI system for automated fault tracking and correction, consisting of a distributed architecture deployed near network devices and infrastructure components.

[0042] In one embodiment, the system comprises several key components. The first component is an edge AI processing unit, an edge computing unit capable of performing AI inference locally. This unit hosts trained machine learning models, including support vector machines, decision trees, and random forests, for real-time analysis of incoming data. The second component is an IoT sensor network consisting of a variety of IoT devices distributed across the network infrastructure. These IoT devices include temperature sensors such as thermocouples and thermistors, camera modules, network probes for monitoring signal loss and packet loss, and fiber optic photodetectors. These sensors continuously collect operational, environmental, and performance data.The third component is a data acquisition and preprocessing module where the collected sensor and log data are filtered, normalized, and transformed into structured feature sets suitable for AI-based analysis at the edge. The fourth component is an automated fault detection module where AI models analyze data streams to identify anomalies and classify faults related to congestion, latency, packet loss, hardware degradation, environmental stress, or security incidents. The fifth component is a solution recommendation engine. Once a fault is detected, the system generates remediation recommendations based on learned patterns, historical solutions, and predefined guidelines. The sixth component is an automated remediation module.Where permissible, the system independently performs corrective actions such as device resets, adjustments to network parameters, software or configuration updates, and the isolation of faulty components. The seventh component is a feedback and learning loop. The results of the troubleshooting are fed back into the system to retrain and refine AI models. This enables continuous learning and performance optimization.

[0043] During implementation, the system begins by collecting data at the network edge, where operational and performance data are gathered and processed. In an anomaly detection phase, the data is analyzed to identify potential problems. If an anomaly is detected, the system checks whether it is a known bug. If so, it is linked to an existing bug report; otherwise, a new bug report is created. The bug information is then transmitted to a central bug tracking system, which assigns the bug to a development team and simultaneously generates analytical insights for reporting dashboards. The development team investigates the bug, implements a code fix, and tests it. If the test fails, the process is repeated for further investigation. If the test is successful, the patch is deployed to the edge AI system.The system then monitors performance to verify that the problem has been resolved. Once the problem is confirmed to be resolved, the error report is closed and the process is completed.

[0044] The present invention describes an edge AI system for automated fault detection and resolution in network infrastructures. The system integrates IoT sensors, an edge processing unit, and AI-based analytics to detect and resolve network faults in real time. This architecture enables intelligent monitoring and autonomous problem solving directly at the network edge.

[0045] The system uses advanced machine learning models to analyze network data and identify anomalies. Specifically, it employs support vector machines, decision trees, and random forests for precise anomaly detection and fault classification. These AI models process incoming data streams to identify patterns that indicate various types of network problems and operational disruptions.

[0046] A key feature of the system is its ability to perform automated corrective actions directly at the network edge, without requiring manual intervention. Once a fault or anomaly is detected and classified, the system independently initiates corrective actions to resolve the issue. This autonomous operation significantly reduces response time and eliminates the need for manual diagnosis and troubleshooting of network problems by human operators.

[0047] The IoT devices deployed throughout the network continuously monitor various environmental and operational parameters. They capture key metrics such as temperature fluctuations, signal loss, and the overall device health. This comprehensive monitoring capability ensures that the system always has insight into various aspects of network performance and environmental conditions that could affect system reliability.

[0048] Furthermore, the system features a feedback mechanism that enables continuous learning and improvement of the AI ​​models. Troubleshooting results and system performance data are fed back into the machine learning models, allowing them to refine their detection accuracy and improve their remediation strategies over time. This adaptive learning capability ensures that the system becomes increasingly effective at detecting and resolving network problems as it gains operational experience.

[0049] The present invention is scalable, adaptable and applicable to a wide range of networked environments, including telecommunications, data centers, cloud infrastructures, industrial IoT and smart cities.

[0050] The drawing and the preceding description illustrate embodiments. Those skilled in the art will recognize that one or more of the described elements can be combined to form a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment can be added to another. For example, the process flows described here can be modified and are not limited to the manner described herein. Furthermore, the actions of a flowchart need not be performed in the sequence shown; nor do all actions necessarily need to be carried out. Actions that do not depend on other actions can be performed in parallel with the other actions. The scope of protection of the embodiments is in no way limited by these specific examples. Numerous variations, whether explicitly stated in the description or not, such as...Differences in structure, dimensions, and materials are possible. The scope of protection of the embodiments is at least as comprehensive as described by the following claims.

[0051] The advantages, other benefits, and problem solutions have been described above with reference to specific embodiments. However, the advantages, benefits, problem solutions, and any components that can effect or enhance an advantage, benefit, or solution are not to be construed as critical, necessary, or essential features or components of the claims. REFERENCES 100 An Edge AI System for Automated Fault Tracking and Resolution in the Network Infrastructure. 102 Variety of Sensors for the Internet of Things 104 Data Acquisition Module 106 Preprocessing module 108 Edge processing units 110 Automated fault detection module 110a Centralized Fault Tracking System 112 - Resolution Recommendation Engine 114 Automated Remediation Module 116 Feedback and Learning Loop Module

Claims

An edge AI system for automated fault tracking and resolution in network infrastructures, consisting of: a variety of IoT sensors distributed across the network infrastructure and configured to continuously collect operational, environmental, and performance data; a data acquisition module configured to retrieve the collected data from a variety of IoT sensors; a preprocessing module connected to the data acquisition module and configured to filter, normalize, and transform the collected data into structured feature sets; an edge processing unit connected to the preprocessing module and configured to locally execute artificial intelligence inference processes and host trained machine learning models;an automated fault detection module within the edge processing unit, configured to analyze data streams using trained machine learning models to detect anomalies, the automated fault detection module further configured to classify faults related to congestion, latency, packet loss, hardware degradation, environmental stress, or security incidents; a solution recommendation engine connected to the edge processing unit, configured to generate remediation recommendations upon fault detection based on learned patterns, historical solutions, and predefined policies; an automated remediation module connected to the solution recommendation engine and configured to execute corrective actions autonomously without manual intervention;and a feedback and learning loop module connected to the automated remediation module and the edge computing unit, wherein the feedback and learning loop module is configured to receive the results after remediation and retrain the trained machine learning models for continuous performance optimization. Edge AI system according to claim 1, wherein the plurality of IoT sensors includes temperature sensors, camera modules, network probes and fiber optic photodetectors. Edge AI system according to claim 2, wherein the temperature sensors comprise at least thermocouples or thermistors for monitoring environmental parameters and network probes are configured to monitor signal loss and packets throughout the network infrastructure. Edge AI system according to claim 1, wherein the trained machine learning models implemented by the edge processing unit comprise support vector machines, decision trees and random forests configured for anomaly detection and fault classification. Edge AI system according to claim 1, wherein the automatic fault detection module is further configured to: determine whether a detected anomaly corresponds to a previously known fault; link the detected anomaly to an existing fault record if the detected anomaly corresponds to a previously known fault; and create a new fault report if the detected anomaly does not correspond to a previously known fault. The edge AI system according to claim 5 further comprises: a central bug tracking system configured to receive bug information from the automated bug detection module, and wherein the central bug tracking system is configured to assign the bug to a development team and generate analytical insights for reporting dashboards. Edge AI system according to claim 5, wherein the automatic fault detection module is configured to analyze at least one of the following types of data in real time: network performance data, environmental parameters and device logs. Edge AI system according to claim 1, wherein the corrective actions performed by the automated remediation module include: device reset; adjustment of network parameters; software updates; configuration updates; and isolation of faulty components. Edge AI system according to claim 8, wherein the system is further configured to monitor performance after the deployment of a patch to verify the resolution of the error and close the error report once it has been confirmed that the error has been resolved.

Images