Automatic operation and maintenance method and system based on AI algorithm

Abstract

The invention relates to an automatic operation and maintenance method and system based on an AI algorithm, and the method comprises the steps: carrying out the training based on preset rules and programs and a database through employing a deep learning algorithm, and obtaining a trained AI algorithm model for path planning and optimization, traffic prediction and load balancing, and intelligent decision support; a distributed architecture is constructed based on an AI algorithm model, and a plurality of computing nodes are formed and used for processing computing tasks in parallel; receiving an operation and maintenance service demand, and dynamically distributing and scheduling computing nodes to process the operation and maintenance service demand according to the operation and maintenance service demand and the load condition of the distributed architecture to obtain an optimal operation and maintenance strategy and solution; and in the calculation processing process of the operation and maintenance service requirements, automatically discovering and positioning faults by adopting a fault detection algorithm based on machine learning, and executing fault measures. Compared with the prior art, the method has the advantages that the operation and maintenance efficiency is improved, the flexibility and adaptability are enhanced, and comprehensiveness and systematicness are achieved.

Description

Technical Field

[0001] The present invention relates to the field of automated operation and maintenance technology, and in particular to an automated operation and maintenance method and system based on an AI algorithm. Background Art

[0002] With the development of emerging technologies such as cloud computing, big data, and the Internet of Things, the scale and complexity of data centers are increasing, and traditional manual operation and maintenance methods can no longer meet the needs of modern data centers. Therefore, automated operation and maintenance technology has emerged, which uses automation to achieve efficient management and maintenance of large-scale and complex systems. At the same time, artificial intelligence algorithms have also been widely used in various fields. Among them, path planning, traffic prediction, load balancing, fault detection, and intelligent decision support are important applications of artificial intelligence algorithms in the field of automated operation and maintenance.

[0003] Existing automated operation and maintenance technologies mainly use script automation, process automation, etc., to automatically perform some repetitive operations through preset rules and procedures, such as system deployment, configuration changes, fault handling, etc. In addition, artificial intelligence algorithms are also applied to the field of automated operation and maintenance, for example, traffic prediction through machine learning algorithms, fault detection and self-healing through deep learning algorithms, and path planning and optimization through reinforcement learning algorithms.

[0004] Although existing automated operation and maintenance technologies and artificial intelligence algorithms have improved operation and maintenance efficiency to a certain extent, there are still some problems and challenges. First, most of the existing automated operation and maintenance technologies rely on preset rules and procedures, lack flexibility and adaptability, and cannot cope with complex operation and maintenance scenarios. Secondly, the application of existing artificial intelligence algorithms in the field of automated operation and maintenance is mainly concentrated in a single functional module, such as traffic prediction, fault detection, etc., which lacks comprehensiveness and systematicness and cannot achieve true intelligent operation and maintenance. Finally, when processing large-scale, high-concurrency data, existing automated operation and maintenance technologies and artificial intelligence algorithms may encounter performance bottlenecks and scalability issues. Summary of the invention

[0005] The purpose of the present invention is to provide an automated operation and maintenance method and system based on AI algorithm in order to overcome the defects of the above-mentioned prior art in that the automated operation and maintenance technology lacks flexibility and adaptability and is concentrated on a single functional module.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] An automated operation and maintenance method based on an AI algorithm comprises the following steps:

[0008] Use deep learning algorithms to train based on preset rules, programs and databases to obtain trained AI algorithm models for path planning and optimization, traffic prediction and load balancing, and intelligent decision support;

[0009] Building a distributed architecture based on the AI ​​algorithm model to form multiple computing nodes for parallel processing of computing tasks;

[0010] Receive operation and maintenance business requirements, dynamically allocate and schedule computing nodes to process operation and maintenance business requirements based on the operation and maintenance business requirements and the load of the distributed architecture, and obtain the optimal operation and maintenance strategy and solution;

[0011] In the process of calculating and processing operation and maintenance business needs, a machine learning-based fault detection algorithm is used to automatically discover and locate faults, and execute corresponding fault measures.

[0012] Furthermore, the distributed architecture uses Hadoop as a distributed file system and Spark as a distributed computing engine to achieve parallel processing through multiple computing nodes.

[0013] Furthermore, the method adopts Kubernetes as a container management platform to dynamically allocate and schedule computing nodes.

[0014] Furthermore, the deep learning algorithm provides optimal operation and maintenance strategies and solutions by analyzing and learning historical data.

[0015] Furthermore, the method trains and optimizes the fault detection algorithm through a pre-established fault library.

[0016] The present invention also provides an automated operation and maintenance system based on an AI algorithm, comprising:

[0017] The access layer is used to provide a data interface to receive operation and maintenance business requirements;

[0018] The platform layer is used to provide a distributed architecture to form multiple computing nodes for parallel processing of computing tasks;

[0019] The application layer is used to pre-train with deep learning algorithms based on preset rules, programs and databases to obtain trained AI algorithm models for path planning and optimization, traffic prediction and load balancing, fault detection and self-healing, and intelligent decision support; and dynamically allocate and schedule computing nodes to process operation and maintenance business needs according to operation and maintenance business needs and the load of the distributed architecture to obtain the optimal operation and maintenance strategy and solution; in the process of calculating and processing operation and maintenance business needs, a machine learning-based fault detection algorithm is used to automatically discover and locate faults, and execute corresponding fault measures;

[0020] The support layer is used to provide various fault libraries for the fault detection algorithm to be trained and optimized.

[0021] Furthermore, the distributed architecture uses Hadoop as a distributed file system and Spark as a distributed computing engine to achieve parallel processing through multiple computing nodes.

[0022] Furthermore, the application layer uses Kubernetes as a container management platform to dynamically allocate and schedule computing nodes.

[0023] Furthermore, the deep learning algorithm provides optimal operation and maintenance strategies and solutions by analyzing and learning historical data.

[0024] Furthermore, the fault library provided by the support layer includes a Linux fault library, an nginx fault library, a K8S fault library and a MySQL fault library.

[0025] Compared with the prior art, the present invention has the following advantages:

[0026] (1) Improve operation and maintenance efficiency: The automated operation and maintenance technology based on AI algorithm can automatically perform a series of operation and maintenance operations, such as system deployment, configuration changes, fault handling, etc., which greatly improves operation and maintenance efficiency and reduces labor costs.

[0027] (2) Enhanced flexibility and adaptability: The present invention not only relies on preset rules and procedures, but also can realize functions such as path planning, traffic prediction, load balancing, fault detection and intelligent decision support through AI algorithms. It has higher flexibility and adaptability and can cope with complex operation and maintenance scenarios.

[0028] (3) Comprehensiveness and systematicity: The present invention applies artificial intelligence algorithms to multiple aspects of automated operation and maintenance, such as path planning, traffic prediction, load balancing, fault detection, and intelligent decision support, achieving comprehensiveness and systematicity and enabling true intelligent operation and maintenance.

[0029] (4) Improve performance and scalability: The present invention realizes automated operation and maintenance through AI algorithms, which can process large-scale, high-concurrency data, avoiding the performance bottlenecks and scalability problems that may occur in traditional automated operation and maintenance technologies when processing large-scale, high-concurrency data. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flowchart of an automated operation and maintenance method based on an AI algorithm provided in an embodiment of the present invention;

[0031] Figure 2A schematic diagram of a framework of an automated operation and maintenance system based on an AI algorithm provided in an embodiment of the present invention;

[0032] Figure 3 A schematic diagram of the processing process of an AI algorithm model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0034] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0036] Example 1

[0037] like Figure 1 As shown, this embodiment provides an automated operation and maintenance method based on an AI algorithm, comprising the following steps:

[0038] S1: Use deep learning algorithms to train based on preset rules, programs and databases to obtain trained AI algorithm models for path planning and optimization, traffic prediction and load balancing, fault detection and self-healing, and intelligent decision support;

[0039] S2: Build a distributed architecture based on the AI ​​algorithm model to form multiple computing nodes for parallel processing of computing tasks;

[0040] S3: Receives operation and maintenance business requirements, and dynamically allocates and schedules computing nodes to process the operation and maintenance business requirements based on the operation and maintenance business requirements and the load of the distributed architecture, to obtain the optimal operation and maintenance strategy and solution;

[0041] S4: In the process of calculating and processing operation and maintenance business needs, a machine learning-based fault detection algorithm is used to automatically discover and locate faults, and execute corresponding fault measures.

[0042] Specifically, in step S1, by using advanced artificial intelligence algorithms, complex operation and maintenance scenarios are automatically identified and processed to improve the flexibility and adaptability of automated operation and maintenance technology. At the same time, the platform can also realize functions such as path planning and optimization, traffic prediction and load balancing, fault detection and self-healing, and intelligent decision support, realizing truly intelligent operation and maintenance.

[0043] Specifically, Python is used to develop an automated operation and maintenance platform based on AI algorithms, and the TensorFlow framework is used to train and deploy deep learning models. The main functions of the platform include path planning and optimization, traffic prediction and load balancing, fault detection and self-healing, and intelligent decision support.

[0044] In step S2, distributed architecture design: In order to cope with large-scale, high-concurrency data processing needs, Hadoop is used as the distributed file system and Spark is used as the distributed computing engine to achieve parallel processing through multiple computing nodes.

[0045] In this way, large-scale, high-concurrency data processing requirements can be met, and the system's processing capacity and scalability can be improved. At the same time, the distributed architecture can also achieve load balancing, avoid single point failures, and improve system reliability.

[0046] In step S3, Kubernetes is used as the container management platform. Through the automatic scaling function of Kubernetes, computing resources are dynamically allocated and scheduled according to business needs and system load conditions, thereby improving resource utilization and reducing resource waste.

[0047] In step S4, an intelligent fault detection and self-healing mechanism is used to automatically discover and locate faults by real-time monitoring of the system operation status, and to take corresponding repair measures to improve the stability and reliability of the system.

[0048] In this embodiment, a fault detection algorithm based on machine learning is adopted to automatically discover and locate faults by monitoring the system operation status in real time, and take corresponding repair measures.

[0049] The fault detection algorithm is pre-trained and optimized using an established fault library.

[0050] In summary, this solution adopts intelligent decision support technology to provide the best operation and maintenance strategies and solutions through analysis and learning of historical data, thereby improving operation and maintenance efficiency and quality.

[0051] The above are the specific implementation steps of this embodiment. Through these steps, we can implement an automated operation and maintenance technology based on AI algorithm to improve operation and maintenance efficiency and quality.

[0052] The above is an introduction to the method embodiment. The following is a further explanation of the solution of the present invention through a system embodiment.

[0053] like Figure 2 As shown, this embodiment also relates to an automated operation and maintenance system based on an AI algorithm, including:

[0054] The access layer is used to provide a data interface to receive operation and maintenance business requirements;

[0055] The platform layer is used to provide a distributed architecture to form multiple computing nodes for parallel processing of computing tasks;

[0056] The application layer is used to pre-train with deep learning algorithms based on preset rules, programs and databases to obtain trained AI algorithm models for path planning and optimization, traffic prediction and load balancing, fault detection and self-healing, and intelligent decision support; and dynamically allocate and schedule computing nodes to process operation and maintenance business needs according to operation and maintenance business needs and the load of the distributed architecture to obtain the optimal operation and maintenance strategy and solution; in the process of calculating and processing operation and maintenance business needs, a machine learning-based fault detection algorithm is used to automatically discover and locate faults, and execute corresponding fault measures;

[0057] The support layer is used to provide various fault libraries for training and optimization of fault detection algorithms.

[0058] Optionally, the access layer can provide data interfaces through WebSocket, HTTP / HTTPS, and Nginx.

[0059] The platform layer can provide K8S platform, use Hadoop as distributed file system, and use Spark as distributed computing engine.

[0060] The application layer can be divided into statistical display module, application service module and automated operation and maintenance service module;

[0061] The statistical display module is used to display results, record data, and report statistics;

[0062] The application service module is used to provide fault library management, visual monitoring platform, API interface, operation and maintenance center, machine management, data statistics and analysis, authority management, cluster library management, and log and report modules;

[0063] The automated operation and maintenance service module is used to provide functions such as concurrent execution, one-click start and stop, and status management.

[0064] The fault libraries provided by the support layer include Linux fault library, nginx fault library, K8S fault library and MySQL fault library.

[0065] like Figure 3 As shown in the figure, users can transmit operation and maintenance business requirements to the access layer through the API gateway. The automated operation and maintenance system based on AI algorithm can realize task scheduling, task issuance, monitoring and alarm, fault self-healing and provide a fault library through AI functions.

[0066] It should be noted that the specific content and beneficial effects of the system of the present application can be found in the above-mentioned method embodiment, which will not be repeated here.

[0067] This solution can be widely used in application fields such as cloud computing, big data, and the Internet of Things. With the development of these emerging technologies, the scale and complexity of data centers are increasing, and traditional manual operation and maintenance methods can no longer meet the needs of modern data centers. Therefore, automated operation and maintenance technology has emerged, which uses automation to achieve efficient management and maintenance of large-scale and complex systems. At the same time, artificial intelligence algorithms have also been widely used in various fields. Among them, path planning, traffic prediction, load balancing, fault detection, and intelligent decision support are important applications of artificial intelligence algorithms in the field of automated operation and maintenance. The automated operation and maintenance technology based on AI algorithms of the present invention can improve operation and maintenance efficiency, enhance the flexibility and adaptability of the system, and realize truly intelligent operation and maintenance. It has broad market demand and good application prospects.

[0068] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. An automated operation and maintenance method based on AI algorithm, characterized in that: The following steps are involved: Use deep learning algorithms to train based on preset rules, programs and databases to obtain trained AI algorithm models for path planning and optimization, traffic prediction and load balancing, and intelligent decision support; Building a distributed architecture based on the AI ​​algorithm model to form multiple computing nodes for parallel processing of computing tasks; Receive operation and maintenance business requirements, dynamically allocate and schedule computing nodes to process operation and maintenance business requirements based on the operation and maintenance business requirements and the load of the distributed architecture, and obtain the optimal operation and maintenance strategy and solution; In the process of calculating and processing operation and maintenance business needs, a machine learning-based fault detection algorithm is used to automatically discover and locate faults, and execute corresponding fault measures.

2. The automated operation and maintenance method based on AI algorithm according to claim 1, characterized in that: The distributed architecture uses Hadoop as a distributed file system and Spark as a distributed computing engine to achieve parallel processing through multiple computing nodes.

3. The automated operation and maintenance method based on AI algorithm according to claim 1, characterized in that: The method adopts Kubernetes as a container management platform to dynamically allocate and schedule computing nodes.

4. The automated operation and maintenance method based on AI algorithm according to claim 1, characterized in that: The deep learning algorithm provides the best operation and maintenance strategies and solutions by analyzing and learning historical data.

5. The automated operation and maintenance method based on AI algorithm according to claim 1, characterized in that: The method trains and optimizes the fault detection algorithm through a pre-established fault library.

6. An automated operation and maintenance system based on AI algorithm, characterized in that: include: The access layer is used to provide a data interface to receive operation and maintenance business requirements; The platform layer is used to provide a distributed architecture to form multiple computing nodes for parallel processing of computing tasks; The application layer is used to pre-train with deep learning algorithms based on preset rules, programs and databases to obtain trained AI algorithm models for path planning and optimization, traffic prediction and load balancing, fault detection and self-healing, and intelligent decision support; and dynamically allocate and schedule computing nodes to process operation and maintenance business needs according to operation and maintenance business needs and the load of the distributed architecture to obtain the optimal operation and maintenance strategy and solution; in the process of calculating and processing operation and maintenance business needs, a machine learning-based fault detection algorithm is used to automatically discover and locate faults, and execute corresponding fault measures; The support layer is used to provide various fault libraries for the fault detection algorithm to be trained and optimized.

7. The automated operation and maintenance system based on AI algorithm according to claim 6, characterized in that: The distributed architecture uses Hadoop as a distributed file system and Spark as a distributed computing engine to achieve parallel processing through multiple computing nodes.

8. The automated operation and maintenance system based on AI algorithm according to claim 6, characterized in that: The application layer uses Kubernetes as a container management platform to dynamically allocate and schedule computing nodes.

9. The automated operation and maintenance system based on AI algorithm according to claim 6, characterized in that: The deep learning algorithm provides the best operation and maintenance strategies and solutions by analyzing and learning historical data.

10. The automated operation and maintenance system based on AI algorithm according to claim 6, characterized in that: The fault libraries provided by the support layer include Linux fault library, nginx fault library, K8S fault library and MySQL fault library.

Images