Automatic and intelligent management method and system of cloud computing network
An intelligent management system for cloud computing networks addresses scale, security, and regulatory challenges by employing adaptive configuration, AI defense, and self-healing mechanisms, enhancing efficiency and reliability.
Patent Information
- Application Number
- CN202411240084.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Cloud computing networks face challenges in network scale and complexity, security threats, resource optimization, automation level, compliance with regulations, business continuity, isolation and sharing in multi-tenant environments, and cloud-edge collaboration, necessitating intelligent and adaptive management solutions.
An automated and intelligent management system utilizing adaptive network configuration, AI-based security defense, intelligent fault diagnosis and self-healing, and system testing to dynamically adjust resources, defend against threats, and optimize configurations and recovery strategies.
The system enhances network management efficiency, improves security, optimizes resource utilization, reduces manual intervention, and ensures business continuity by adapting to dynamic changes and threats, thereby improving the reliability and stability of cloud computing networks.
Smart Images

Figure CN119094372A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of cloud computing network automation technology, and in particular to an automation and intelligent management method and system for a cloud computing network. Background Art
[0002] As a revolutionary technology in the field of information technology, cloud computing has profoundly changed the operation mode of enterprises and the way of building IT infrastructure. With the popularization of cloud computing services, enterprises have a growing demand for cloud computing networks, which also brings a series of new challenges and problems. Cloud computing environments usually need to support thousands of virtual machines and containers. The rapid deployment, migration and destruction of these virtual entities leads to the rapid expansion of network scale, and the network topology and configuration become extremely complex. Traditional manual configuration and management methods can no longer adapt to this scale and complexity, and automated network management tools are urgently needed to improve efficiency.
[0003] Network security in cloud environments faces new challenges. Virtualization technology expands the attack surface, and traditional physical security boundaries are no longer applicable. At the same time, the multi-tenant nature of cloud services also brings data leakage and isolation issues. In addition, security threats such as DDoS attacks and malware propagation in cloud environments are becoming increasingly serious. Therefore, intelligent network security solutions are needed to monitor and defend against these threats in real time. Resources in cloud computing environments are dynamically allocated, and virtual machines and containers can be quickly expanded or reduced according to business needs. This requires the network to be able to flexibly adjust resources to adapt to different performance requirements such as bandwidth and latency. Traditional static network configurations can no longer meet this dynamic nature, and intelligent resource optimization and scheduling mechanisms are required.
[0004] Although cloud computing service providers provide a certain degree of automated management tools, there is still much room for improvement in the level of automation at the network level. For example, in scenarios such as virtual machine deployment, migration, and fault recovery, the degree of automation of network configuration is not high enough. In addition, automatic diagnosis and recovery of network faults is also an issue that needs to be addressed. With the continuous development of cloud computing technology, the concept of cloud native has emerged. Cloud native emphasizes building highly scalable and maintainable systems based on technologies such as containers, microservices, and continuous integration / continuous deployment (CI / CD). In the field of cloud computing networks, cloud native technology architecture is also needed to adapt to rapidly changing business needs.
[0005] With the increasing perfection of data security and privacy protection regulations, how to build and manage cloud computing networks under the premise of complying with relevant laws and regulations has become an issue that cannot be ignored. Technical solutions need to achieve efficient use and secure management of data on the basis of meeting regulatory requirements. The stability of cloud computing networks is directly related to the availability of cloud services and business continuity. In the face of risks such as network failures and security attacks, how to quickly restore services and ensure business continuity is an important consideration. This requires intelligent fault diagnosis and recovery mechanisms, as well as perfect backup and disaster recovery strategies. The multi-tenant nature of cloud computing environments brings about the issue of isolation and sharing. On the one hand, the networks between different tenants need to be effectively isolated to ensure data security and performance; on the other hand, tenants also need a certain degree of resource sharing to improve resource utilization. This requires the network to find a balance between isolation and sharing.
[0006] With the development of the Internet of Things (IoT) and edge computing, cloud-edge collaboration has become a new trend. Cloud computing networks need to work closely with edge networks to achieve rapid data processing and analysis. This requires the network to be able to achieve efficient data transmission and collaborative computing between the cloud and the edge. Artificial intelligence (AI) technology is increasingly being used in the field of cloud computing networks. Through machine learning and deep learning algorithms, intelligent analysis of network traffic can be achieved to optimize network configuration, predict network failures, and defend against security threats. The integration of AI technology will greatly enhance the intelligence level of cloud computing networks.
[0007] In summary, the automation and intelligent management of cloud computing networks faces multiple challenges, including network scale and complexity, security challenges, resource optimization requirements, automation level improvement, technical architecture evolution, regulations and standards constraints, business continuity requirements, isolation and sharing in a multi-tenant environment, cloud-edge collaboration requirements, and artificial intelligence technology integration. Through technological innovation, an adaptive, secure, efficient, and intelligent cloud computing network management system can be built to meet these challenges and promote the further development of cloud computing technology. Summary of the invention
[0008] The purpose of the present invention is to provide an automated and intelligent management method and system for a cloud computing network to solve the problems raised in the above background technology.
[0009] To achieve the above object, the present invention provides the following technical solution: an automated and intelligent management method for a cloud computing network, the method comprising the following steps:
[0010] Adaptive network configuration;
[0011] Security threat identification and defense;
[0012] Intelligent fault diagnosis and self-healing;
[0013] System testing and performance evaluation.
[0014] Preferably, the specific operations of the adaptive network configuration include:
[0015] Real-time monitoring of network traffic, virtual machine status, and business load data;
[0016] Use machine learning algorithms to predict future network traffic changes;
[0017] Dynamically adjust network resource allocation based on traffic prediction results;
[0018] Automatically send configuration commands to network devices;
[0019] Continuously optimize configuration strategies through feedback loops.
[0020] Preferably, the specific operations of security threat identification and defense include:
[0021] Real-time network traffic analysis to identify abnormal traffic patterns;
[0022] Automatically generate security policies and automatically deploy defense measures based on identified threats;
[0023] Security situation awareness and visualization, monitoring and displaying network security status;
[0024] Threat intelligence integration and sharing to improve threat identification capabilities;
[0025] Security policy adaptive optimization automatically adjusts security policy based on the latest threat intelligence.
[0026] Preferably, the specific operations of intelligent fault diagnosis and self-healing include:
[0027] Use fault detection and location algorithms to quickly identify the source of network faults;
[0028] Fault cause analysis to determine the root cause of the fault;
[0029] Self-healing strategy generation and execution, automatically generating and executing recovery operations based on the cause of the failure;
[0030] Self-healing effect verification and feedback, evaluate the effect of self-healing operations and optimize self-healing strategies;
[0031] Self-healing knowledge base accumulates fault handling experience and assists in the generation of self-healing strategies.
[0032] Preferably, the specific operations of system testing and performance evaluation include:
[0033] A unified user interface for managing network configuration, security defense, and fault recovery;
[0034] Lay out application programming interfaces to support integration of automation tools and third-party services;
[0035] Containerized deployment support ensures that the system can run on multiple cloud platforms.
[0036] An automated and intelligent management system for a cloud computing network, the system comprising:
[0037] Adaptive network configuration system to improve network management efficiency;
[0038] Security threat identification and defense system to enhance network security;
[0039] Intelligent fault diagnosis and self-healing network to optimize resource allocation;
[0040] System testing and performance evaluation framework to improve system adaptability and self-healing capabilities.
[0041] Preferably, the adaptive network configuration system monitors network traffic, virtual machine status and business load data in real time; uses machine learning algorithms to predict future network traffic changes; dynamically adjusts network resource allocation based on traffic prediction results; automatically sends configuration commands to network devices; and continuously optimizes configuration strategies through feedback loops.
[0042] Preferably, the security threat identification and defense system includes:
[0043] Real-time network traffic analysis module to identify abnormal traffic patterns;
[0044] A security policy automatic generation module for automatically deploying defense measures based on identified threats;
[0045] Security situation awareness and visualization tools to monitor and display network security status;
[0046] Threat intelligence integration and sharing mechanism to improve threat identification capabilities;
[0047] Security policy adaptive optimization algorithm is used to automatically adjust security policies based on the latest threat intelligence.
[0048] Preferably, the intelligent fault diagnosis and self-healing network includes:
[0049] Fault detection and location algorithms to quickly identify the source of network faults;
[0050] Failure cause analysis model to determine the root cause of failure;
[0051] Self-healing strategy generation and execution system, used to automatically generate and execute recovery operations based on the cause of the failure;
[0052] Self-healing effect verification and feedback mechanism, used to evaluate the effect of self-healing operations and optimize self-healing strategies;
[0053] The self-healing knowledge base is used to accumulate fault handling experience and assist in the generation of self-healing strategies.
[0054] Preferably, the system testing and performance evaluation framework includes:
[0055] A unified user interface for managing network configuration, security defense, and fault recovery;
[0056] Application Programming Interface (API) to support integration of automation tools and third-party services;
[0057] Containerized deployment support ensures that the system can run on multiple cloud platforms.
[0058] Compared with the prior art, the present invention has the following beneficial effects:
[0059] The automated and intelligent management method and system of cloud computing network proposed in the present invention reduces the need for manual intervention through an automated network configuration system, thereby significantly improving the efficiency of network management. The adaptive network configuration can quickly respond to the deployment and migration of virtual machines and changes in business loads, ensuring efficient use of network resources.
[0060] The AI-based active security defense mechanism can monitor the network status in real time, automatically identify and defend against various security threats, including DDoS attacks, malware propagation, etc. Compared with traditional passive defense methods, this active defense mechanism can more effectively protect the security of the cloud computing environment.
[0061] The intelligent resource optimization and scheduling system can dynamically adjust network resource allocation according to real-time business needs, improve resource utilization, reduce operating costs, and ensure that the performance requirements of key businesses are met.
[0062] Intelligent fault diagnosis and self-healing networks can quickly locate problems and automatically perform recovery operations when network failures occur, minimizing service interruption time and enhancing the reliability and business continuity of cloud computing services.
[0063] The automated and intelligent network management system reduces the reliance on professional operation and maintenance personnel and reduces labor costs. At the same time, the system's high adaptability and self-healing capabilities reduce fault handling time and reduce business losses caused by network failures. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] Figure 1 It is a flow chart of the method of the present invention;
[0065] Figure 2This is a system block diagram of the present invention. DETAILED DESCRIPTION
[0066] In order to make the purpose and technical solution of the present invention clearly and completely described, and the advantages more clearly understood, the embodiments of the present invention are further described in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are part of the embodiments of the present invention, rather than all of the embodiments, and are only used to explain the embodiments of the present invention, and are not used to limit 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.
[0067] For example, see Figure 1 The present invention provides a technical solution: an automated and intelligent management method for a cloud computing network, the method comprising the following steps:
[0068] Adaptive network configuration; specific operations include:
[0069] Real-time monitoring of network traffic, virtual machine status, and business load data;
[0070] Use machine learning algorithms to predict future network traffic changes;
[0071] Dynamically adjust network resource allocation based on traffic prediction results;
[0072] Automatically send configuration commands to network devices;
[0073] Continuously optimize configuration strategies through feedback loops.
[0074] Security threat identification and defense; specific operations include:
[0075] Real-time network traffic analysis to identify abnormal traffic patterns;
[0076] Automatically generate security policies and automatically deploy defense measures based on identified threats;
[0077] Security situation awareness and visualization, monitoring and displaying network security status;
[0078] Threat intelligence integration and sharing to improve threat identification capabilities;
[0079] Security policy adaptive optimization automatically adjusts security policy based on the latest threat intelligence.
[0080] Intelligent fault diagnosis and self-healing; specific operations include:
[0081] Use fault detection and location algorithms to quickly identify the source of network faults;
[0082] Fault cause analysis to determine the root cause of the fault;
[0083] Self-healing strategy generation and execution, automatically generating and executing recovery operations based on the cause of the failure;
[0084] Self-healing effect verification and feedback, evaluate the effect of self-healing operations and optimize self-healing strategies;
[0085] Self-healing knowledge base accumulates fault handling experience and assists in the generation of self-healing strategies.
[0086] System testing and performance evaluation, including:
[0087] A unified user interface for managing network configuration, security defense, and fault recovery;
[0088] Lay out application programming interfaces to support integration of automation tools and third-party services;
[0089] Containerized deployment support ensures that the system can run on multiple cloud platforms.
[0090] Embodiment 2, based on embodiment 1, proposes:
[0091] 1. Implementation of adaptive network configuration and optimization system
[0092] 1.1 Requirements Analysis and System Design
[0093] First, we worked with cloud computing service providers to deeply analyze network configuration requirements, including virtual machine deployment modes, migration frequencies, peak and valley changes in network traffic, etc. Based on these requirements, we designed the overall architecture of the adaptive network configuration system and clarified the module division and functional responsibilities of the system.
[0094] 1.2 Data collection and processing
[0095] Develop data collection modules to collect network traffic, virtual machine status, business load and other data in real time. Use big data processing technologies such as Apache Spark to clean, transform and aggregate data to provide high-quality input for subsequent analysis and decision-making.
[0096] 1.3 Traffic Analysis and Forecasting
[0097] Using machine learning algorithms, such as the long short-term memory network (LSTM), a traffic prediction model is established. This model can predict future network traffic trends based on historical data and provide decision support for network configuration.
[0098] 1.4 Adaptive Configuration Strategy Development
[0099] Develop adaptive configuration strategies to dynamically adjust network resource allocation based on traffic forecast results. For example, when traffic peaks are predicted, the system can automatically increase bandwidth allocation to avoid congestion; when traffic is low, it can reduce resource allocation to improve resource utilization.
[0100] 1.5 Configuration execution and feedback
[0101] Design a configuration execution module to convert the adaptive configuration strategy into specific network configuration commands and automatically send them to network devices. At the same time, establish a feedback mechanism to monitor the configuration execution effect in real time and adjust the prediction model and configuration strategy according to the actual network status.
[0102] 1.6 System testing and optimization
[0103] Deploy the adaptive network configuration system in the cloud environment and conduct system testing. Collect test data and evaluate system performance, such as configuration accuracy, response time, etc. Based on the test results, optimize the system design and improve the stability and reliability of the system.
[0104] 2. Implementation of AI-based active security defense mechanism
[0105] 2.1 Security Threat Identification
[0106] Develop security threat identification modules that use machine learning algorithms, such as support vector machines (SVMs), to analyze network traffic in real time and identify abnormal traffic patterns, such as DDoS attacks and malware propagation.
[0107] 2.2 Security Policy Generation
[0108] Based on the security threat identification results, security policies are automatically generated. For example, for DDoS attacks, inbound rules for abnormal traffic can be automatically restricted; for malware propagation, infected virtual machines can be automatically isolated.
[0109] 2.3 Security Situation Awareness
[0110] Build a security situation awareness system to monitor the security status of the network in real time. Use visualization technologies, such as Kibana, to display the security situation of the network and provide an intuitive security view for security operation and maintenance personnel.
[0111] 2.4 Threat Intelligence Sharing
[0112] Cooperate with the security community to establish a threat intelligence sharing mechanism. By sharing security threat information, the system's threat identification capabilities can be improved, forming a group immunity effect for security protection.
[0113] 2.5 Adaptive Security Policy Optimization
[0114] Establish an adaptive security policy optimization mechanism to dynamically adjust security policies based on the latest security threat intelligence. Use reinforcement learning algorithms to automatically explore the optimal security policy and improve the system's adaptability.
[0115] 2.6 Safety Effect Evaluation
[0116] Develop a security effectiveness evaluation module to regularly evaluate the effectiveness of security defense mechanisms. Use attack simulation technologies, such as Detonator, to test the system's defense capabilities and optimize security strategies based on the evaluation results.
[0117] 3. Implementation of intelligent fault diagnosis and self-healing network
[0118] 3.1 Fault detection and location
[0119] Develop fault detection modules to monitor the status of network devices in real time, such as CPU load, memory usage, packet loss rate, etc. Use anomaly detection algorithms, such as Isolation Forest, to quickly locate the source of faults.
[0120] 3.2 Failure Cause Analysis
[0121] Design a fault cause analysis module and use causal inference algorithms to analyze the root cause of the fault. For example, when an abnormal packet loss rate is detected, the system can automatically analyze whether it is caused by network congestion or device failure.
[0122] 3.3 Self-healing strategy generation
[0123] Based on the results of the fault cause analysis, a self-healing strategy is automatically generated. For example, in the case of network congestion, the routing strategy can be automatically adjusted; in the case of equipment failure, the backup device can be automatically switched.
[0124] 3.4 Self-healing execution and verification
[0125] Design a self-healing execution module to convert the self-healing strategy into specific operation commands for automatic execution. At the same time, establish a self-healing effect verification mechanism to evaluate the effect of the self-healing operation and ensure that the fault is effectively recovered.
[0126] 3.5 Construction of Self-Healing Knowledge Base
[0127] Build a self-healing knowledge base and accumulate fault handling experience. Use knowledge graph technology to organize and manage self-healing knowledge and provide knowledge support for fault diagnosis and self-healing strategy generation.
[0128] 3.6 Self-healing effect evaluation and optimization
[0129] Regularly evaluate the effectiveness of the self-healing network, such as the self-healing success rate, recovery time, etc. Based on the evaluation results, optimize the self-healing strategy and improve the intelligence level of the self-healing network.
[0130] Through the above implementation steps, this solution can build a highly automated and intelligent cloud computing network management system. The system can adapt to network changes, actively defend against security threats, and has self-healing capabilities, which significantly improves the management efficiency and stability of cloud computing networks. At the same time, the implementation of this solution also provides new ideas and directions for technological progress and innovative development in the field of cloud computing network management.
[0131] Embodiment 3, refer to the attached Figure 2 Based on the second embodiment, an automatic and intelligent management system for a cloud computing network is proposed, and the system includes:
[0132] Adaptive network configuration system improves network management efficiency; monitors network traffic, virtual machine status, and business load data in real time; uses machine learning algorithms to predict future network traffic changes; dynamically adjusts network resource allocation based on traffic prediction results; automatically sends configuration commands to network devices; and continuously optimizes configuration strategies through feedback loops.
[0133] Security threat identification and defense system to enhance network security; including:
[0134] Real-time network traffic analysis module to identify abnormal traffic patterns;
[0135] A security policy automatic generation module for automatically deploying defense measures based on identified threats;
[0136] Security situation awareness and visualization tools to monitor and display network security status;
[0137] Threat intelligence integration and sharing mechanism to improve threat identification capabilities;
[0138] Security policy adaptive optimization algorithm is used to automatically adjust security policies based on the latest threat intelligence.
[0139] Intelligent fault diagnosis and self-healing network to optimize resource allocation; including:
[0140] Fault detection and location algorithms to quickly identify the source of network faults;
[0141] Failure cause analysis model to determine the root cause of failure;
[0142] Self-healing strategy generation and execution system, used to automatically generate and execute recovery operations based on the cause of the failure;
[0143] Self-healing effect verification and feedback mechanism, used to evaluate the effect of self-healing operations and optimize self-healing strategies;
[0144] The self-healing knowledge base is used to accumulate fault handling experience and assist in the generation of self-healing strategies.
[0145] System testing and performance evaluation framework to improve system adaptability and self-healing capabilities; including:
[0146] A unified user interface for managing network configuration, security defense, and fault recovery;
[0147] Application Programming Interface (API) to support integration of automation tools and third-party services;
[0148] Containerized deployment support ensures that the system can run on multiple cloud platforms.
[0149] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. An automated and intelligent management method for a cloud computing network, characterized in that: The method comprises the following steps: Adaptive network configuration; Security threat identification and defense; Intelligent fault diagnosis and self-healing; System testing and performance evaluation.
2. The method for automatic and intelligent management of a cloud computing network according to claim 1, characterized in that: The specific operations of adaptive network configuration include: Real-time monitoring of network traffic, virtual machine status, and business load data; Use machine learning algorithms to predict future network traffic changes; Dynamically adjust network resource allocation based on traffic prediction results; Automatically send configuration commands to network devices; Continuously optimize configuration strategies through feedback loops.
3. The method for automatic and intelligent management of a cloud computing network according to claim 1, characterized in that: The specific operations of security threat identification and defense include: Real-time network traffic analysis to identify abnormal traffic patterns; Automatically generate security policies and automatically deploy defense measures based on identified threats; Security situation awareness and visualization, monitoring and displaying network security status; Threat intelligence integration and sharing to improve threat identification capabilities; Security policy adaptive optimization automatically adjusts security policy based on the latest threat intelligence.
4. The method for automated and intelligent management of a cloud computing network according to claim 1, characterized in that: The specific operations of intelligent fault diagnosis and self-healing include: Use fault detection and location algorithms to quickly identify the source of network faults; Fault cause analysis to determine the root cause of the fault; Self-healing strategy generation and execution, automatically generating and executing recovery operations based on the cause of the failure; Self-healing effect verification and feedback, evaluate the effect of self-healing operations and optimize self-healing strategies; Self-healing knowledge base accumulates fault handling experience and assists in the generation of self-healing strategies.
5. The method for automatic and intelligent management of a cloud computing network according to claim 1, characterized in that: The specific operations of system testing and performance evaluation include: A unified user interface for managing network configuration, security defense, and fault recovery; Lay out application programming interfaces to support integration of automation tools and third-party services; Containerized deployment support ensures that the system can run on multiple cloud platforms.
6. An automated and intelligent management system for a cloud computing network according to the automated and intelligent management method for a cloud computing network according to any one of claims 1 to 5, characterized in that: The system comprises: Adaptive network configuration system to improve network management efficiency; Security threat identification and defense system to enhance network security; Intelligent fault diagnosis and self-healing network to optimize resource allocation; System testing and performance evaluation framework to improve system adaptability and self-healing capabilities.
7. The automatic and intelligent management system for cloud computing network according to claim 6, characterized in that: The adaptive network configuration system monitors network traffic, virtual machine status and business load data in real time; uses machine learning algorithms to predict future network traffic changes; dynamically adjusts network resource allocation based on traffic prediction results; and automatically sends configuration commands to network devices; Continuously optimize configuration strategies through feedback loops.
8. The automatic and intelligent management system for cloud computing network according to claim 6, characterized in that: The security threat identification and defense system includes: Real-time network traffic analysis module to identify abnormal traffic patterns; A security policy automatic generation module for automatically deploying defense measures based on identified threats; Security situation awareness and visualization tools to monitor and display network security status; Threat intelligence integration and sharing mechanism to improve threat identification capabilities; Security policy adaptive optimization algorithm is used to automatically adjust security policies based on the latest threat intelligence.
9. The automatic and intelligent management system for cloud computing network according to claim 6, characterized in that: The intelligent fault diagnosis and self-healing network includes: Fault detection and location algorithms to quickly identify the source of network faults; Failure cause analysis model to determine the root cause of failure; Self-healing strategy generation and execution system, used to automatically generate and execute recovery operations based on the cause of the failure; Self-healing effect verification and feedback mechanism, used to evaluate the effect of self-healing operations and optimize self-healing strategies; The self-healing knowledge base is used to accumulate fault handling experience and assist in the generation of self-healing strategies.
10. The automatic and intelligent management system for cloud computing network according to claim 6, characterized in that: The system testing and performance evaluation framework includes: A unified user interface for managing network configuration, security defense, and fault recovery; Application Programming Interface (API) to support integration of automation tools and third-party services; Containerized deployment support ensures that the system can run on multiple cloud platforms.
Citation Information
Patent Citations
Network diagnosis system based on cloud intelligent maintenance center
CN118041750A
Dynamic adaptive network traffic management system and method
CN118055024A
Cloud computing service operation and maintenance management platform
CN118260158A
Cited By
Fault self-recovery method and device for cloud native platform
CN120950302A
