Network Management System Based on Intelligent Evaluation

Abstract

The present invention discloses a network management system based on intelligent evaluation, and the operation method of the system includes: performing cloud data center network equipment health index hierarchy setting management; performing index formulation for cloud data center network equipment performance evaluation; performing cloud data center network evaluation analysis and optimization processing; and performing data information reception and early warning notification processing. The cloud data center network equipment health index hierarchy setting management includes: adopting AHP hierarchical analysis method to perform network equipment health index system setting management, and obtaining the relative subjective weight of each specific performance index relative to the overall equipment health target through normalization analysis processing; after completing the network equipment health index system setting management, adopting the entropy method to calculate the objective weight of each set network performance index. The present invention has the characteristics of efficient analysis management and strong stability.

Description

Technical Field

[0001] The present invention relates to the technical field of network management, in particular to a network management system based on intelligent evaluation. Background Art

[0002] With the continuous development of modern mobile Internet, cloud computing, big data processing and virtualization technology, cloud data center network, as the supporting foundation of Internet and cloud computing, has been widely developed and applied in recent years. Cloud data center network is different from other traditional networks. Cloud data center network concentrates various network services and network resources. It is an infrastructure with large-scale data storage and analysis processing capabilities. With the innovation of Internet technology, the development of new cloud computing models, and the widespread use of virtualization technology, cloud data center network plays an increasingly important role. In modern data center networks, due to the large number of internal network devices, complex operating programs, and diverse and bursty traffic in the network, there is currently a lack of effective evaluation and analysis of the overall operation of network devices and networks and network monitoring, which makes it difficult to efficiently solve problems in the network and equipment, seriously affecting user use. Therefore, it is necessary to design a network management system based on intelligent evaluation with efficient analysis and management and strong stability. Summary of the invention

[0003] The purpose of the present invention is to provide a network management system based on intelligent evaluation to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a network management method based on intelligent evaluation, comprising:

[0005] Manage the hierarchical structure of health indicators for cloud data center network equipment;

[0006] Formulate indicators for cloud data center network equipment performance evaluation;

[0007] Conduct evaluation, analysis and optimization of cloud data center networks;

[0008] Receive data information and process early warning notifications.

[0009] According to the above technical solution, the cloud data center network equipment health index hierarchy setting management includes:

[0010] The AHP hierarchical analysis method is used to set up and manage the network equipment health index system, and the relative subjective weight of each specific performance index relative to the overall equipment health target is obtained through normalization analysis and processing;

[0011] After completing the setting and management of the network equipment health index system, the entropy method is used to calculate the objective weight of each set network performance index. The less information the performance index contains, the smaller its objective weight is, otherwise it is larger.

[0012] According to the above technical solution, the index formulation for cloud data center network equipment performance evaluation includes:

[0013] The performance evaluation of the equipment running in the network is evaluated by the formulated indicator information, so that the network administrator can specifically judge the operating status of the equipment through the formulated indicator information.

[0014] According to the above technical solution, the evaluation, analysis and optimization process of the cloud data center network includes:

[0015] After collecting real-time data information from devices in the cloud data center network, the collected data is stored in a database table;

[0016] After completing the data information collection and processing of the devices in the cloud data center network, further calculate and analyze the criticality of network nodes for optimization and management;

[0017] After obtaining the cloud data center network equipment health and node criticality data information through optimization processing, the performance evaluation of the cloud data center network is carried out.

[0018] According to the above technical solution, the receiving of data information and the early warning notification processing include:

[0019] After receiving the performance evaluation data information of the cloud data center network, it is identified and analyzed, and the result data information that is determined to have potential risks or abnormal operation is marked;

[0020] The marked result data information is transmitted to the workbench for early warning notification, so that the staff can quickly perform maintenance and management on the cloud data center network.

[0021] According to the above technical solution, a network management system based on intelligent evaluation includes:

[0022] A preliminary processing module, used for performing preliminary processing on the cloud data center network;

[0023] Analysis and evaluation module, used for cloud data center network analysis and evaluation management;

[0024] The warning receiving module is used to receive data information and process warning notifications.

[0025] According to the above technical solution, the preliminary processing module includes:

[0026] Hierarchical structure module, used for hierarchical management of network equipment health indicator system;

[0027] Performance indicator module, used for performance indicator optimization analysis and management;

[0028] The evaluation formulation module is used to formulate indicators for equipment performance evaluation.

[0029] According to the above technical solution, the analysis and evaluation module includes:

[0030] Data collection module, used for data information collection and management;

[0031] Analysis and management module, used for analyzing and processing data information;

[0032] The evaluation processing module is used to perform performance evaluation processing on the cloud data center network.

[0033] According to the above technical solution, the warning receiving module includes:

[0034] A receiving and identifying module, used for receiving and identifying data information;

[0035] The early warning notification module is used for early warning notification control.

[0036] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by providing a preliminary processing module, an analysis and evaluation module and a receiving early warning module, can make the hierarchical structure setting of network equipment health indicators more comprehensive and specific, which is beneficial to subsequent evaluation and analysis processing, and makes the equipment health results obtained by the final analysis of each performance indicator more reasonable and reliable, focuses on tracking and observing equipment with low health values, and further effectively helps network management personnel understand the operation status of the entire network and equipment, and realizes automatic monitoring and management of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0038] Figure 1 is a flow chart of a network management method based on intelligent evaluation provided in Embodiment 1 of the present invention;

[0039] Figure 2 This is a module structure diagram of a network management system based on intelligent evaluation provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0041] Embodiment 1: Figure 1 This is a flow chart of a network management method based on intelligent evaluation provided in Embodiment 1 of the present invention. This embodiment can be applied to a network management system. The method can be executed by a network management system based on intelligent evaluation provided in an embodiment of the present invention. The system is composed of multiple software and hardware modules, such as Figure 1 As shown, the method specifically comprises the following steps:

[0042] S101. Perform cloud data center network equipment health indicator hierarchy configuration management;

[0043] Exemplarily, in an embodiment of the present invention, the AHP hierarchical analysis method is used to set up and manage the network equipment health index system, and the relative subjective weight of each specific performance indicator relative to the overall equipment health target is obtained through normalized analysis processing; in this step, first, a pairwise comparison matrix of each performance indicator in the network construction sub-criteria layer relative to the main criterion layer is constructed respectively, and then the normalized result value of each performance indicator in the current layer relative to the main criterion layer comparison matrix is ​​calculated respectively through the rule column averaging method, so as to obtain the relative weight of each performance indicator in the sub-criteria layer relative to the main criterion layer, and after the relative weight of the main criterion layer relative to the overall target, i.e., the health of the network equipment, is obtained by analyzing the same method, the relative subjective weight of each specific performance indicator relative to the overall target of the equipment health is obtained, wherein when constructing the comparison judgment matrix, the corresponding scale value is filled in according to the AHP hierarchical analysis method, and through this processing, the network equipment health index hierarchy structure setting can be made more comprehensive and specific, which is conducive to subsequent evaluation and analysis processing.

[0044] After completing the setting and management of the network equipment health index system, the entropy method is used to calculate the objective weights of each set network performance index. The less information the performance index contains, the smaller its objective weight is, otherwise the larger it is. Through this step, the equipment health results obtained by the final analysis of each performance index can be made more reasonable and reliable.

[0045] S102. Formulate indicators for cloud data center network equipment performance evaluation;

[0046] Exemplarily, in an embodiment of the present invention, indicators are formulated for performance evaluation of equipment running in the network through formulated indicator information, so that network administrators can specifically judge the operating status of the equipment through the formulated indicator information; in this step, the formulated indicator information includes: average port packet loss rate, average error packet rate, average throughput, average terminal utilization and other indicator information of network equipment. Through the formulation of this indicator, the overall operating status of the network equipment can be reflected from aspects such as network availability, abnormality of network communication data, and data forwarding capability. Devices with low health values ​​can be tracked and observed in detail, and further effectively help network management personnel understand the operating status of the entire network and equipment, and realize automated monitoring and management of the network.

[0047] S103, performing evaluation, analysis and optimization processing of the cloud data center network;

[0048] Exemplarily, in an embodiment of the present invention, after real-time data information is collected from devices in the cloud data center network, the collected data is stored in a database table; in this step, the ICMP protocol is used to collect device interface status data, and the SNMP network management protocol is used to complete the collection of data such as relevant performance parameter values ​​of network devices and device system information, as well as the setting of corresponding Trap and Syslog servers to record and collect relevant log information of device operation. Specifically, the thread pool service of the SNMP management end for processing messages is first enabled. Whenever an agent sends data information at the device layer, the SNMP management end thread pool is controlled to determine whether the thread pool thread has been used up. If it has been used up, the thread pool sending the message is enabled. The message is blocked until an idle thread is generated to process the data information. If there is an idle processing thread, the information processing thread is controlled to parse the information and store the parsed results in the corresponding database table. At the same time, the control network establishes a Socket socket descriptor and sets its specific properties through the set Trap and Syslog servers. Finally, the Socket socket is monitored. When a network event or alarm event occurs, the network device agent will automatically send a message to the server. The Trap and Syslog server will automatically parse the corresponding message and store the log information contained in it in the database. Through this processing, the collection of data information can be more comprehensive and accurate, and the generation of errors can be effectively avoided.

[0049] After completing the data information collection and processing of the equipment in the cloud data center network, the criticality of the network nodes is further calculated, analyzed and optimized. In this step, the network topology data collected from the resource layer is first converted into an adjacency matrix representation, and the degree and betweenness values ​​of the network device nodes are calculated respectively. Then, the attribute matrix of the degree and betweenness is constructed, and the mean square error coefficient is used to calculate the weights of the node degree and betweenness respectively. Finally, the node criticality mean square error decision contribution matrix is ​​constructed and the criticality value of the network node is calculated by normalizing the matrix.

[0050] After obtaining the cloud data center network equipment health and node criticality data information through optimization processing, the performance evaluation of the cloud data center network is performed; in this step, the cloud data center network equipment health and node criticality data information are compared with the set thresholds respectively. If both data information exceed the set threshold information, it is determined that the current cloud data center network is in good operating condition. If there is one of the data information that is less than the set corresponding threshold, it is determined that the current cloud data center network is in a potential risk of operating. Otherwise, it indicates that the current cloud data center network is operating abnormally.

[0051] S104, receiving data information and processing early warning notifications;

[0052] Exemplarily, in an embodiment of the present invention, after receiving the performance evaluation data information of the cloud data center network, it is identified and analyzed, and the result data information determined to have potential risks or abnormal operation is marked;

[0053] The marked result data information is transmitted to the workbench for early warning notification, so that the staff can quickly perform maintenance and management on the cloud data center network.

[0054] Embodiment 2: Embodiment 2 of the present invention provides a network management system based on intelligent evaluation. Figure 2 The schematic diagram of the module structure of the network management system based on intelligent evaluation provided in the second embodiment is as follows: Figure 2 As shown, the system includes:

[0055] A preliminary processing module, used for performing preliminary processing on the cloud data center network;

[0056] Analysis and evaluation module, used for cloud data center network analysis and evaluation management;

[0057] The warning receiving module is used to receive data information and process warning notifications.

[0058] In some embodiments of the present invention, the preliminary processing module includes:

[0059] Hierarchical structure module, used for hierarchical management of network equipment health indicator system;

[0060] Performance indicator module, used for performance indicator optimization analysis and management;

[0061] The evaluation formulation module is used to formulate indicators for equipment performance evaluation.

[0062] In some embodiments of the present invention, the analysis and evaluation module includes:

[0063] Data collection module, used for data information collection and management;

[0064] Analysis and management module, used for analyzing and processing data information;

[0065] The evaluation processing module is used to perform performance evaluation processing on the cloud data center network.

[0066] In some embodiments of the present invention, the early warning receiving module includes:

[0067] A receiving and identifying module, used for receiving and identifying data information;

[0068] The early warning notification module is used for early warning notification control.

[0069] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0070] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A network management method based on intelligent evaluation, characterized in that: include: Manage the hierarchical structure of health indicators for cloud data center network equipment; Formulate indicators for cloud data center network equipment performance evaluation; Conduct evaluation, analysis and optimization of cloud data center networks; Receive data information and process early warning notifications; The cloud data center network equipment health indicator hierarchy structure setting management includes: The AHP hierarchical analysis method is used to set up and manage the network equipment health index system, and the relative subjective weight of each specific performance index relative to the overall equipment health target is obtained through normalization analysis and processing; In this step, firstly, the pairwise comparison matrix of each performance index in the network construction sub-criteria level relative to the main criterion level is constructed respectively, and then the normalized result value of each performance index in the current level relative to the comparison matrix of the main criterion level is calculated respectively by the rule column average method, so as to obtain the relative weight of each performance index in the sub-criteria level relative to the main criterion level, and then the relative weight of the main criterion level relative to the overall goal, that is, the health of the network equipment, is obtained by the same method, and then the relative subjective weight of each specific performance index relative to the overall goal of the health of the equipment is obtained, wherein when constructing the comparison judgment matrix, the corresponding scale value is filled in according to the AHP hierarchical analysis method; After completing the setting and management of the network equipment health index system, the objective weight of each set network performance index is calculated using the entropy value method. The less information the performance index contains, the smaller its objective weight is, otherwise, the larger it is; The formulating of indicators for cloud data center network equipment performance evaluation includes: The performance evaluation of the equipment running in the network is evaluated by the formulated indicator information, so that the network administrator can judge the operation status of the equipment in detail through the formulated indicator information; In this step, the formulated indicator information includes: average packet loss rate, average error packet rate, average throughput, average end utilization rate and other indicator information of the network equipment. Through the formulation of this indicator, the overall operation status of the network equipment can be reflected from aspects such as network availability, abnormality of network communication data, and data forwarding capability. The equipment with low health value can be tracked and observed in detail. The evaluation, analysis and optimization process of the cloud data center network includes: After collecting real-time data information from devices in the cloud data center network, the collected data is stored in a database table; In this step, the ICMP protocol is used to collect the device interface status data, and the SNMP network management protocol is used to complete the collection of data such as the relevant performance parameter values ​​and device system information of the network device, and the relevant log information of the device operation is recorded and collected by setting the corresponding Trap and Syslog servers. Specifically, the thread pool service of the SNMP management end for processing messages is first turned on. Whenever an agent sends data information at the device layer, the SNMP management end thread pool is controlled to determine whether the thread of the thread pool has been used up. If it has been used up, the sent message is blocked until an idle thread is generated to process the data information. If there is an idle processing thread, the information processing thread is controlled to parse the information and store the parsed result in the corresponding database table. At the same time, the control network establishes a Socket socket descriptor and sets its specific attributes through the set Trap and Syslog servers, and finally monitors the Socket socket. When a network event or alarm event occurs, the network device agent will automatically send a message to the server, and the Trap and Syslog server will automatically parse the corresponding message and store the log information contained in it in the database. After completing the data information collection and processing of the devices in the cloud data center network, further calculate and analyze the criticality of network nodes for optimization and management; In this step, the network topology data collected from the resource layer is first converted into the representation of the adjacency matrix, and the degree and betweenness values ​​of the network device nodes are calculated respectively. Then, the attribute matrix of degree and betweenness is constructed, and the weights of node degree and betweenness are calculated respectively using the mean square error coefficient. Finally, the node criticality mean square error decision contribution matrix is ​​constructed and the criticality value of the network node is calculated by normalizing the matrix. After obtaining the cloud data center network equipment health and node criticality data information through optimization, the cloud data center network performance evaluation is performed; In this step, the cloud data center network equipment health and node criticality data information are compared with the set thresholds respectively. If both data information exceed the set threshold information, it is determined that the current cloud data center network is in good condition. If one of the data information is less than the set corresponding threshold, it is determined that the current cloud data center network is in a potential risk. Otherwise, it indicates that the current cloud data center network is operating abnormally. The receiving of data information and early warning notification processing include: After receiving the performance evaluation data information of the cloud data center network, it is identified and analyzed, and the result data information that is determined to have potential risks or abnormal operation is marked; The marked result data information is transmitted to the workbench for early warning notification, so that the staff can quickly perform maintenance and management on the cloud data center network.

Images