Intelligent operation and maintenance management system, method and device for model simulation and data optimization

Abstract

The invention belongs to the field of intelligent operation and maintenance management, relates to a data analysis technology, and is used for solving the problems that an existing operation and maintenance management system cannot find out core operation and maintenance data from massive operation and maintenance data and cannot accurately alarm the operation state of the system according to the priority of the core operation and maintenance data. The intelligent operation and maintenance management system comprises a model simulation module, an operation and maintenance data analysis module, an operation and maintenance alarm module and an operation and maintenance optimization evaluation module. The model simulation module, the operation and maintenance data analysis module, the operation and maintenance alarm module and the operation and maintenance optimization evaluation module are in communication connection in sequence; the core operation and maintenance data can be found out from massive operation and maintenance data, and the core operation and maintenance data are jointly monitored, so that the risk degree of the system is accurately judged, an alarm is given in time, potential problems can be found in advance, the occurrence probability of system faults is effectively reduced, continuous and normal operation of services is guaranteed, and the service quality is improved. And the operation and maintenance efficiency and the resource utilization rate are improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent operation and maintenance management, and relates to data analysis technology, specifically to an intelligent operation and maintenance management system, method and device for model simulation and data optimization. Background Art

[0002] The intelligent operation and maintenance management system is a platform that uses artificial intelligence, big data, machine learning and other technologies to realize automated and intelligent monitoring, management and maintenance of IT systems, network equipment, servers, applications, etc.; with the rapid development of information technology, the business operations of enterprises and organizations are increasingly dependent on information systems, and the stable operation and efficient management of information systems have become key factors in ensuring business continuity and competitiveness.

[0003] With the growth of business and the continuous updating of technology, the scale of infrastructure such as servers, network equipment and storage devices in information systems continues to expand, and their mutual connections and dependencies have become more complex. When dealing with these complex systems, traditional operation and maintenance management methods have many shortcomings, such as low accuracy and difficulty in coping with massive data.

[0004] Existing operation and maintenance management systems are often unable to perform model simulation and optimization analysis on massive amounts of operation and maintenance data to find the core operation and maintenance data that reflects the system status. They are also unable to accurately warn of the system's operating status based on the priority of the core operation and maintenance data, resulting in the inability of operation and maintenance personnel to respond and handle problems quickly and effectively.

[0005] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent operation and maintenance management system, method and device for model simulation and data optimization, which is used to solve the problem that the existing operation and maintenance management system cannot find the core operation and maintenance data reflecting the system status from the massive operation and maintenance data, and cannot accurately warn the operating status of the system according to the priority of the core operation and maintenance data; The technical problem to be solved by the present invention is: how to provide an intelligent operation and maintenance management system, method and device for model simulation and data optimization that can find core operation and maintenance data reflecting the system status from massive operation and maintenance data, and at the same time can accurately warn the system's operating status according to the priority of the core operation and maintenance data.

[0007] The purpose of the present invention can be achieved by the following technical solutions: An intelligent operation and maintenance management system for model simulation and data optimization includes a model simulation module, an operation and maintenance data analysis module, an operation and maintenance alarm module, and an operation and maintenance optimization evaluation module; the model simulation module, the operation and maintenance data analysis module, the operation and maintenance alarm module, and the operation and maintenance optimization evaluation module are sequentially connected in communication; The model simulation module is used to build and simulate the operation and maintenance management model: the infrastructure that needs to be operated and managed is marked as an operation and maintenance component, the operation and maintenance component is modeled using simulation software, a simulation cycle with a fixed duration of T1 is generated, the actual workload is simulated within the simulation cycle, and the load factor FZ within the simulation cycle is calculated; The operation and maintenance data analysis module is used to analyze and optimize the classification of the operation and maintenance data according to the simulation model: the data collected during the model simulation in the simulation cycle is marked as operation and maintenance data YWi, where i is the number of types of operation and maintenance data, i=1,2...m, and m is a positive integer; the operation and maintenance data YWi in n simulation cycles and the load factor FZ are calculated to obtain the compliance ratio FH, and the operation and maintenance data YWi is divided into core operation and maintenance data HX and general operation and maintenance data according to the compliance ratio FH; The operation and maintenance alarm module is used to jointly monitor and alarm the operation and maintenance components according to the optimized core operation and maintenance data: in the operation and maintenance work, the abnormal value YC of the core operation and maintenance data HX is obtained, the abnormal coefficient YX is calculated by the abnormal value YC of all the core operation and maintenance data HX, and the operation and maintenance components are monitored and alarmed according to the abnormal coefficient YX; The operation and maintenance optimization evaluation module is used to evaluate the operation and maintenance optimization according to the service availability coefficients before and after optimization: generate a service cycle with a fixed duration of T2, obtain the service availability coefficient FW and the historical service availability coefficient LW within the service cycle, and determine whether the operation and maintenance optimization meets the conditions by comparing the service availability coefficient FW and the historical service availability coefficient LW.

[0008] Furthermore, the operation and maintenance components include servers, network devices and storage devices, and the connection relationships, dependencies, configuration information and performance parameters between the operation and maintenance components are defined according to the actual working status.

[0009] Furthermore, the workload includes user request volume QQ, data traffic LL and concurrent access volume BF; the user request volume QQ is the number of user requests to the server during the simulation period; the data traffic LL is the sum of the traffic of different types of request data during the simulation period, and the request data includes text data, image data and audio data; the concurrent access volume BF is the average number of users accessing the server at the same time during the simulation period; the user request volume QQ, data traffic LL and concurrent access volume BF are numerically calculated to obtain the load coefficient FZ during the simulation period.

[0010] Furthermore, the operation and maintenance data YWi within n simulation cycles are obtained, and a rectangular coordinate system is established with the operation and maintenance data YWi as the Y axis of the coordinate system and the simulation cycle as the X axis of the coordinate system. Points are plotted in the rectangular coordinate system and a scatter plot of the operation and maintenance data YWi-cycle is drawn; the n coordinate points on the scatter plot of the operation and maintenance data YWi-cycle are recorded as (X n , Y n ), the angle between the line connecting two adjacent coordinate points and the positive direction of the X-axis is recorded as θ n , then θ n =arctan[(Y n+1 -Y n ) / (X n+1 -X n )]; Similarly, obtain the load factor FZ within n simulation cycles and draw a load factor FZ-cycle scatter plot, and calculate the angle β between the line connecting two adjacent coordinate points and the positive direction of the X-axis n ; The included angle β n and the angle θ corresponding to the simulation period n , compared with the preset angle α: If |β n -θ n |≤ α, then the change trend between the two sets of coordinate points on the two scatter plots meets the requirements. If |β n -θ n |>α, then it is judged that the change trend between the two corresponding sets of coordinate points on the two scatter plots does not meet the requirements.

[0011] Furthermore, the total number of (n-1) groups of angles β in n simulation cycles is n ,θ n The ratio of the number of data that meet the requirements to (n-1) is recorded as the compliance ratio FH, and the ratio of the number that does not meet the requirements to (n-1) is recorded as the non-compliance ratio BH, then FH+BH=1; compare the compliance ratio FHi corresponding to the operation and maintenance data YWi with the preset compliance threshold FHmax: if the compliance ratio FHi is greater than or equal to the compliance threshold FHmax, then it is judged that the operation and maintenance data YWi can meet the actual workload, and the operation and maintenance data YWi is recorded as the core operation and maintenance data HX; if the compliance ratio FHi is less than the compliance threshold FHmax, then it is judged that the operation and maintenance data YWi cannot meet the actual workload, and the operation and maintenance data YWi is recorded as general operation and maintenance data.

[0012] Furthermore, the core operation and maintenance data HX is obtained in real time and compared with the preset core operation and maintenance data threshold HXmax: if the core operation and maintenance data HX is less than the core operation and maintenance data threshold HXmax, the core operation and maintenance data HX is judged to be normal and no processing is required; if the core operation and maintenance data HX is greater than or equal to the core operation and maintenance data threshold HXmax, the core operation and maintenance data HX is judged to be abnormal, and an abnormal value YC is assigned to the core operation and maintenance data HX. The abnormal value YC is assigned in the following manner: the core operation and maintenance data HX is arranged in descending order according to the matching ratio FHi to obtain a core operation and maintenance sequence, and the number of elements in the core operation and maintenance sequence is recorded as The number of cores is S, and the position order of the core operation and maintenance data HX in the core operation and maintenance sequence is recorded as the sequence number P, then the abnormal value YC=S-P+1; the abnormal values ​​YC of all core operation and maintenance data HX are summed and averaged to calculate the abnormal coefficient YX, and the abnormal coefficient YX is compared with the preset abnormal threshold YXmax: if the abnormal coefficient YX is less than the abnormal threshold YXmax, the system risk is judged to be low, and a low-risk alarm signal is generated and sent to the mobile phone terminal of the administrator; if the abnormal coefficient YX is greater than or equal to the abnormal threshold YXmax, the system risk is judged to be high, and a high-risk alarm signal is generated and sent to the mobile phone terminal of the administrator.

[0013] Furthermore, the normal time ZC and the fault time GZ within the service cycle are obtained; the normal time ZC is the total time of normal operation within the service cycle, and the fault time GZ is the total time of failure within the service cycle; the normal time ZC and the fault time GZ are numerically calculated to obtain the service availability coefficient FW within the service cycle; the historical service data before the core operation and maintenance data is used for operation and maintenance alarm is obtained through the historical database, and the historical service data includes the historical total normal operation time and the historical total failure time. Similarly, the historical total normal operation time and the historical total failure time are numerically calculated to obtain the historical service availability coefficient LW; the service availability coefficient FW is compared with the historical service availability coefficient LW: if the service availability coefficient FW is greater than the historical service availability coefficient LW, it is judged that the generation condition of the alarm signal meets the requirements and no adjustment is required; if the service availability coefficient FW is less than or equal to the historical service availability coefficient LW, it is judged that the generation condition of the alarm signal does not meet the requirements, and an operation and maintenance optimization signal is generated and sent to the mobile phone terminal of the manager.

[0014] The intelligent operation and maintenance management method of model simulation and data optimization includes the following steps: Step 1: Mark the infrastructure that needs to be managed as an operation and maintenance component, use simulation software to model the operation and maintenance component, generate a simulation cycle with a fixed duration of T1, simulate the actual user request volume QQ, data traffic LL, and concurrent access volume BF during the simulation cycle, and perform numerical calculations on the user request volume QQ, data traffic LL, and concurrent access volume BF to obtain the load factor FZ during the simulation cycle; Step 2: Obtain the operation and maintenance data YWi within n simulation cycles, plot points in the rectangular coordinate system and draw a scatter plot of the operation and maintenance data YWi-cycle, and calculate the angle θ between the line connecting two adjacent coordinate points and the positive direction of the X-axis n Similarly, obtain the load factor FZ within n simulation cycles and calculate the angle β between the line connecting two adjacent coordinate points and the positive direction of the X axis n , and according to the angle β n ,θ n Calculate the compliance ratio FH and divide the operation and maintenance data YWi into core operation and maintenance data and general operation and maintenance data; Step 3: In actual operation and maintenance work, the core operation and maintenance data HX is compared with the preset core operation and maintenance data threshold HXmax to determine whether the core operation and maintenance data HX is abnormal and calculate the abnormal coefficient YX. A low-risk alarm or a high-risk alarm is issued by determining the abnormal coefficient YX; Step 4: Generate a service cycle with a fixed duration of T2, and perform numerical calculations on the normal time ZC and the fault time GZ within the service cycle to obtain the service availability coefficient FW; compare the service availability coefficient FW with the historical service availability coefficient LW to determine whether the operation and maintenance optimization meets the requirements.

[0015] An intelligent operation and maintenance management device for model simulation and data optimization, wherein the intelligent operation and maintenance management device for model simulation and data optimization is applied to an intelligent operation and maintenance management system for model simulation and data optimization.

[0016] The present invention has the following beneficial effects: 1. Accurate model building and simulation of operation and maintenance management through the model simulation module can more realistically reflect the system's workload and operating status, providing an accurate basis for subsequent data analysis and optimization; 2. The operation and maintenance data analysis module can deeply analyze the operation and maintenance data, optimize and classify it according to its conformity with the actual workload, and divide the massive operation and maintenance data into core operation and maintenance data and general operation and maintenance data, so that the operation and maintenance personnel can focus on key data more specifically; 3. The operation and maintenance alarm module conducts joint monitoring based on core operation and maintenance data, assigns abnormal values ​​to abnormal core operation and maintenance data through calculation and comparison, so as to accurately judge the risk level of the system. Through accurate analysis of operation and maintenance data, timely alarm can be issued, which can discover and solve potential problems in advance, effectively reduce the probability of system failures, ensure the continuous and normal operation of the business, and reduce unnecessary troubleshooting time and resource waste, thereby improving operation and maintenance efficiency and resource utilization; 4. Through intelligent operation and maintenance management, the costs caused by manual monitoring and erroneous judgment are reduced, while the system availability is improved, indirectly reducing the business loss costs caused by system failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 is an overall system block diagram of Embodiment 1 of the present invention; Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0020] Embodiment 1: Figure 1 As shown, the intelligent operation and maintenance management system for model simulation and data optimization includes a model simulation module, an operation and maintenance data analysis module, an operation and maintenance alarm module, and an operation and maintenance optimization evaluation module; the model simulation module, the operation and maintenance data analysis module, the operation and maintenance alarm module, and the operation and maintenance optimization evaluation module are sequentially connected in communication; The model simulation module is used to build models and simulate operation and maintenance management: the infrastructure that needs to be operated and managed is marked as operation and maintenance components, and the operation and maintenance components are modeled using simulation software. The operation and maintenance components include servers, network devices, and storage devices. The connection relationship, dependency relationship, configuration information, and performance parameters between the operation and maintenance components are defined according to the actual working status; a simulation cycle with a fixed duration of T1 is generated, and the actual workload is simulated during the simulation cycle. The workload includes user request volume QQ, data traffic LL, and concurrent access volume BF; the user request volume QQ is the number of user requests to the server during the simulation cycle; the data traffic LL is the number of different types of requests during the simulation cycle. The request data includes text data, image data and audio data; the concurrent access volume BF is the average number of users accessing the server at the same time during the simulation period; the user request volume QQ, data flow LL and concurrent access volume BF are numerically calculated through the formula FZ=k1*QQ+k2*LL+k3*BF to obtain the load factor FZ during the simulation period, where k1, k2 and k3 are all proportional coefficients, and k1>k2>k3; the model simulation module is used to accurately build and simulate the operation and maintenance management model, which can more realistically reflect the system's workload and operating status, and provide an accurate basis for subsequent data analysis and optimization.

[0021] The operation and maintenance data analysis module is used to analyze and optimize the classification of operation and maintenance data according to the simulation model: the data collected during the model simulation in the simulation cycle is marked as operation and maintenance data YWi, where i is the number of types of operation and maintenance data, i=1,2...m, and m is a positive integer; it should be noted that the operation and maintenance data YWi includes server data, network data, application data, etc. Server data includes CPU usage, memory usage, disk IO speed, etc., network data includes network delay, packet loss rate, etc., and application data includes application response time, error log, warning information, etc.; The operation and maintenance data YWi can be obtained by searching and filtering log data from different sources; obtain the operation and maintenance data YWi within n simulation cycles, n is a numerical constant, and the specific value of n is set by the management personnel, and establish a rectangular coordinate system with the operation and maintenance data YWi as the Y axis of the coordinate system and the simulation cycle as the X axis of the coordinate system, draw points in the rectangular coordinate system and draw a scatter plot of the operation and maintenance data YWi-cycle; the n coordinate points on the scatter plot of the operation and maintenance data YWi-cycle are respectively recorded as (X n , Y n ), the angle between the line connecting two adjacent coordinate points and the positive direction of the X-axis is recorded as θ n , then θ n =arctan[(Y n+1 -Y n ) / (X n+1 -X n)]; Similarly, obtain the load factor FZ within n simulation cycles and draw a load factor FZ-cycle scatter plot, and calculate the angle β between the line connecting two adjacent coordinate points and the positive direction of the X-axis n ; The included angle β n and the angle θ corresponding to the simulation period n , compared with the preset angle α: If |β n -θ n |≤ α, then the change trend between the two sets of coordinate points on the two scatter plots meets the requirements. If |β n -θ n |>α, then it is judged that the change trend between the two corresponding sets of coordinate points on the two scatter plots does not meet the requirements; The total (n-1) groups of angles β in n simulation cycles n ,θ n The ratio of the number of data that meet the requirements to (n-1) is recorded as the compliance ratio FH, and the ratio of the number that does not meet the requirements to (n-1) is recorded as the non-compliance ratio BH, then FH+BH=1; compare the compliance ratio FHi corresponding to the operation and maintenance data YWi with the preset compliance threshold FHmax: if the compliance ratio FHi is greater than or equal to the compliance threshold FHmax, then it is judged that the operation and maintenance data YWi can meet the actual workload, and the operation and maintenance data YWi is recorded as the core operation and maintenance data HX; if the compliance ratio FHi is less than the compliance threshold FHmax, then it is judged that the operation and maintenance data YWi cannot meet the actual workload, and the operation and maintenance data YWi is recorded as general operation and maintenance data; the operation and maintenance data analysis module can deeply analyze the operation and maintenance data, and optimize and classify it according to its compliance with the actual workload, so as to divide the massive operation and maintenance data into core operation and maintenance data and general operation and maintenance data, so that the operation and maintenance personnel can pay more attention to key data.

[0022] The operation and maintenance alarm module is used to jointly monitor the operation and maintenance components and issue alarms based on the optimized core operation and maintenance data: in actual operation and maintenance work, the core operation and maintenance data HX is obtained in real time and compared with the preset core operation and maintenance data threshold HXmax: if the core operation and maintenance data HX is less than the core operation and maintenance data threshold HXmax, the core operation and maintenance data HX is judged to be normal and no processing is required; if the core operation and maintenance data HX is greater than or equal to the core operation and maintenance data threshold HXmax, the core operation and maintenance data HX is judged to be abnormal, and an abnormal value YC is assigned to the core operation and maintenance data HX. The allocation method of the abnormal value YC is: the core operation and maintenance data HX is arranged in order from large to small according to the compliance ratio FHi to obtain the core operation and maintenance sequence, and the number of elements in the core operation and maintenance sequence is recorded as the core number S, and the position order of the core operation and maintenance data HX in the core operation and maintenance sequence is recorded as the sequence number P, then the abnormal value YC=S-P+1; all core The abnormal value YC of the operation and maintenance data HX is summed and averaged to calculate the abnormal coefficient YX, and the abnormal coefficient YX is compared with the preset abnormal threshold YXmax: if the abnormal coefficient YX is less than the abnormal threshold YXmax, the system risk is judged to be low, a low-risk alarm signal is generated and the signal is sent to the manager's mobile terminal; if the abnormal coefficient YX is greater than or equal to the abnormal threshold YXmax, the system risk is judged to be high, a high-risk alarm signal is generated and the signal is sent to the manager's mobile terminal; the operation and maintenance alarm module performs joint monitoring based on the core operation and maintenance data, calculates and compares the abnormal core operation and maintenance data and assigns abnormal values, so as to accurately judge the risk level of the system, and issues timely alarms through precise analysis of the operation and maintenance data, which can detect and solve potential problems in advance, effectively reduce the probability of system failures, and ensure the continuous and normal operation of the business, while reducing unnecessary troubleshooting time and resource waste, and improving operation and maintenance efficiency and resource utilization.

[0023] The operation and maintenance optimization evaluation module is used to evaluate the operation and maintenance optimization according to the service availability coefficient before and after optimization: generate a service cycle with a fixed duration of T2, and obtain the normal time ZC and the failure time GZ within the service cycle; the normal time ZC is the total time of normal operation within the service cycle, and the failure time GZ is the total time of failure within the service cycle; through the formula The normal time ZC and the fault time GZ are numerically calculated to obtain the service availability coefficient FW within the service cycle; the historical service data before the core operation and maintenance data is used for operation and maintenance alarm is obtained through the historical database. The historical service data includes the historical total normal operation time and the historical total fault time. Similarly, the historical total normal operation time and the historical total fault time are numerically calculated to obtain the historical service availability coefficient LW; the service availability coefficient FW is compared with the historical service availability coefficient LW: if the service availability coefficient FW is greater than the historical service availability coefficient LW, it is judged that the generation condition of the alarm signal meets the requirements and no adjustment is required; if the service availability coefficient FW is less than or equal to the historical service availability coefficient LW, it is judged that the generation condition of the alarm signal does not meet the requirements, and an operation and maintenance optimization signal is generated and sent to the mobile phone terminal of the manager.

[0024] Embodiment 2: Figure 2 As shown, the intelligent operation and maintenance management method of model simulation and data optimization includes the following steps: Step 1: Mark the infrastructure that needs to be managed as an operation and maintenance component, use simulation software to model the operation and maintenance component, generate a simulation cycle with a fixed duration of T1, simulate the actual user request volume QQ, data traffic LL, and concurrent access volume BF during the simulation cycle, and perform numerical calculations on the user request volume QQ, data traffic LL, and concurrent access volume BF to obtain the load factor FZ during the simulation cycle; Step 2: Obtain the operation and maintenance data YWi within n simulation cycles, plot points in the rectangular coordinate system and draw a scatter plot of the operation and maintenance data YWi-cycle, and calculate the angle θ between the line connecting two adjacent coordinate points and the positive direction of the X-axis n Similarly, obtain the load factor FZ within n simulation cycles and calculate the angle β between the line connecting two adjacent coordinate points and the positive direction of the X axis n , and according to the angle β n ,θ n Calculate the compliance ratio FH and divide the operation and maintenance data YWi into core operation and maintenance data and general operation and maintenance data; Step 3: In actual operation and maintenance work, the core operation and maintenance data HX is compared with the preset core operation and maintenance data threshold HXmax to determine whether the core operation and maintenance data HX is abnormal and calculate the abnormal coefficient YX. A low-risk alarm or a high-risk alarm is issued by determining the abnormal coefficient YX; Step 4: Generate a service cycle with a fixed duration of T2, and perform numerical calculations on the normal time ZC and the fault time GZ within the service cycle to obtain the service availability coefficient FW; compare the service availability coefficient FW with the historical service availability coefficient LW to determine whether the operation and maintenance optimization meets the requirements.

[0025] The intelligent operation and maintenance management system, method and device of model simulation and data optimization, when working, mark the infrastructure that needs operation and maintenance management as operation and maintenance components, use simulation software to model the operation and maintenance components, generate a simulation cycle of fixed length, and calculate the load factor within the simulation cycle, obtain the operation and maintenance data and load factor within n simulation cycles and calculate the compliance ratio, and divide the operation and maintenance data into core operation and maintenance data and general operation and maintenance data through the compliance ratio; in actual operation and maintenance work, compare the core operation and maintenance data with the threshold to determine whether the core operation and maintenance data is abnormal, and calculate the abnormal coefficient, and issue a low-risk alarm or a high-risk alarm by judging the abnormal coefficient; finally, numerically calculate the normal time and failure time within the service cycle to obtain the service availability coefficient, compare the service availability coefficient with the historical service availability coefficient, and determine whether the operation and maintenance optimization meets the requirements.

[0026] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0027] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula FZ=k1*QQ+k2*LL+k3*BF; technicians in this field collect multiple groups of sample data and set corresponding load coefficients for each group of sample data; substitute the set load coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of k1, k2 and k3 as 2.15, 1.87 and 1.65 respectively; The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the initial setting of the corresponding load coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the load coefficient is proportional to the value of the user request amount.

[0028] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0029] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Intelligent operation and maintenance management system for model simulation and data optimization, characterized by: It includes a model simulation module, an operation and maintenance data analysis module, an operation and maintenance alarm module, and an operation and maintenance optimization evaluation module; the model simulation module, the operation and maintenance data analysis module, the operation and maintenance alarm module, and the operation and maintenance optimization evaluation module are sequentially connected in communication; The model simulation module is used to build and simulate the operation and maintenance management model: the infrastructure that needs to be operated and maintained is marked as an operation and maintenance component, the operation and maintenance component is modeled using simulation software, a simulation cycle with a fixed duration of T1 is generated, the actual workload is simulated within the simulation cycle, and the load factor FZ within the simulation cycle is calculated; The operation and maintenance data analysis module is used to analyze and optimize the classification of the operation and maintenance data according to the simulation model: the data collected during the model simulation within the simulation cycle is marked as operation and maintenance data YWi, where i is the number of types of operation and maintenance data, i=1,2...m, and m is a positive integer; the operation and maintenance data YWi within n simulation cycles and the load factor FZ are calculated to obtain a coincidence ratio FH, and the operation and maintenance data YWi is divided into core operation and maintenance data HX and general operation and maintenance data according to the coincidence ratio FH; The operation and maintenance alarm module is used to jointly monitor and alarm the operation and maintenance components based on the optimized core operation and maintenance data: during the operation and maintenance work, the abnormal value YC of the core operation and maintenance data HX is obtained, the abnormal coefficient YX is calculated by the abnormal value YC of all the core operation and maintenance data HX, and the operation and maintenance components are monitored and alarmed based on the abnormal coefficient YX; The operation and maintenance optimization evaluation module is used to evaluate the operation and maintenance optimization based on the service availability coefficients before and after optimization: generate a service cycle with a fixed duration T2, obtain the service availability coefficient FW and the historical service availability coefficient LW within the service cycle, and determine whether the operation and maintenance optimization meets the conditions by comparing the service availability coefficient FW and the historical service availability coefficient LW.

2. The intelligent operation and maintenance management system for model simulation and data optimization according to claim 1 is characterized in that: Operation and maintenance components include servers, network devices, and storage devices. The connection relationships, dependencies, configuration information, and performance parameters between operation and maintenance components are defined according to the actual working status.

3. The intelligent operation and maintenance management system for model simulation and data optimization according to claim 2 is characterized in that: The workload includes user request volume QQ, data traffic LL, and concurrent access volume BF; user request volume QQ is the number of user requests to the server during the simulation period; The data traffic LL is the sum of the traffic of different types of request data during the simulation period, including text data, image data, and audio data; the concurrent access volume BF is the average number of users accessing the server at the same time during the simulation period; the user request volume QQ, data traffic LL, and concurrent access volume BF are numerically calculated to obtain the load factor FZ during the simulation period.

4. The intelligent operation and maintenance management system for model simulation and data optimization according to claim 3 is characterized in that: Obtain the operation and maintenance data YWi within n simulation cycles, and establish a rectangular coordinate system with the operation and maintenance data YWi as the Y axis of the coordinate system and the simulation cycle as the X axis of the coordinate system. Draw points in the rectangular coordinate system and draw a scatter plot of the operation and maintenance data YWi-cycle; record the n coordinate points on the scatter plot of the operation and maintenance data YWi-cycle as (X n , Y n ), the angle between the line connecting two adjacent coordinate points and the positive direction of the X-axis is recorded as θ n , then θ n =arctan[(Y n+1 -Y n ) / (X n+1 -X n )]; Similarly, obtain the load factor FZ within n simulation cycles and draw a scatter plot of load factor FZ-cycle, and calculate the angle β between the line connecting two adjacent coordinate points and the positive direction of the X axis n ; Set the angle β n and the angle θ corresponding to the simulation period n , compared with the preset angle α: If |β n -θ n |≤ α, then the change trend between the two corresponding sets of coordinate points on the two scatter plots meets the requirements. If |β n -θ n |> α, then it is judged that the change trend between the two corresponding groups of coordinate points on the two scatter plots does not meet the requirements.

5. The intelligent operation and maintenance management system for model simulation and data optimization according to claim 4 is characterized in that: The total number of (n-1) groups of angles β in n simulation cycles n ,θ n The ratio of the number of items that meet the requirements to (n-1) is recorded as the compliance ratio FH, and the ratio of the number that does not meet the requirements to (n-1) is recorded as the non-compliance ratio BH, then FH+BH=1; compare the compliance ratio FHi corresponding to the operation and maintenance data YWi with the preset compliance threshold FHmax: if the compliance ratio FHi is greater than or equal to the compliance threshold FHmax, then it is determined that the operation and maintenance data YWi can meet the actual workload, and the operation and maintenance data YWi is recorded as the core operation and maintenance data HX; if the compliance ratio FHi is less than the compliance threshold FHmax, then it is determined that the operation and maintenance data YWi cannot meet the actual workload, and the operation and maintenance data YWi is recorded as general operation and maintenance data.

6. The intelligent operation and maintenance management system for model simulation and data optimization according to claim 5 is characterized in that: The core operation and maintenance data HX is obtained in real time and compared with the preset core operation and maintenance data threshold HXmax: if the core operation and maintenance data HX is less than the core operation and maintenance data threshold HXmax, the core operation and maintenance data HX is judged to be normal and no processing is required; if the core operation and maintenance data HX is greater than or equal to the core operation and maintenance data threshold HXmax, the core operation and maintenance data HX is judged to be abnormal, and an abnormal value YC is assigned to the core operation and maintenance data HX. The abnormal value YC is assigned in the following manner: the core operation and maintenance data HX is arranged in descending order according to the compliance ratio FHi, Obtain a core operation and maintenance sequence, and record the number of elements in the core operation and maintenance sequence as the core number S, and the position order of the core operation and maintenance data HX in the core operation and maintenance sequence as the sequence number P, then the abnormal value YC = S-P+1; sum and average the abnormal values ​​YC of all core operation and maintenance data HX to calculate the abnormal coefficient YX, and compare the abnormal coefficient YX with the preset abnormal threshold YXmax: If the abnormal coefficient YX is less than the abnormal threshold YXmax, the system risk is judged to be low, and a low-risk alarm signal is generated and sent to the administrator's mobile terminal; If the abnormal coefficient YX is greater than or equal to the abnormal threshold YXmax, the system risk is judged to be high, a high-risk alarm signal is generated and sent to the administrator's mobile terminal.

7. The intelligent operation and maintenance management system for model simulation and data optimization according to claim 6 is characterized in that: Get the normal time ZC and fault time GZ within the service cycle; the normal time ZC is the total time of normal operation within the service cycle, and the fault time GZ is the total time of faults within the service cycle; The normal time ZC and the fault time GZ are numerically calculated to obtain the service availability coefficient FW within the service cycle; the historical service data before the core operation and maintenance data is used for operation and maintenance alarm is obtained through the historical database. The historical service data includes the total historical normal operation time and the total historical fault time. Similarly, the historical normal operation time and the total historical fault time are numerically calculated to obtain the historical service availability coefficient LW.

8. The intelligent operation and maintenance management system for model simulation and data optimization according to claim 7 is characterized in that: Compare the service availability coefficient FW with the historical service availability coefficient LW: If the service availability coefficient FW is greater than the historical service availability coefficient LW, it is determined that the conditions for generating the alarm signal meet the requirements and no adjustment is required; if the service availability coefficient FW is less than or equal to the historical service availability coefficient LW, it is determined that the conditions for generating the alarm signal do not meet the requirements, and an operation and maintenance optimization signal is generated and sent to the manager's mobile terminal.

9. The intelligent operation and maintenance management method for model simulation and data optimization includes the following steps: Step 1: Mark the infrastructure that requires O&M management as an O&M component. Use simulation software to model the O&M component and generate a simulation cycle with a fixed duration of T1. Simulate the actual user request volume QQ, data traffic LL, and concurrent access volume BF during the simulation cycle. Numerically calculate the user request volume QQ, data traffic LL, and concurrent access volume BF to obtain the load factor FZ during the simulation cycle. Step 2: Obtain the operation and maintenance data YWi within n simulation cycles, plot the points in the rectangular coordinate system and draw a scatter plot of the operation and maintenance data YWi-cycle, and calculate the angle θ between the line connecting two adjacent coordinate points and the positive direction of the X-axis n Similarly, obtain the load factor FZ within n simulation cycles and calculate the angle β between the line connecting two adjacent coordinate points and the positive direction of the X axis n , and according to the angle β n ,θ n Calculate the compliance ratio FH and divide the operation and maintenance data YWi into core operation and maintenance data and general operation and maintenance data; Step 3: In actual operation and maintenance work, the core operation and maintenance data HX is compared with the preset core operation and maintenance data threshold HXmax to determine whether the core operation and maintenance data HX is abnormal and calculate the abnormality coefficient YX. Based on the abnormality coefficient YX, a low-risk alarm or a high-risk alarm is issued; Step 4: Generate a service cycle with a fixed duration of T2. Perform numerical calculations on the normal time ZC and the fault time GZ within the service cycle to obtain the service availability coefficient FW. Compare the service availability coefficient FW with the historical service availability coefficient LW to determine whether the operation and maintenance optimization meets the requirements.

10. Intelligent operation and maintenance management device for model simulation and data optimization, characterized by: The intelligent operation and maintenance management device for model simulation and data optimization is applied to the system described in claim 1.

Images