Server automatic configuration management method based on artificial intelligence

Abstract

The invention relates to the technical field of server automatic configuration management. The invention relates to a server automatic configuration management method based on artificial intelligence. The method comprises the following steps: S1, collecting the number of server resources which can be used for configuration optimization, and determining service users of a server at the same time; s2, acquiring historical operation data of a service user, extracting load operation characteristics in the historical operation data, and acquiring a server resource demand quantity corresponding to each operation characteristic; by calculating the weight of the server resources and preferentially adjusting the server resources with low risk and small operation and storage occupation, the server resources are effectively distributed and used based on actual load and risk conditions instead of pure resource quantity, resource idling or over-crowding is avoided, and the overall resource utilization rate is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic server configuration management, and in particular to an automatic server configuration management method based on artificial intelligence. Background Art

[0002] The cloud center manages a large number of heterogeneous servers. During the cloud platform construction and operation and maintenance management process, the environment provisioning time is long, the configuration is complex, and the later operation and maintenance configuration model is not unified, which has become a bottleneck restricting the development of the cloud center;

[0003] At present, the mainstream solution for managing network configuration of large quantities of servers usually uses automated operation and maintenance tools such as Saltstack, Ansible, and Puppet to complete automated adjustments. However, in dynamic environments, such as frequent server changes or automatically expanded cloud environments, the automated configuration is inconsistent with the actual system status. This disconnect may lead to unexpected behaviors or configuration errors, because the automated operation and maintenance tools cannot understand the actual status changes of the system in a timely manner. As a result, when adjusting server resources, resources are prone to idleness or overcrowding, resulting in server resource interruptions, increasing the instability of system load and the possibility of failure. Therefore, an artificial intelligence-based server automatic configuration management method is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based server automatic configuration management method to solve the problems raised in the above background technology.

[0005] To achieve the above object, a server automatic configuration management method based on artificial intelligence is provided, comprising the following steps:

[0006] S1. Collect the amount of server resources that can be used for configuration optimization and determine the service users of the server;

[0007] S2. Obtain historical operation data of the service user, extract load operation features from the historical operation data, and obtain the server resource demand quantity corresponding to each operation feature;

[0008] S3. Establish an artificial intelligence model, use the artificial intelligence model to monitor the real-time operation status of service users, input the operation characteristics and the number of characteristic resource requirements into the artificial intelligence model, and grant the server resource quantity configuration management authority;

[0009] S4. Set buffer configuration rules in the artificial intelligence model, make load predictions based on historical operation data of service users, and compare the server resources required for the predicted load with the server resources required for real-time operation characteristics. Then, the artificial intelligence model selects data that occupies more server resources as management tasks.

[0010] S5. Set dynamic adjustment rules in the artificial intelligence model. When configuring and adjusting server resources, obtain the operating status of the load data in the server resources, use the operating status and running memory of the load data as weights, select the server with the highest weight value for adjustable analysis, and screen out the adjustable servers for adjustment.

[0011] As a further improvement of the technical solution, the step of S1 is as follows:

[0012] S1.1. Collect and manage the number of server resources in the system and obtain the service users of each server resource;

[0013] S1.2. Extract the configuration change log of each server resource, screen the properties of the server resources according to the configuration change log, and divide the server resources into those that can be used for configuration optimization and those that are fixedly configured, thereby obtaining the number of server resources that can be used for configuration optimization and the number of server resources that are fixedly configured.

[0014] As a further improvement of the technical solution, the steps of S2 are as follows:

[0015] S2.1. Collect historical operation data of service users, screen the historical operation data according to load status, and then extract load operation features for each load status in combination with the historical operation data to obtain operation features representing different load statuses of service users;

[0016] S2.2. Then, the operation characteristics are combined with the server resource quantity to perform demand matching, and the server resource demand quantity corresponding to each operation characteristic is obtained.

[0017] As a further improvement of the technical solution, the formula of S2 is as follows:

[0018]

[0019] Among them, R CPU is the amount of CPU resources required, C feature is the number of CPU cores required to run the feature, C server is the number of CPU cores in each server;

[0020]

[0021] Among them, R Memory is the amount of memory resources required, M feature is the memory capacity required to run the feature, M server is the memory capacity of each server;

[0022]

[0023] Among them, R Storage is the amount of storage resources required, S feature is the storage capacity required to run the feature, S server is the storage capacity of each server;

[0024]

[0025] Among them, R Network is the number of network resources required, N feature is the network bandwidth required to run the feature, N server is the network bandwidth of each server.

[0026] As a further improvement of the technical solution, the steps of S3 are as follows:

[0027] S3.1. Access the server management system and use the artificial intelligence algorithm to establish an artificial intelligence model within the server management system, and then use the artificial intelligence model to monitor the load status of the server and the real-time operation status of the service users;

[0028] S3.2. Give the artificial intelligence model the authority to manage server configuration in the server management system, and then input the number of server resources required for each operating feature obtained in S2.2 into the artificial intelligence model. Monitor each service user through the artificial intelligence model, and when the service user shows the corresponding operating characteristics, configure the required number of server resources for the service user.

[0029] As a further improvement of the technical solution, the overall server is determined to be in a high load state by setting in the server management system that the overall server usage exceeds 80%.

[0030] When the server management system is not under overall high load, the control authority priority of S3 is lower than that of S4.

[0031] When the server management system is under overall high load, the control authority of S3 takes precedence over that of S4.

[0032] S3 and S4 will trigger dynamic adjustment regulations when configuring server resources.

[0033] As a further improvement of the present technical solution, the formula of S4 is as follows:

[0034] X t =μ+φ 1 X t-1 +φ 2 X t-2 +φ+φ p X t-p +θ1t-1 +θ 2t-2 +…+θ qt-q+t

[0035] Among them, X t is the predicted load at the current time point, μ is a constant term, indicating the average level of the data, and φ 1 ,φ 2 ,…,φ p are autoregressive parameters that control the impact of historical load values ​​on current load, θ1,θ2,…,θ q is a moving average parameter that controls the impact of past errors on the current load. t is the white noise or error term at the current time point, representing the random error between the actual load and the predicted load;

[0036] ΔR=R pred -R real

[0037] Where ΔR is the difference between the predicted load and the real-time load, R pred is the predicted resource demand, R real It is the real-time resource demand;

[0038] B=α×R pred +β×ΔR

[0039] Where B is the buffer size, α and β are tuning parameters, and R pred is the predicted resource demand, ΔR is the load difference;

[0040]

[0041] Among them, S i is the priority score of task i, R i is the resource occupancy of task i, and max(R) is the maximum resource occupancy value among all tasks.

[0042] As a further improvement of the technical solution, the step of S5 is as follows:

[0043] S5.1. Dynamic adjustment rules are set in the artificial intelligence model. The dynamic adjustment rules are used to first obtain the number of server resources that need to be increased for the service user when configuring and adjusting server resources;

[0044] S5.2. Obtain the server resources corresponding to each service user, and obtain the operating status of the load data in the server resources, and then use the operating status of the load data and the memory as weights. The higher the adjustment risk coefficient of the operating status, the lower the weight, and the smaller the memory ratio, the higher the weight ratio. Then select the server with the highest weight value for adjustable analysis. After the server resources are adjusted, if the number of server resources served by the service user can still withstand the operating data generated by the service user, the server resources are determined to be adjustable servers. Conversely, after the server resources are adjusted, if the number of server resources served by the service user cannot withstand the operating data generated by the service user, the server resources are determined to be non-adjustable servers.

[0045] As a further improvement of the present technical solution, the formula of S5 is as follows:

[0046]

[0047] Where L is the current load level, R is the adjusted risk factor of the operating status, M is the current server memory usage ratio, and W is the weight;

[0048] C=AL

[0049] Among them, A is the calculated adjusted load capacity, C is the current server load capacity, if C ≥ 0, the server is adjustable; otherwise, it is not adjustable.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. In the server automatic configuration management method based on artificial intelligence, by calculating the weight of server resources, priority is given to adjusting server resources with lower risks and smaller memory usage. This ensures that adjustment decisions are based on actual load and risk conditions rather than simply the number of resources, effectively allocating and using server resources, avoiding idle or overcrowded resources, and improving overall resource utilization. At the same time, the weight calculation takes the adjustment risk factor of the operating status into consideration, reducing the risks that may arise during the adjustment process, and by giving priority to adjusting servers with lower risks, the instability of the system load and the possibility of failure are reduced.

[0052] 2. In this AI-based automatic server configuration management method, resources are dynamically adjusted to ensure that the server can meet the needs of service users and avoid situations where some servers are overloaded while other servers are idle, thereby balancing the system load, improving the server's ability to process requests, improving response time and service quality, and enhancing user experience. At the same time, automated resource adjustment reduces manual intervention, simplifies the operation and maintenance workflow, and improves operation and maintenance efficiency. Analysis based on load data and operating status makes resource adjustment decisions more scientific and reasonable, reducing human errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is the overall flow chart of the present invention;

[0054] Figure 2 A flowchart of the number of server resources in the collection and management system of the present invention;

[0055] Figure 3 A flowchart of the present invention for obtaining the number of server resource requirements corresponding to each operating feature;

[0056] Figure 4 A flowchart of configuring the required number of server resources for a service user according to the present invention;

[0057] Figure 5 A flowchart of obtaining the amount of server resources that need to be increased to serve a user according to the present invention. DETAILED DESCRIPTION

[0058] 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.

[0059] See also Figure 1-Figure 5 As shown, the purpose of this embodiment is to provide a server automatic configuration management method based on artificial intelligence, comprising the following steps:

[0060] S1. Collect the amount of server resources that can be used for configuration optimization and determine the service users of the server;

[0061] The steps of S1 are as follows:

[0062] S1.1. Collect and manage the number of server resources in the system and obtain the service users of each server resource;

[0063] Use the system monitoring tool Prometheus to collect the number and usage of server resources;

[0064] Analyze server logs (such as application logs, system logs) to identify resource usage and users of services.

[0065] S1.2. Extract the configuration change log of each server resource, screen the properties of the server resources according to the configuration change log, and divide the server resources into those that can be used for configuration optimization and those that are fixedly configured, thereby obtaining the number of server resources that can be used for configuration optimization and the number of server resources that are fixedly configured. The specific working steps are as follows:

[0066] Collect configuration change logs: Extract configuration change logs from the server management system or log system, and ensure that the logs contain information such as timestamp, change content, and change type;

[0067] Parsing configuration change logs: Use text parsing technology to extract configuration information about resources from logs, usually including parameters such as CPU, memory, storage, and network;

[0068] Determine the nature of resource configuration: Analyze the configuration change history of each server to determine the nature of the resource, by using change frequency analysis (if a configuration changes frequently, it indicates that the configuration is still being optimized) and change content analysis (check whether there is an obvious optimization trend or fixed pattern);

[0069] Classify server resources: Server resources are divided into "available for configuration optimization (resource configuration changes frequently, or configuration changes reflect a certain optimization trend)" and "fixed configuration (configuration changes rarely, or change records show that the configuration is stable)"

[0070] Statistics and Reports: Calculate the number of server resources under each category and generate reports to more accurately categorize and count server resources. The formula is as follows:

[0071]

[0072] The number of changes is the number of times a certain configuration is changed within an observation period. The observation period can be a period of one month or one year. The configuration change frequency of each server is calculated.

[0073] Stability = standard deviation (configuration parameter)

[0074] To calculate the stability of the configuration, you can use statistics such as standard deviation to measure the degree of fluctuation of the configuration parameters. The smaller the standard deviation, the more stable the configuration.

[0075] S2. Obtain historical operation data of the service user, extract load operation features from the historical operation data, and obtain the server resource demand quantity corresponding to each operation feature;

[0076] The steps of S2 are as follows:

[0077] S2.1. Collect historical operation data of service users, screen the historical operation data according to load status, and then extract load operation features for each load status combined with historical operation data to obtain operation features representing different load statuses of service users. The specific working steps are as follows:

[0078] Collect historical data: Collect historical operation data of user services, which may include CPU usage, memory usage, network traffic, I / O operations, etc.

[0079] Data types: structured data (such as database logs), unstructured data (such as log files), time series data, etc.

[0080] Define load status: classify according to different load status of the system (such as low load, medium load, high load);

[0081] Load status marking: Mark each piece of historical data with the corresponding load status;

[0082] Feature selection: extract important features from the data for each load state;

[0083] Feature construction: Generate a feature vector representing the load state.

[0084] S2.2, then match the operation characteristics with the server resource quantity to obtain the server resource quantity required for each operation characteristic. The specific working steps are as follows:

[0085] Determine operating characteristics: It is necessary to define and identify the operating characteristics of the system or application. These characteristics include computing requirements, memory requirements, storage requirements, network requirements, GPU requirements, I / O operations, etc.

[0086] Determine server resources: Understand the resource configuration of each server, usually including CPU, memory, storage, network, GPU quantity and type, etc.;

[0087] Establish resource demand model: Establish resource demand model for each operation characteristic, usually using the following formula:

[0088]

[0089] Among them, R CPU is the amount of CPU resources required, C featureis the number of CPU cores required to run the feature, C server is the number of CPU cores in each server;

[0090]

[0091] Among them, R Memory is the amount of memory resources required, M feature is the memory capacity required to run the feature, M server is the memory capacity of each server;

[0092]

[0093] Among them, R Storage is the amount of storage resources required, S feature is the storage capacity required to run the feature, S server is the storage capacity of each server;

[0094]

[0095] Among them, R Network is the number of network resources required, N feature is the network bandwidth required to run the feature, N server is the network bandwidth of each server.

[0096] Calculate the required quantity: For each operating characteristic, calculate the required number of server resources according to the above formula. Assuming there are multiple characteristics and resource configurations, these calculations can be summarized into a comprehensive demand table.

[0097] S3. Establish an artificial intelligence model, use the artificial intelligence model to monitor the real-time operation status of service users, input the operation characteristics and the number of characteristic resource requirements into the artificial intelligence model, and grant the server resource quantity configuration management authority;

[0098] The steps for S3 are as follows:

[0099] S3.1. Access the server management system and use the artificial intelligence algorithm to establish an artificial intelligence model within the server management system, and then use the artificial intelligence model to monitor the load status of the server and the real-time operation status of the service users;

[0100] S3.2. Give the artificial intelligence model the authority to manage server configuration in the server management system, and then input the required number of server resources corresponding to each operating feature obtained in S2.2 into the artificial intelligence model. Monitor each service user through the artificial intelligence model. When the service user has the corresponding operating feature, configure the required number of server resources for the service user. The specific working steps are as follows:

[0101] Access server management system: collect server operation data, such as CPU usage, memory usage, disk I / O, network traffic, etc., and integrate the data into a central database or data warehouse for subsequent processing and analysis;

[0102] Establish an artificial intelligence model: Select a suitable AI model, such as a classification model, and extract features related to server load. The formula is as follows:

[0103]

[0104] Where P(Y=1) is the number of server resources, X i is the operating characteristic, β i is the regression coefficient;

[0105] Real-time monitoring and feedback: Use stream processing systems (such as Apache Kafka and Apache Flink) to process real-time data, input real-time data into AI models, and obtain resource requirements for the current load;

[0106] Automatically configure server resources: Automatically adjust server configuration based on model output, such as increasing or decreasing virtual machine instances, adjusting CPU and memory allocation, etc., and feed the adjustment results back to the AI ​​model for further optimization. The formula is as follows:

[0107]

[0108] Where C is the total cost, c i is the cost of each server resource, x i It is the number of resources on each server that determines the optimal allocation of resources.

[0109] By setting in the server management system that the overall server usage exceeds 80%, the overall server is determined to be in a high load state;

[0110] When the server management system is not under overall high load, the control authority priority of S3 is lower than that of S4.

[0111] When the server management system is under overall high load, the control authority of S3 takes precedence over that of S4.

[0112] S3 and S4 will trigger dynamic adjustment regulations when configuring server resources.

[0113] S4. Set buffer configuration rules in the artificial intelligence model, make load predictions based on the historical operation data of service users, and compare the server resources required for the predicted load with the server resources required for real-time operation characteristics. Then, the artificial intelligence model selects the data that occupies more server resources as the management task. The specific working steps are as follows:

[0114] Load forecasting: Use the time series forecasting model to predict future loads. The formula is as follows:

[0115] X t =μ+φ 1 X t-1 +φ 2 X t-2 +…+φ p X t-p +θ 1t-1 +θ 2t-2 +φ+θ qt-q+ t

[0116] Among them, X t is the predicted load at the current time point, μ is a constant term, indicating the average level of the data, and φ 1 ,φ 2 ,…,φ p are autoregressive parameters that control the impact of historical load values ​​on current load, θ1,θ2,…,θ q is a moving average parameter that controls the impact of past errors on the current load. t is the white noise or error term at the current time point, representing the random error between the actual load and the predicted load;

[0117] Resource demand comparison: Collect real-time server resource usage data and compare the load predicted by the AI ​​model with the real-time load using the following formula:

[0118] ΔR=R pred -R real

[0119] Where ΔR is the difference between the predicted load and the real-time load, R pred is the predicted resource demand, R real It is the real-time resource demand;

[0120] Buffer configuration rules: Set buffer configuration based on the predicted load to prevent resource shortage and determine how to allocate resources to cope with load fluctuations. The formula is as follows:

[0121] B=α×R pred +β×ΔR

[0122] Where B is the buffer size, α and β are tuning parameters, and R predis the predicted resource demand, ΔR is the load difference;

[0123] Management task selection: Evaluate the resource usage of each service user and select the tasks that use the most resources for priority management adjustment. The formula is as follows:

[0124]

[0125] Among them, S i is the priority score of task i, R i is the resource occupancy of task i, and max(R) is the maximum resource occupancy value among all tasks.

[0126] S5. Set dynamic adjustment rules in the artificial intelligence model. When configuring and adjusting server resources, obtain the operating status of the load data in the server resources, use the operating status and running memory of the load data as weights, select the server with the highest weight value for adjustable analysis, and screen out the adjustable servers for adjustment.

[0127] The steps of S5 are as follows:

[0128] S5.1. Dynamic adjustment rules are set in the artificial intelligence model. The dynamic adjustment rules are used to first obtain the number of server resources that need to be increased for the service user when configuring and adjusting server resources;

[0129] S5.2, obtain the server resources corresponding to each service user, and obtain the operating status of the load data in the server resources, and then use the operating status and memory of the load data as weights. The higher the risk factor of the operating status adjustment, the lower the weight, and the smaller the memory ratio, the higher the weight ratio. Then select the server with the highest weight value for adjustable analysis. When the server resources are adjusted, the number of server resources served by the service user can still bear the operating data generated by the service user, then the server resources are determined to be adjustable servers. Conversely, when the server resources are adjusted, the number of server resources served by the service user cannot bear the operating data generated by the service user, then the server resources are determined to be non-adjustable servers. The specific working steps are as follows:

[0130] Obtain user needs and existing resource status: determine the number of server resources that need to be added, and obtain the server resources corresponding to each service user, including their load data and operating status;

[0131] Calculate resource weight: Calculate the weight of server resources based on their load data and operating status. The higher the adjustment risk coefficient displayed by the operating status, the lower the weight; the smaller the proportion of operating memory, the higher the weight;

[0132] Selection and analysis: Select the server with the highest weight value for adjustability analysis to determine whether the adjusted server resources can withstand the operating data generated by users;

[0133] Decision: If the server resources after adjustment can meet the needs of users, it is determined to be adjustable. Otherwise, it is determined to be unadjustable. The formula is as follows:

[0134]

[0135] Where L is the current load level, R is the adjusted risk coefficient of the operating status (the value range is 0 to 1, and the higher the value, the higher the risk), M is the current server memory usage ratio (the value range is 0 to 1, and the higher the value, the greater the memory usage), and W is the weight;

[0136] The impact of load data L on weight calculation can be adjusted by comprehensively considering the relationship between load data L, operating status risk coefficient R, and operation memory ratio M. The higher the operating status risk coefficient R, the lower the weight; the larger the operation memory ratio M, the lower the weight;

[0137] After calculating the weights of all servers, select the server with the highest weight value for analysis. Assuming that the adjusted server resources can increase by ΔR (ΔR is the amount of newly added resources), calculate the adjusted load capacity A. The current server load capacity C can be expressed as:

[0138] C=AL

[0139] If C ≥ 0, the server is scalable; otherwise, it is not scalable.

[0140] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A server automatic configuration management method based on artificial intelligence, characterized in that: The following steps are involved: S1. Collect the amount of server resources that can be used for configuration optimization and determine the service users of the server; S2. Obtain historical operation data of the service user, extract load operation features from the historical operation data, and obtain the server resource demand quantity corresponding to each operation feature; S3. Establish an artificial intelligence model, use the artificial intelligence model to monitor the real-time operation status of service users, input the operation characteristics and the number of characteristic resource requirements into the artificial intelligence model, and grant the server resource quantity configuration management authority; S4. Set buffer configuration rules in the artificial intelligence model, make load predictions based on historical operation data of service users, and compare the server resources required for the predicted load with the server resources required for real-time operation characteristics. Then, the artificial intelligence model selects data that occupies more server resources as management tasks. S5. Set dynamic adjustment rules in the artificial intelligence model. When configuring and adjusting server resources, obtain the operating status of the load data in the server resources, use the operating status and running memory of the load data as weights, select the server with the highest weight value for adjustable analysis, and screen out the adjustable servers for adjustment.

2. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The steps of S1 are as follows: S1.

1. Collect and manage the number of server resources in the system and obtain the service users of each server resource; S1.

2. Extract the configuration change log of each server resource, screen the properties of the server resources according to the configuration change log, and divide the server resources into those that can be used for configuration optimization and those that are fixedly configured, thereby obtaining the number of server resources that can be used for configuration optimization and the number of server resources that are fixedly configured.

3. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The steps of S2 are as follows: S2.

1. Collect historical operation data of service users, screen the historical operation data according to load status, and then extract load operation features for each load status in combination with the historical operation data to obtain operation features representing different load statuses of service users; S2.

2. Then, the operation characteristics are combined with the server resource quantity to perform demand matching, and the server resource demand quantity corresponding to each operation characteristic is obtained.

4. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The formula of S2 is as follows: Among them, R CPU is the amount of CPU resources required, C feature is the number of CPU cores required to run the feature, C server is the number of CPU cores in each server; Among them, R Memory is the amount of memory resources required, M feature is the memory capacity required to run the feature, M server is the memory capacity of each server; Among them, R Storage is the amount of storage resources required, S feature is the storage capacity required to run the feature, S server is the storage capacity of each server; Among them, R Network is the number of network resources required, N feature is the network bandwidth required to run the feature, N server is the network bandwidth of each server.

5. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The steps of S3 are as follows: S3.

1. Access the server management system and use the artificial intelligence algorithm to establish an artificial intelligence model within the server management system, and then use the artificial intelligence model to monitor the load status of the server and the real-time operation status of the service users; S3.

2. Give the artificial intelligence model the authority to manage server configuration in the server management system, and then input the number of server resources required for each operating feature obtained in S2.2 into the artificial intelligence model. Monitor each service user through the artificial intelligence model, and when the service user shows the corresponding operating characteristics, configure the required number of server resources for the service user.

6. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The overall server is determined to be in a high load state by setting in the server management system that the overall server usage exceeds 80%; When the server management system is not under overall high load, the control authority priority of S3 is lower than that of S4. When the server management system is under overall high load, the control authority of S3 takes precedence over that of S4. S3 and S4 will trigger dynamic adjustment regulations when configuring server resources.

7. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The formula of S4 is as follows: X t =μ+φ 1 X t-1 +φ 2 X t-2 +…+φ p X t -p +θ 1t-1 +θ 2t-2 +…+θ q t -q + t Among them, X t is the predicted load at the current time point, μ is a constant term, indicating the average level of the data, and φ 1 ,φ 2 ,…,φ p are autoregressive parameters that control the impact of historical load values ​​on current load, θ1,θ2,…,θ q is a moving average parameter that controls the impact of past errors on the current load. t is the white noise or error term at the current time point, representing the random error between the actual load and the predicted load; ΔR=R pred -R real Where ΔR is the difference between the predicted load and the real-time load, R pred is the predicted resource demand, R real It is the real-time resource demand; B=α×R pred +β×ΔR Where B is the buffer size, α and β are tuning parameters, and R pred is the predicted resource demand, ΔR is the load difference; Among them, S i is the priority score of task i, R i is the resource occupancy of task i, and max(R) is the maximum resource occupancy value among all tasks.

8. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The steps of S5 are as follows: S5.

1. Dynamic adjustment rules are set in the artificial intelligence model. The dynamic adjustment rules are used to first obtain the number of server resources that need to be increased for the service user when configuring and adjusting server resources; S5.

2. Obtain the server resources corresponding to each service user, and obtain the operating status of the load data in the server resources, and then use the operating status of the load data and the memory as weights. The higher the adjustment risk coefficient of the operating status, the lower the weight, and the smaller the memory ratio, the higher the weight ratio. Then select the server with the highest weight value for adjustable analysis. After the server resources are adjusted, if the number of server resources served by the service user can still withstand the operating data generated by the service user, the server resources are determined to be adjustable servers. Conversely, after the server resources are adjusted, if the number of server resources served by the service user cannot withstand the operating data generated by the service user, the server resources are determined to be non-adjustable servers.

9. The server automatic configuration management method based on artificial intelligence according to claim 1 is characterized in that: The formula of S5 is as follows: Where L is the current load level, R is the adjusted risk factor of the operating status, M is the current server memory usage ratio, and W is the weight; C=AL Among them, A is the calculated adjusted load capacity, C is the current server load capacity, if C ≥ 0, the server is adjustable; otherwise, it is not adjustable.

Images