System performance simulation verification method based on information data analysis

Abstract

The invention discloses a system performance simulation verification method based on information data analysis, and relates to the technical field of system performance testing and simulation. The system performance simulation verification method based on information data analysis comprises the six steps of information data collection, preprocessing, simulation model construction, model calibration, performance simulation verification and result analysis, the real-time collection and historical data are combined, a high-precision simulation model is constructed, performance verification is carried out in various load scenes, and the system performance simulation verification efficiency is improved. And finally generating a verification report containing performance bottleneck diagnosis and optimization suggestions. According to the system performance simulation verification method based on information data analysis, the accuracy and comprehensiveness of system performance simulation can be effectively improved, the actual test cost is reduced, and a scientific basis is provided for system optimization.

Description

Technical Field

[0001] This invention relates to the field of system performance testing and simulation technology, specifically a system performance simulation verification method based on information data analysis. Background Technology

[0002] With the rapid development of information technology, the scale and complexity of various information systems are constantly increasing, and the requirements for system performance are also rising. System performance verification is a key link in ensuring the stable operation of the system. Traditional methods mostly rely on performance testing in real-world environments, which has problems such as high cost, long cycle, and limited scenario coverage.

[0003] Existing system performance simulation methods often suffer from the following shortcomings: incomplete data acquisition, failing to effectively combine real-time and historical data; insufficient simulation model accuracy, making it difficult to accurately reflect the actual operating state of the system; limited simulation scenarios, unable to cope with complex and ever-changing business loads; and imperfect model calibration mechanisms, leading to significant deviations between simulation results and reality. Existing technologies exhibit clear deficiencies: for example, patent CN109885678A only discloses a scheme of "combining real-time and historical data acquisition," but fails to employ edge computing for preliminary filtering of real-time data, resulting in excessive data transmission volume and low processing efficiency; while patent CN110245789B achieves multi-scenario simulation, the deviation rate after model calibration is only controlled within 10%, failing to meet the performance verification requirements of high-precision systems (such as financial trading systems and industrial control systems).

[0004] Therefore, there is a need for a method that can comprehensively utilize multi-source data to construct a high-precision simulation model and conduct comprehensive performance verification in various scenarios, so as to improve the accuracy and reliability of system performance simulation and provide a scientific basis for system optimization. Summary of the Invention

[0005] The purpose of this invention is to provide a system performance simulation and verification method based on information data analysis, so as to solve the problems of incomplete data collection, insufficient model accuracy, single scenario, and imperfect calibration mechanism in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a system performance simulation verification method based on information data analysis, comprising the following steps: S1: Information and data collection: Collect hardware resource data, business load data and system configuration data of the system to be verified. The collection method combines real-time collection and historical data import. S2: Information data preprocessing: The data collected in step S1 is subjected to data cleaning, data noise reduction, data normalization and key feature extraction in sequence to obtain key feature data; S3: Simulation Model Construction: Based on key feature data, a system performance simulation model is constructed using simulation tools, which includes a hardware resource sub-model, a business load sub-model, and a system interaction sub-model. S4: Simulation Model Calibration: By comparing the actual operating data of the system to be verified with the simulation indicators of the simulation model, adjust the model parameters until the deviation rate between the simulation indicators and the actual indicators is ≤5%; S5: Performance simulation verification: Based on the calibrated model, set up normal, burst load, and service switching scenarios, run simulations and collect performance indicators, and take the average of multiple simulation results as the final simulation result; S6: Simulation Result Analysis: Compare the final simulation results with the system performance requirements, diagnose performance bottlenecks, and generate a performance simulation verification report.

[0007] Preferably, in step S1, hardware resource data includes CPU utilization, memory usage, disk I / O rate, and network bandwidth utilization; business load data includes business request volume, request response time, and request failure rate; system configuration data includes the number of processes, thread scheduling policy, and cache size; real-time data collection is achieved through SNMP or Prometheus interface, with a sampling frequency of 1-10Hz; historical data is extracted from the Elasticsearch log database; the real-time collected data is initially filtered through edge computing nodes, and only valid data is transmitted to the data processing center to reduce data transmission volume; filtering rules: data exceeding the reasonable threshold range of hardware resources, such as invalid data with CPU utilization > 100% and memory usage < 0%.

[0008] Preferably, in step S2, data cleaning uses the 3σ principle or box plot method to remove outliers, and linear interpolation or mean is used to fill missing values; data denoising uses wavelet transform or moving average; data normalization uses the Min-Max algorithm; and key feature extraction uses principal component analysis or random forest algorithm.

[0009] Preferably, in step S3, the simulation tools include NS-3, MATLAB / Simulink, or OPNET; the hardware resource sub-model simulates CPU scheduling, memory allocation, disk I / O, and network transmission; the service load sub-model supports custom load intensity; and the system interaction sub-model defines the interaction rules between hardware and services.

[0010] Preferably, in step S4, the actual running data is collected by performing a performance test with the same configuration on the system to be verified; the adjusted model parameters include CPU scheduling latency, memory access time, and request generation interval.

[0011] Preferably, in step S5, the number of business requests in the sudden load scenario increases by 10-20 times; performance indicators include average response time, maximum response time, throughput per unit time, average utilization of CPU / memory / disk / network, and request success rate; the simulation is executed 3-5 times.

[0012] Preferably, in step S6, the performance simulation verification report includes simulation scenario settings, performance index details, requirement comparison analysis, bottleneck diagnosis results, and system optimization suggestions.

[0013] Preferably, in step S1, the real-time collected data is initially filtered by edge computing nodes, and only valid data is transmitted to the data processing center to reduce the amount of data transmitted.

[0014] Preferably, the simulation model constructed in step S3 supports dynamic adjustment. During the simulation, the sub-model parameters can be updated based on real-time supplementary data to adapt to dynamic changes in business scenarios.

[0015] The technical effects and advantages of this invention are as follows: 1. This system performance simulation verification method based on information data analysis adopts a combination of real-time acquisition and historical data import to comprehensively collect various types of data from system operation, providing a data foundation for building a high-precision simulation model; 2. This system performance simulation verification method based on information data analysis uses edge computing nodes to perform preliminary filtering of real-time data, reducing data transmission volume and improving data processing efficiency. 3. The system performance simulation verification method based on information data analysis performs multi-step preprocessing on the collected data, which effectively improves data quality, extracts key features, and reduces model complexity. 4. This system performance simulation verification method based on information data analysis constructs a system performance simulation model containing multiple sub-models and supports dynamic adjustment, which can adapt to the dynamic changes in business scenarios. 5. This system performance simulation verification method based on information data analysis ensures that the deviation rate between simulation indicators and actual indicators is ≤5% through model calibration steps, thereby improving simulation accuracy. 6. This system performance simulation and verification method based on information data analysis performs performance simulation and verification under various load scenarios to comprehensively evaluate system performance; 7. This system performance simulation verification method based on information data analysis generates a verification report containing performance bottleneck diagnosis and optimization suggestions, providing a scientific basis for system optimization. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the data acquisition and preprocessing process of the present invention; Figure 2 This is a flowchart illustrating the simulation model construction module and model calibration module of the present invention; Figure 3 This is a flowchart illustrating the "performance simulation verification module" and "result analysis and report generation management module" of this invention. Figure 4 This is a flowchart illustrating the result analysis and report generation management module of this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] This invention discloses a system performance simulation verification method based on information data analysis.

[0020] Example 1: According to the appendix Figures 1 to 4 As shown, it includes the following steps: S1: Information Data Acquisition: Hardware resource data (including CPU utilization, memory usage, disk I / O speed, and network bandwidth utilization) and business load data (including order request volume, payment response time, and request failure rate) of an e-commerce platform's server are collected in real-time via an SNMP interface, with a sampling frequency of 5Hz. Simultaneously, historical data from the past three months, including system configuration data (number of processes, thread scheduling strategy, and cache size), is imported from the Elasticsearch log database. The real-time collected data is first filtered by edge computing nodes to remove invalid data (such as outliers significantly exceeding reasonable limits) before being transmitted to the data processing center. This combination of real-time acquisition and historical data import comprehensively collects various types of data from system operation, providing a data foundation for building high-precision simulation models; the initial filtering of real-time data by edge computing nodes reduces data transmission volume and improves data processing efficiency.

[0021] S2: Information Data Preprocessing: Outliers in data such as CPU utilization and memory usage are removed using the 3σ principle; missing order request volume data is filled using linear interpolation; noise reduction of payment response time data is performed using the moving average method; all data are normalized to the [0,1] interval using the Min-Max algorithm; key features are extracted from the processed data using principal component analysis to obtain key feature data. Multi-step preprocessing of the collected data effectively improves data quality, extracts key features, and reduces model complexity.

[0022] S3: Simulation Model Construction: Based on key feature data, a system performance simulation model is constructed using the NS-3 simulation tool. This model includes: Hardware resource sub-model: Simulates server CPU scheduling, memory allocation, disk I / O, and network transmission processes; Business load sub-model: Supports custom load intensity such as order request volume; System interaction sub-model: Defines the interaction rules between hardware resources and order processing business.

[0023] This simulation model supports dynamic adjustment, allowing sub-model parameters to be updated based on real-time supplementary user access data during the simulation process. A system performance simulation model containing multiple sub-models is constructed, supporting dynamic adjustment to adapt to dynamic changes in business scenarios.

[0024] S4: Simulation Model Calibration: Perform performance tests with the same configuration as the simulation model on the e-commerce platform server to be verified, and collect actual running data. Compare the simulation metrics (such as average response time and CPU utilization) of the simulation model with the actual running data, and adjust model parameters such as CPU scheduling latency, memory access time, and order request generation interval until the deviation rate between the simulation metrics and the actual metrics is ≤5%. Through the model calibration step, ensure that the deviation rate between the simulation metrics and the actual metrics is ≤5%, and improve the simulation accuracy.

[0025] S5: Performance Simulation Verification Three scenarios are set up based on the calibrated model: Typical scenario: Order request volume is at the average level of a normal working day; Sudden load scenario: Order request volume surges by 15 times (simulating a promotional event); Business switching scenario: Switching from order processing business to product recommendation business.

[0026] The simulation was run four times for each scenario, and performance metrics such as average response time, maximum response time, throughput per unit time, average utilization of CPU / memory / disk / network, and request success rate were collected. The average of the four simulation results was taken as the final simulation result. Performance simulations were performed under various load scenarios to comprehensively evaluate the system performance.

[0027] S6: Simulation Result Analysis: Comparing the final simulation results with the performance requirements of the e-commerce platform, it was found that the system's network bandwidth utilization reached 95% under sudden load scenarios, becoming a performance bottleneck. A performance simulation verification report was generated, including setting details for the three scenarios, specific values ​​for each performance indicator, comparative analysis with the required indicators, diagnostic results of the network bandwidth bottleneck, and optimization suggestions for increasing network bandwidth. A verification report containing performance bottleneck diagnosis and optimization suggestions was generated, providing a scientific basis for system optimization.

[0028] By combining real-time data acquisition with historical data import, comprehensive data collection of various types of system operation data is achieved, providing a data foundation for building a high-precision simulation model. Real-time data is initially filtered through edge computing nodes to reduce data transmission volume and improve data processing efficiency. Multi-step preprocessing of the collected data effectively improves data quality, extracts key features, and reduces model complexity. A system performance simulation model containing multiple sub-models is constructed and supports dynamic adjustment to adapt to dynamic changes in business scenarios. Model calibration steps ensure that the deviation rate between simulation and actual indicators is ≤5%, improving simulation accuracy. Performance simulation verification is conducted under various load scenarios to comprehensively evaluate system performance. A verification report containing performance bottleneck diagnosis and optimization suggestions is generated, providing a scientific basis for system optimization.

[0029] Example 2: A system for implementing the above method, according to the appendix Figures 1 to 4 As shown, it includes: Data acquisition module: Collects server hardware resource data and business load data in real time through SNMP interface, imports historical data from Elasticsearch log database, and performs preliminary filtering of real-time data in edge computing node units; Data preprocessing module: The collected data is cleaned sequentially (outliers are removed by the 3σ principle and missing values ​​are filled by linear interpolation), denoising is performed (moving average method), data normalization is performed (Min-Max algorithm), and key feature extraction is performed (principal component analysis method). Simulation model construction module: The NS-3 simulation tool is used to build a system performance simulation model that includes hardware resource sub-model, business load sub-model and system interaction sub-model, and supports dynamic adjustment of model parameters based on real-time supplementary data; Model calibration module: Compares simulation metrics with actual operating data of the system under test, and adjusts parameters such as CPU scheduling latency until the deviation rate is ≤5%; Performance simulation verification module: Set up three scenarios: normal, burst load, and service switching. Run the simulation 4 times for each scenario, collect performance indicators and take the average value. Results analysis and report generation module: Compare simulation results with performance requirements, diagnose network bandwidth bottlenecks, and generate a verification report containing optimization suggestions.

[0030] By combining real-time data acquisition with historical data import, comprehensive data collection of various types of system operation data is achieved, providing a data foundation for building a high-precision simulation model. Real-time data is initially filtered through edge computing nodes to reduce data transmission volume and improve data processing efficiency. Multi-step preprocessing of the collected data effectively improves data quality, extracts key features, and reduces model complexity. A system performance simulation model containing multiple sub-models is constructed and supports dynamic adjustment to adapt to dynamic changes in business scenarios. Model calibration steps ensure that the deviation rate between simulation and actual indicators is ≤5%, improving simulation accuracy. Performance simulation verification is conducted under various load scenarios to comprehensively evaluate system performance. A verification report containing performance bottleneck diagnosis and optimization suggestions is generated, providing a scientific basis for system optimization.

[0031] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0032] The foregoing has shown and described 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 to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A system performance simulation verification method based on information data analysis, characterized in that, Includes the following steps: S1: Information and data collection: Collect hardware resource data, business load data and system configuration data of the system to be verified. The collection method combines real-time collection and historical data import. S2: Information data preprocessing: The data collected in step S1 is subjected to data cleaning, data noise reduction, data normalization and key feature extraction in sequence to obtain key feature data; S3: Simulation Model Construction: Based on key feature data, a system performance simulation model is constructed using simulation tools, which includes a hardware resource sub-model, a business load sub-model, and a system interaction sub-model. S4: Simulation Model Calibration: By comparing the actual operating data of the system to be verified with the simulation indicators of the simulation model, adjust the model parameters until the deviation rate between the simulation indicators and the actual indicators is ≤5%; S5: Performance simulation verification: Based on the calibrated model, set up normal, burst load, and service switching scenarios, run simulations and collect performance indicators, and take the average of multiple simulation results as the final simulation result; S6: Simulation Result Analysis: Compare the final simulation results with the system performance requirements, diagnose performance bottlenecks, and generate a performance simulation verification report.

2. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, In step S1, hardware resource data includes CPU utilization, memory usage, disk I / O rate, and network bandwidth utilization; business load data includes business request volume, request response time, and request failure rate; system configuration data includes the number of processes, thread scheduling policy, and cache size; real-time data collection is achieved through SNMP or Prometheus interface, with a sampling frequency of 1-10Hz; historical data is extracted from the Elasticsearch log database; the real-time collected data is initially filtered through edge computing nodes, transmitting only valid data to the data processing center to reduce data transmission volume; filtering rules: data exceeding the reasonable threshold range of hardware resources, such as invalid data with CPU utilization > 100% and memory usage < 0%.

3. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, In step S2, outliers are removed by the 3σ principle or box plot method for data cleaning, and missing values ​​are filled by linear interpolation or mean; wavelet transform or moving average method is used for data denoising; and Min-Max algorithm is used for data normalization. Key feature extraction employs either principal component analysis or random forest algorithms.

4. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, In step S3, the simulation tools include NS-3, MATLAB / Simulink, or OPNET; the hardware resource sub-model simulates CPU scheduling, memory allocation, disk I / O, and network transmission; the service load sub-model supports custom load intensity; and the system interaction sub-model defines the interaction rules between hardware and services.

5. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, In step S4, the actual running data is collected by performing a performance test with the same configuration on the system to be verified; the adjusted model parameters include CPU scheduling latency, memory access time and request generation interval.

6. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, In step S5, the number of business requests in the sudden load scenario increases by 10-20 times; performance indicators include average response time, maximum response time, throughput per unit time, average utilization of CPU / memory / disk / network, and request success rate; the simulation is executed 3-5 times.

7. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, In step S6, the performance simulation verification report includes simulation scenario settings, performance index details, requirement comparison analysis, bottleneck diagnosis results, and system optimization suggestions.

8. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, In step S1, the real-time collected data is initially filtered by edge computing nodes, and only valid data is transmitted to the data processing center to reduce the amount of data transmitted.

9. The system performance simulation verification method based on information data analysis according to claim 1, characterized in that, The simulation model constructed in step S3 supports dynamic adjustment. During the simulation, the parameters of the sub-model can be updated based on real-time supplementary data to adapt to dynamic changes in the business scenario.

Images