Intelligent data center infrastructure performance evaluation method and system

Abstract

The invention provides an intelligent data center infrastructure performance evaluation method and system. The method comprises the following steps: acquiring real-time operation data of a data center infrastructure; constructing a multi-level performance index system according to the real-time operation data, and dynamically adjusting a performance evaluation model according to the multi-level performance index system; calculating a comprehensive performance index of the data center infrastructure by using the multi-level performance index system; and performing performance evaluation on the operation quality of the data center infrastructure based on the comprehensive performance index and the acquired service level protocol requirement, and providing an improvement measure corresponding to a performance evaluation result. According to the technical scheme provided by the invention, comprehensive and accurate evaluation of the operation quality of the infrastructure of the data center can be realized, a scientific basis is provided for continuous optimization, and the management level and the technical efficiency of the data center are effectively improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of performance evaluation technology, and in particular, to a method and system for evaluating the performance of an intelligent data center infrastructure. Background Art

[0002] With the rapid development of information technology, data centers, as one of the core infrastructures of the information society, are becoming increasingly important. Data centers not only carry a large amount of data storage, processing and transmission tasks, but also need to maintain high availability and high performance. Therefore, real-time monitoring and performance evaluation of data center infrastructure has become particularly critical. In order to meet this demand, a technical solution is needed that can obtain data center infrastructure operation data in real time, build a multi-level performance indicator system based on these data, dynamically adjust the performance evaluation model, calculate the comprehensive performance index, and perform performance evaluation based on the index and service level agreement (SLA) requirements. The technical solution must also be able to provide specific improvement measures to guide the data center to continuously optimize its operation quality.

[0003] At present, data centers generally adopt performance evaluation methods based on fixed rules. These methods usually rely on pre-set performance indicators to monitor the operating status of data centers and perform performance evaluations regularly or on demand. However, such methods have certain limitations in practical applications, especially when faced with the growing complexity and dynamic changes of data centers.

[0004] The defects of the existing solutions are: Lack of dynamic adjustment capabilities: Existing performance evaluation methods often rely on statically set performance indicator systems, which are difficult to adapt to the frequent changes in the operating status of data center infrastructure. Fixed evaluation models cannot reflect changes in actual operating conditions in a timely manner, resulting in inaccurate evaluation results.

[0005] Evaluation models are not smart enough: Existing performance evaluation models usually do not have the ability to self-learn and cannot be optimized and adjusted based on historical data. This makes the model inflexible when facing new operating conditions and difficult to make accurate evaluations.

[0006] Improvement measures are not specific enough: Even if existing assessment methods can point out problems in data centers, they often lack targeted and feasible improvement measures, resulting in difficulty in effectively solving problems even if problems are discovered, thus affecting the operating quality and user experience of the data center. Summary of the invention

[0007] The embodiments of the present application provide an intelligent data center infrastructure performance evaluation method and system to solve the problems in the prior art of lack of dynamic adjustment capability, insufficient intelligence of the evaluation model, and insufficient specificity of the improvement measures.

[0008] In a first aspect, an embodiment of the present application provides a method for evaluating the performance of an intelligent data center infrastructure, including: Get real-time operational data of data center infrastructure; Constructing a multi-level performance indicator system according to the real-time operation data, and dynamically adjusting a performance evaluation model according to the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operation data of the data center infrastructure and the corresponding performance evaluation results; Using the multi-level performance indicator system, calculating a comprehensive performance index of the data center infrastructure; Based on the comprehensive performance index and the obtained service level agreement requirements, a performance evaluation is performed on the operation quality of the data center infrastructure, and improvement measures corresponding to the performance evaluation results are provided.

[0009] Optionally, constructing a multi-level performance indicator system according to the real-time operation data, and dynamically adjusting a performance evaluation model according to the multi-level performance indicator system includes: Define a multi-level performance indicator system, construct different levels of performance indicators from the device level, system level to the overall level, the performance indicators include hardware health, device communication network delay, energy efficiency, service availability, and each performance indicator has a corresponding weight and threshold; Using the historical operation data of the data center infrastructure and the corresponding performance evaluation results, training a machine learning model to form an initial performance evaluation model, wherein the initial performance evaluation model is used to perform performance evaluation on the data center infrastructure according to the multi-level performance indicator system; The multi-level performance indicator system is dynamically updated according to the real-time operation data, and the parameter settings in the performance evaluation model are adjusted according to the updated multi-level performance indicator system to ensure that the performance evaluation model can accurately reflect the current operation status of the data center infrastructure.

[0010] Optionally, using the multi-level performance indicator system to calculate a comprehensive performance index of the data center infrastructure includes: Designing a corresponding scoring algorithm for the performance indicators, wherein the scoring algorithm is determined according to a nonlinear relationship, a synergistic effect, and a time dependency among the plurality of performance indicators; Calculate the score of each performance indicator based on the scoring algorithm corresponding to the performance indicator; The scores of performance indicators at different levels are aggregated to obtain a comprehensive performance index of the data center infrastructure.

[0011] Optionally, the performing performance evaluation on the operation quality of the data center infrastructure based on the comprehensive performance index and the obtained service level agreement requirements includes: According to the service level agreement requirements of the data center infrastructure, a mapping relationship between the comprehensive performance index and the service level agreement standard is established; Based on the mapping relationship, the comprehensive performance index is compared with the service level agreement standard to evaluate whether the data center infrastructure meets the predetermined service level requirements, so as to achieve performance evaluation of the operation quality of the data center infrastructure.

[0012] Optionally, calculating the score of each performance indicator based on a scoring algorithm corresponding to the performance indicator includes: calculating the score of each performance indicator by the following formula: ; in, represents the score of the i-th performance indicator at time t; is the actual measured value of the i-th performance indicator at time t; is the ideal target value of the i-th performance indicator; is the adjustment factor, which is used to control the steepness of the scoring function and the importance of different influencing factors; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t in the past period of time; n is the total number of performance indicators, refers to the jth performance indicator at time (i.e., the integrating variable).

[0013] Optionally, the scores of performance indicators at different levels are aggregated to obtain a comprehensive performance index of the data center infrastructure: The comprehensive performance index of the data center infrastructure is calculated by the following formula: ; in, represents the comprehensive performance index of the data center infrastructure at time t; The base value is the basic level of the comprehensive performance index when the scores of all performance indicators are zero. represents the regression coefficient of the i-th performance indicator at time t, represents the score of the i-th performance indicator at time t, represents the interaction coefficient between the i-th performance indicator and the j-th performance indicator at time t, represents the coefficient related to the rate of change of performance index at time t, represents the weight of the score change rate of the i-th performance indicator at time t, is the score of the jth performance indicator at time t; represents the rate of change of the score of the i-th performance indicator at time t; is the error term at time t.

[0014] Optionally, after the mapping relationship between the comprehensive performance index and the service level agreement standard is established, the method further includes: Analyzing the gap between the comprehensive performance index and the service level agreement standard to adjust the mapping relationship; The gap between the comprehensive performance index and the service level agreement standard is calculated by the following formula: ; in, It represents the gap between the comprehensive performance index and the service level agreement standard at time t; is the comprehensive performance index of the data center infrastructure at time t; is the standard score specified in the service level agreement at time t; is the adjustment factor, which is used to control the influence of deviation on the total gap at time t; is the weight coefficient of the impact of the i-th performance indicator on the total gap at time t; is the score of the i-th performance indicator at time t; is the i-th performance indicator at time score; is the ideal score of the i-th performance indicator at time t; is the i-th performance indicator at time ideal score.

[0015] In a second aspect, an embodiment of the present application provides an intelligent data center infrastructure performance evaluation system, including: An acquisition module is used to obtain real-time operation data of the data center infrastructure; An adjustment module, configured to construct a multi-level performance indicator system according to the real-time operation data, and dynamically adjust a performance evaluation model according to the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operation data of the data center infrastructure and the corresponding performance evaluation results; A calculation module, for calculating a comprehensive performance index of the data center infrastructure using the multi-level performance indicator system; The evaluation module is used to perform a performance evaluation on the operation quality of the data center infrastructure based on the comprehensive performance index and the obtained service level agreement requirements, and provide improvement measures corresponding to the performance evaluation results.

[0016] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent data center infrastructure performance evaluation method as described in the first aspect.

[0017] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements an intelligent data center infrastructure performance evaluation method as described in the first aspect.

[0018] In an embodiment of the present application, real-time operation data of the data center infrastructure is obtained; a multi-level performance indicator system is constructed based on the real-time operation data, and a performance evaluation model is dynamically adjusted based on the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operation data of the data center infrastructure and the corresponding performance evaluation results; the comprehensive performance index of the data center infrastructure is calculated using the multi-level performance indicator system; based on the comprehensive performance index and the obtained service level agreement requirements, the operation quality of the data center infrastructure is performance evaluated, and improvement measures corresponding to the performance evaluation results are provided. The technical solution provided by the present application realizes a comprehensive and accurate evaluation of the operation quality of the data center infrastructure, and provides a scientific basis for continuous optimization, effectively improving the management level and technical efficiency of the data center.

[0019] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of an intelligent data center infrastructure performance evaluation method provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an intelligent data center infrastructure performance evaluation system provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0023] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0025] Figure 1 A flowchart of a method for evaluating the performance of an intelligent data center infrastructure is provided for an embodiment of the present application. Figure 1 As shown, the method includes: 101. Obtain real-time operating data of data center infrastructure; In this step, obtaining the real-time operation data of the data center infrastructure means collecting the current operation status information of various devices and systems in the data center through various monitoring means. This operation status information includes but is not limited to infrastructure energy consumption, energy efficiency, operation vibration / noise, input / output harmonics, cumulative operation time, operation frequency, UPS, diesel generator sets, chillers, precision air conditioners and other equipment utilization, redundancy, function, performance, and other indicators. The purpose of obtaining this data is to subsequently build a multi-level performance indicator system and perform performance evaluation based on this data.

[0026] In the embodiments of the present application, real-time operation data of the data center infrastructure may be obtained in a variety of ways, for example, sensor networks, network management systems, and software monitoring tools may be used to collect different types of data.

[0027] Specifically, different components can be set in the data center infrastructure to complete the process of acquiring real-time operation data through the setting of different components. For example, the following components are set according to the data center infrastructure performance evaluation conditions: collection detection tools, detection basis, detection method, indicator requirements and detection items.

[0028] Specifically, this involves the following aspects: Detection tools: Choose appropriate hardware and software tools to monitor various aspects of the data center. Hardware tools can be sensors installed on the server to measure physical parameters such as temperature and voltage; software tools can be monitoring software running on the server to monitor the performance of high and low voltage power distribution systems, UPS systems, diesel generator systems, precision air conditioning systems, etc.

[0029] Testing Basis: Clarify the standards and specifications for performance evaluation to ensure that all testing activities have a basis. These bases can be industry standards, internal corporate regulations, or best practice guidelines.

[0030] Detection method: defines how to perform the detection task, including the detection frequency, method, and data recording method. For example, you can set the performance data collection frequency to once every five minutes, or trigger a specific detection process under certain conditions.

[0031] Index requirements: Set thresholds and targets for performance indicators to ensure that the collected data can reflect the actual operating status of the data center. These indicators may include but are not limited to the utilization, redundancy, function, and performance of UPS, diesel generator sets, chillers, precision air conditioners, and other equipment.

[0032] Test items: Develop a specific list of test items to ensure that all important performance parameters are covered. These items may include environmental monitoring (such as temperature, humidity), hardware monitoring (such as test instruments), network monitoring (such as intelligent systems), etc.

[0033] The above component design ensures that the acquired data is both comprehensive and accurate, providing a reliable foundation for the subsequent multi-level performance indicator system construction and performance evaluation. The purpose of this is to better understand the operating status of the data center infrastructure and make optimization decisions accordingly to achieve the goal of reducing costs and increasing efficiency.

[0034] Here are some examples of getting real-time operational data: Embodiment 1: Collecting the working status information of hardware devices through a sensor network.

[0035] Various sensors (such as temperature sensors, current sensors, fan speed sensors, etc.) are deployed inside the data center, and the data from these sensors is acquired in real time through the data acquisition system (DAS). For example, suppose that 100 precision air conditioners are deployed inside the data center, and each precision air conditioner is equipped with a temperature sensor, a current sensor, and a fan speed sensor. Every 5 minutes, the data acquisition system will record the data from these sensors and store it in the central database. Assume that at a certain moment, the system records that the temperature of a precision air conditioner is 30 degrees Celsius, the current consumption is 10 amps, and the fan speed is 2000 rpm.

[0036] Embodiment 2: Collecting traffic statistics information of network devices through a network management system.

[0037] Use the Network Management System (NMS) to collect traffic statistics (such as voltage, current, frequency, fan speed, etc.) of switches, routers and other network devices in the data center. NMS can monitor port traffic, packet loss rate, latency and other information of these devices. For example, suppose there is a core switch in the data center, and NMS records the port traffic information of the switch every 10 minutes. At a certain moment, the system records that the inbound traffic of a port of the core switch is 100Mbps, the outbound traffic is 95Mbps, the packet loss rate is 0.5%, and the average latency is 1 millisecond.

[0038] Embodiment 3: Collecting the operation status information of the business system through application performance management tools.

[0039] Application Performance Management (APM) tools can monitor the performance of applications running inside a data center. APM tools can collect indicators such as application response time, transaction success rate, and error rate. For example, a critical business system is running inside a data center, and the APM tool collects performance data of the system every 5 minutes.

[0040] Through the above three examples, it can be seen that the process of obtaining real-time operation data of data center infrastructure involves various types of data sources and technical means. These data provide a basis for the subsequent construction of a multi-level performance indicator system and lay the foundation for further performance evaluation and optimization.

[0041] 102. Construct a multi-level performance indicator system according to the real-time operation data, and dynamically adjust a performance evaluation model according to the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operation data of the data center infrastructure and the corresponding performance evaluation results; Optionally, in step 102, “constructing a multi-level performance indicator system according to the real-time operation data, and dynamically adjusting a performance evaluation model according to the multi-level performance indicator system” includes: Define a multi-level performance indicator system, construct different levels of performance indicators from the device level, system level to the overall level, the performance indicators include hardware health, device communication network delay, energy efficiency, service availability, and each performance indicator has a corresponding weight and threshold; Using the historical operation data of the data center infrastructure and the corresponding performance evaluation results, training a machine learning model to form an initial performance evaluation model, wherein the initial performance evaluation model is used to perform performance evaluation on the data center infrastructure according to the multi-level performance indicator system; The multi-level performance indicator system is dynamically updated according to the real-time operation data, and the parameter settings in the performance evaluation model are adjusted according to the updated multi-level performance indicator system to ensure that the performance evaluation model can accurately reflect the current operation status of the data center infrastructure.

[0042] In this step, a multi-level performance indicator system is constructed based on the real-time operation data of the data center infrastructure, and the performance evaluation model is dynamically adjusted based on the system. The multi-level performance indicator system refers to dividing the operation performance of the data center infrastructure into different levels, and the performance indicators of each level reflect the key performance characteristics of a certain aspect of the data center. For example, the first level can be basic performance indicators, such as infrastructure energy consumption, energy efficiency, operation vibration / noise, input / output harmonics, cumulative operation time, operation frequency and other indicators; the second level can be intermediate performance indicators, such as equipment communication network delay, storage throughput, etc.; the third level can be high-level performance indicators, such as energy efficiency ratio, operation and maintenance efficiency, etc. The performance evaluation model is based on these multi-level performance indicator systems, combined with the historical operation data of the data center infrastructure and the corresponding performance evaluation results. It is a model for evaluating the operation quality of the data center. The model can be dynamically adjusted according to the current real-time operation data to ensure that the evaluation results are more accurate and timely.

[0043] In the embodiment of the present application, the process of constructing a multi-level performance indicator system and dynamically adjusting the performance evaluation model according to the system can be divided into the following steps: Example: Constructing a multi-level performance indicator system and dynamically adjusting the performance evaluation model: Define a multi-level performance indicator system: Basic performance indicators: for example, infrastructure energy consumption, energy efficiency, operating vibration / noise, input / output harmonics, cumulative operating time, operating frequency and other indicators.

[0044] Intermediate performance indicators: For example, device communication network latency, storage throughput, virtual machine migration success rate, etc. These indicators further refine the operating status of the data center.

[0045] High-level performance indicators: For example, energy efficiency ratio, operation and maintenance efficiency, fault recovery time, etc. These indicators provide a higher level of performance evaluation.

[0046] Collect historical operation data and performance evaluation results: Collect the operation data of the data center over the past period of time, including but not limited to the various performance indicators mentioned above. At the same time, collect historical performance evaluation results as the basic data for training the performance evaluation model.

[0047] Training performance evaluation model: Use historical operation data and corresponding performance evaluation results to train a performance evaluation model. Machine learning methods such as support vector machine (SVM), neural network (NN), etc. can be used. The goal of model training is to learn the patterns in historical data and be able to predict the comprehensive performance index of the data center based on the current real-time operation data.

[0048] Construct a multi-level performance indicator system: Calculate the score of each performance indicator based on real-time operation data. Aggregate these scores in a hierarchical structure to form a multi-level performance indicator system. Dynamically adjust the performance evaluation model. When the real-time operation data changes, dynamically adjust the performance evaluation model based on the new data. For example, if a sudden increase in device communication network latency is detected, the model may need to re-evaluate the network-related performance indicator weights. Continue to train the model using the latest data to ensure that the model can adapt to the current operating status of the data center.

[0049] Calculate the comprehensive performance index The dynamically adjusted performance evaluation model is used to calculate the comprehensive performance index of the data center. The index combines the performance index scores of all levels and reflects the overall operation quality of the data center.

[0050] Example calculation: Suppose there is a data center whose multi-level performance indicator system includes the following indicators: Basic performance indicators: infrastructure energy consumption, energy efficiency, operation vibration / noise, input / output harmonics, cumulative operating time, operating frequency, etc. Intermediate performance indicators: equipment communication network delay, storage throughput. High-level performance indicators: energy efficiency ratio, operation and maintenance efficiency.

[0051] The historical operation data of the data center for the past month was collected, and a performance evaluation model was trained based on this data.

[0052] Based on this data, the trained model is used to calculate the comprehensive performance index. Assume that the output of the model is a value between 0 and 1, which represents the comprehensive performance score of the data center. If the output is 0.85, it means that the data center is currently running well and the comprehensive performance score is 85%.

[0053] Through the above examples, we can see how to build a multi-level performance indicator system based on real-time operation data, and dynamically adjust the performance evaluation model based on the system, and finally calculate the comprehensive performance index of the data center infrastructure. This method can not only reflect the operation status of the data center in real time, but also adapt to the changing environment by dynamically adjusting the model, thereby improving the accuracy and effectiveness of the evaluation.

[0054] 103. Calculate a comprehensive performance index of the data center infrastructure using the multi-level performance indicator system; Optionally, "using the multi-level performance indicator system to calculate the comprehensive performance index of the data center infrastructure" in step 103 includes: designing a corresponding scoring algorithm for the performance indicator, the scoring algorithm being determined according to the nonlinear relationship, synergy and time dependence among the multiple performance indicators; calculating the score of each performance indicator based on the scoring algorithm corresponding to the performance indicator; and summarizing the scores of performance indicators at different levels to obtain the comprehensive performance index of the data center infrastructure.

[0055] Optionally, calculating the score of each performance indicator based on a scoring algorithm corresponding to the performance indicator includes: calculating the score of each performance indicator by the following formula: ; in, represents the score of the i-th performance indicator at time t; is the actual measured value of the i-th performance indicator at time t; is the ideal target value of the i-th performance indicator; is the adjustment factor, which is used to control the steepness of the scoring function and the importance of different influencing factors; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t in the past period of time; n is the total number of performance indicators, refers to the jth performance indicator at time (i.e., the integrating variable).

[0056] In this step, the comprehensive performance index of the data center infrastructure is calculated using the multi-level performance index system constructed previously. The comprehensive performance index is a comprehensive score that reflects the overall operational quality of the data center infrastructure. The process of calculating the comprehensive performance index involves weighted aggregation of the scores of each indicator in the multi-level performance index system, and taking into account the possible mutual influence between different indicators.

[0057] Explain the concepts involved in the above steps: Multi-level performance indicator system: The multi-level performance indicator system includes performance indicators at different levels, from equipment level, system level to overall level. The performance indicators at each level reflect the operating status of the data center infrastructure at different abstract levels.

[0058] Comprehensive performance index: The comprehensive performance index is a comprehensive score obtained by weighted aggregation of the scores of each indicator in the multi-level performance indicator system, which is used to evaluate the overall operation quality of the data center infrastructure.

[0059] Weighted summary: When calculating the comprehensive performance index, the score of each performance indicator needs to be weighted, and the weight reflects the importance of the indicator in the entire evaluation system. In addition, the mutual influence between different indicators needs to be considered to ensure that the comprehensive performance index can fully reflect the actual operation of the data center.

[0060] Scoring algorithm: A scoring algorithm is a mathematical model that is used to calculate a score (here, the performance indicator score) based on a set of input variables (here, performance indicators). The design of the scoring algorithm needs to take into account the interaction between indicators and the temporal dependencies in order to more accurately reflect the actual operating status of the data center.

[0061] Non-linear relationships: In the scoring algorithm, there may be non-linear relationships between different performance indicators, which means that the impact of changes in one indicator on another indicator is not constant, but changes as the value changes. For example, as the energy consumption of the infrastructure increases, the device communication network latency may increase non-linearly.

[0062] Synergy: Synergy refers to the mutual promotion or inhibition between multiple performance indicators. For example, an increase in memory usage may lead to an increase in infrastructure energy consumption because more data needs to be processed.

[0063] In the embodiment of the present application, a multi-level performance index system is used to calculate the comprehensive performance index to define multi-level performance indicators and their weights: Equipment-level performance indicators: infrastructure energy consumption: weight 0.3, infrastructure energy efficiency: weight 0.2, operating frequency: weight 0.1; System-level performance indicators: device communication network latency: weight 0.2, storage throughput: weight 0.1 Overall performance indicators: Energy efficiency: weight 0.05, service availability: weight 0.05 Collect real-time operation data: Obtain real-time operating data of data center infrastructure, including but not limited to the various performance indicators mentioned above. For example: Infrastructure energy consumption: 80%, infrastructure energy efficiency: 70%, operation frequency: 100 times per second, device communication network delay: average 10 milliseconds, storage throughput: 100MB per second, energy efficiency: 1.5W / W, service availability: 95%; Calculate the score for each performance metric: The score of each performance indicator is calculated based on the actual measured value and the ideal target value of each performance indicator. For example, the score can be calculated using the logistic function (sigmoid function): ; in, represents the score of the i-th performance indicator at time t; is the actual measured value of the i-th performance indicator at time t; is the ideal target value of the i-th performance indicator; is the adjustment factor, which is used to control the steepness of the scoring function and the importance of different influencing factors; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t in the past period of time; n is the total number of performance indicators, refers to the jth performance indicator at time (i.e., the integrating variable).

[0064] Calculate the overall performance index: The comprehensive performance index is calculated using a weighted aggregation method.

[0065] Time Dependency: Some performance indicators may show different characteristics over time. For example, the performance of the same indicator may be completely different during peak and off-peak hours. The scoring algorithm needs to take these changes over time into account in order to more accurately assess the operating status of the data center.

[0066] Optionally, the scores of performance indicators at different levels are aggregated to obtain a comprehensive performance index of the data center infrastructure: The comprehensive performance index of the data center infrastructure is calculated by the following formula: ; in, represents the comprehensive performance index of the data center infrastructure at time t; The base value is the basic level of the comprehensive performance index when the scores of all performance indicators are zero. represents the regression coefficient of the i-th performance indicator at time t, represents the score of the i-th performance indicator at time t, represents the interaction coefficient between the i-th performance indicator and the j-th performance indicator at time t, represents the coefficient related to the rate of change of performance index at time t, represents the weight of the score change rate of the i-th performance indicator at time t, is the score of the jth performance indicator at time t; represents the rate of change of the score of the i-th performance indicator at time t; is the error term at time t.

[0067] In this step, the concepts involved in the above steps are explained: Comprehensive performance index: comprehensive performance index ( ) is a comprehensive score that reflects the overall operational quality of the data center infrastructure at a specific point in time t. The index is calculated by integrating the scores of multiple performance indicators and taking into account the interactions and rates of change between them.

[0068] Base Value : Basic value It represents the base value of the comprehensive performance index even when all other performance indicators have a score of zero. It provides a benchmark point, even without the contribution of other indicators, the data center has a basic operating level.

[0069] Regression coefficients: are regression coefficients used to adjust the impact of different performance indicators on the overall performance index. These coefficients can change over time to better adapt to changes in the operating status of the data center infrastructure.

[0070] Performance index score: It represents the score of the i-th performance indicator at time t, reflecting the performance of the indicator at a specific point in time.

[0071] Interactions between performance indicators: Indicates performance index and the jth performance index at time The interaction weight is the degree of mutual influence between two indicators.

[0072] Score change rate: It represents the rate of change of the i-th performance indicator score, reflecting the speed at which the indicator score changes over time.

[0073] Error term: It represents the performance of the variation not explained by the model over time and place, that is, the impact of factors that the model fails to fully capture on the comprehensive performance index.

[0074] Define performance indicators and their scores: Assume the following performance indicators: Infrastructure energy consumption, infrastructure energy efficiency, device communication network latency, storage throughput, energy efficiency, and service availability.

[0075] Assume that the score of each performance indicator at time t has been calculated, for example: Infrastructure Energy Consumption Score: , Infrastructure Energy Efficiency Score: , device communication network delay score: , Storage Throughput Score: , Energy efficiency score: , service availability score: .

[0076] Define the regression coefficients Assume that the regression coefficients are as follows: Base value , regression coefficient They are: , the interaction coefficient Both are 0.01, the weight coefficient of the score change rate , the weight coefficient of the score change rate Both are 0.05, and the error term Assume it is 0.05.

[0077] Calculate the overall performance index: Use the formula: ; Assuming the score change rate All are 0.01 (for simplification). Calculate the comprehensive performance index: ; Compute the interaction term: ; ; ; Calculate the score change rate term: ; ; Add the error term: ; The final comprehensive performance index is: ; Through the above examples, we can see how to use a multi-level performance indicator system to calculate the comprehensive performance index of the data center infrastructure. This method can not only fully reflect the operation quality of the data center, but also highlight the importance of different performance indicators through weighted aggregation, and consider the interaction between performance indicators and the impact of the score change rate, thereby providing a more accurate and comprehensive evaluation result.

[0078] 104. Based on the comprehensive performance index and the obtained service level agreement requirements, a performance evaluation is performed on the operation quality of the data center infrastructure, and improvement measures corresponding to the performance evaluation results are provided.

[0079] This step specifically includes the following sub-steps: Performance evaluation based on the comprehensive performance index and service level agreement requirements: Compare the calculated comprehensive performance index with the requirements of the service level agreement (SLA) to evaluate whether the operating quality of the data center infrastructure meets the predetermined service standards.

[0080] Provide improvement measures corresponding to performance evaluation results: Based on the evaluation results, propose specific improvement measures to help the data center optimize its operation quality and ensure that it can better meet the requirements of the service level agreement.

[0081] In this step, the concepts involved in the above steps are explained: Comprehensive performance index: Comprehensive performance index It is the overall operational quality score of the data center infrastructure calculated through a multi-level performance indicator system.

[0082] Service Level Agreement (SLA): A service level agreement is a contract between a service provider and a customer that specifies service quality standards, availability, response time, and other specific requirements. A data center service level agreement usually specifies a series of minimum requirements or target values ​​for performance indicators.

[0083] Performance evaluation: Performance evaluation refers to comparing the comprehensive performance index of the data center infrastructure with the requirements of the service level agreement to determine whether the current operating quality of the data center meets the predetermined standards.

[0084] Improvement measures: Improvement measures refer to specific action plans proposed based on the results of performance evaluation to improve the operating quality of data center infrastructure so that it better meets the requirements of the service level agreement.

[0085] In the embodiment of the present application, performance evaluation is performed based on the comprehensive performance index and service level agreement requirements, and improvement measures are provided: Define service level agreement requirements: Assume that the service level agreement (SLA) requirements are as follows: Infrastructure energy consumption: no more than 80%, Infrastructure energy efficiency: no more than 70%, Device communication network latency: no more than 10 milliseconds, Storage throughput: at least 100MB / s, Energy efficiency: no more than 1.5W / W, Service availability: at least 99%.

[0086] Obtaining the comprehensive performance index: Assume that the comprehensive performance index of the data center infrastructure at time t has been calculated ( ) is 1.389024 (see the previous embodiment).

[0087] Performance evaluation: Compare the comprehensive performance index with the service level agreement requirements to evaluate whether the operation quality of the data center meets the SLA requirements. Infrastructure energy efficiency: According to the previously calculated score, the infrastructure energy efficiency score is 0.76. If the score is converted into actual utilization, assuming that the full score of 1 represents 100% utilization, then the infrastructure energy efficiency is about 76%, which meets the SLA requirements. Infrastructure energy efficiency: The infrastructure energy efficiency score is 0.75, which is converted into an actual occupancy rate of about 75%, which meets the SLA requirements. Device communication network latency: The device communication network latency score is 0.77, which is converted into an actual latency of about 7.7 milliseconds, which meets the SLA requirements. Storage throughput: The storage throughput score is 0.78. Assuming that the full score of 1 represents 100MB / s, the actual throughput is about 78MB / s, which is slightly lower than the SLA requirement of 100MB / s. Energy efficiency: The energy efficiency score is 0.86. Assuming that the full score of 1 represents 1.2W / W, the actual energy efficiency is about 1.42W / W, which is slightly higher than the SLA requirement of 1.5W / W. Service availability: The service availability score is 0.92. Assuming that the full score is 1, which represents 99%, the actual availability is about 92%, which is lower than the SLA requirement of 99%.

[0088] Provide improvement measures: Evaluate the results and propose specific improvement measures: Storage throughput: Since the storage throughput is slightly lower than the SLA requirement, it is recommended to upgrade the storage device or optimize the storage architecture to increase the throughput. Energy efficiency: Although the energy efficiency is slightly higher than the SLA requirement, it is still within the acceptable range. The cooling system can be further optimized or more efficient power supply equipment can be used to reduce energy consumption. Service availability: The service availability is significantly lower than the SLA requirement. It is recommended to strengthen the redundancy design, such as adding backup servers, optimizing the load balancing strategy, and enhancing the failover mechanism.

[0089] Example calculation: Assume that the following evaluation results have been obtained: Infrastructure energy consumption: meets SLA requirements, storage utilization rate: meets SLA requirements, network latency: meets SLA requirements, storage throughput: slightly lower than SLA requirements, energy efficiency: slightly higher than SLA requirements, service availability: significantly lower than SLA requirements.

[0090] Based on these results, the following improvement measures can be proposed: Storage throughput: It is recommended to upgrade storage devices or optimize storage architecture to improve throughput. Energy efficiency: Optimize the cooling system or use more efficient power supply equipment to reduce energy consumption. Service availability: Strengthen redundancy design, such as adding spare servers, optimizing load balancing strategies, and enhancing failover mechanisms.

[0091] Through the above examples, we can see how to perform performance evaluation based on the comprehensive performance index and service level agreement requirements, and propose specific improvement measures based on the evaluation results. This method can not only comprehensively evaluate the operation quality of the data center, but also provide targeted optimization suggestions to help the data center better meet the requirements of the service level agreement.

[0092] Optionally, the "perform a performance evaluation on the operation quality of the data center infrastructure based on the comprehensive performance index and the obtained service level agreement requirements" in step 104 includes: establishing a mapping relationship between the comprehensive performance index and the service level agreement standard according to the service level agreement requirements of the data center infrastructure; based on the mapping relationship, comparing the comprehensive performance index with the service level agreement standard to evaluate whether the data center infrastructure meets the predetermined service level requirements, so as to achieve a performance evaluation on the operation quality of the data center infrastructure.

[0093] In this step, the concepts involved in the above steps are explained: Mapping relationship: A mapping relationship refers to a corresponding relationship established between the comprehensive performance index and the service level agreement standard. Through this relationship, the comprehensive performance index can be compared with the SLA requirements to evaluate whether the data center has achieved the predetermined service level requirements.

[0094] In the embodiment of the present application, it is assumed that the service level agreement (SLA) requirements of the data center have been defined as follows: Infrastructure energy consumption: no more than 80%, infrastructure energy efficiency: no more than 70%, device communication network delay: no more than 10 milliseconds, storage throughput: at least 100MB / s, energy efficiency: no more than 1.5W / W, service availability: at least 99%.

[0095] It is also necessary to define a mapping relationship between the comprehensive performance index and these SLA standards. Assume that the comprehensive performance index (SP(t)) has been calculated to be 1.389024 (see the previous embodiment).

[0096] The mapping relationship can be defined as: If the comprehensive performance index SP(t) is greater than or equal to 1.0, the data center is considered to have met the SLA requirements.

[0097] If the comprehensive performance index SP(t) is less than 1.0, it is considered that the data center does not meet the SLA requirements.

[0098] Furthermore, based on the established mapping relationship, the comprehensive performance index SP(t) is compared with the service level agreement standard. The specific steps are as follows: The comprehensive performance index SP(t)=1.389024 is compared with the mapping relationship.

[0099] If SP(t)≥1.0, the data center is considered to have achieved the predetermined service level requirements.

[0100] If SP(t)<1.0, the data center is considered to have failed to meet the predetermined service level requirements.

[0101] In this embodiment, the comprehensive performance index SP(t)=1.389024 is greater than 1.0, so it is considered that the data center has reached the predetermined service level requirement.

[0102] The evaluation results are as follows: Infrastructure energy consumption: Based on the previously calculated score, the infrastructure energy consumption score is 0.76. If the score is converted into actual energy consumption, assuming that the full score of 1 represents 100% utilization, the infrastructure energy consumption is about 76%, which does not meet the SLA requirements.

[0103] Infrastructure energy efficiency: The infrastructure energy efficiency score is 0.75, which translates to an actual energy efficiency of approximately 75%, meeting SLA requirements.

[0104] Device communication network latency: The device communication network latency score is 0.77, which translates to an actual latency of approximately 7.7 milliseconds, meeting SLA requirements.

[0105] Storage throughput: The storage throughput score is 0.78. Assuming that the full score of 1 represents 100 MB / s, the actual throughput is about 78 MB / s, which is slightly lower than the SLA requirement of 100 MB / s.

[0106] Energy efficiency: The energy efficiency score is 0.86. Assuming that the full score is 1, which represents 1.2 W / W, the actual energy efficiency is about 1.42 W / W, which is slightly higher than the SLA requirement of 1.5 W / W.

[0107] Service availability: The service availability score is 0.92. Assuming that the full score is 1, which represents 99%, the actual availability is about 92%, which is lower than the SLA requirement of 99%.

[0108] The comprehensive performance index SP(t) = 1.389024 shows that the data center as a whole has reached the predetermined service level requirements, but there are still problems in some individual indicators: The storage throughput is slightly lower than the SLA requirement.

[0109] The energy efficiency is slightly higher than the SLA requirement.

[0110] Service availability is significantly lower than SLA requirements.

[0111] Provide improvement measures corresponding to the performance evaluation results.

[0112] Based on the evaluation results, specific improvement measures are proposed: Storage throughput: It is recommended to upgrade storage devices or optimize storage architecture to improve throughput.

[0113] Energy efficiency: Reduce energy consumption by optimizing cooling systems or using more efficient power supplies.

[0114] Service availability: Strengthen redundancy design, such as adding backup servers, optimizing load balancing strategies, and enhancing failover mechanisms.

[0115] Through the above examples, we can see how to perform performance evaluation based on the comprehensive performance index and service level agreement requirements, and propose specific improvement measures based on the evaluation results. This method can not only comprehensively evaluate the operation quality of the data center, but also provide targeted optimization suggestions to help the data center better meet the requirements of the service level agreement.

[0116] Optionally, after the mapping relationship between the comprehensive performance index and the service level agreement standard is established, the method further includes: analyzing the gap between the comprehensive performance index and the service level agreement standard to adjust the mapping relationship; The gap between the comprehensive performance index and the service level agreement standard is calculated by the following formula: ; in, It represents the gap between the comprehensive performance index and the service level agreement standard at time t; is the comprehensive performance index of the data center infrastructure at time t; is the standard score specified in the service level agreement at time t; is the adjustment factor, which is used to control the influence of deviation on the total gap at time t; is the weight coefficient of the impact of the i-th performance indicator on the total gap at time t; is the score of the i-th performance indicator at time t; is the i-th performance indicator at time score; is the ideal score of the i-th performance indicator at time t; is the i-th performance indicator at time ideal score.

[0117] In this step, the concepts involved in the above steps are explained: The gap between the comprehensive performance index and the service level agreement standard: This refers to the gap between the comprehensive performance index ( ) and the standard score (SLA(t)) of the service level agreement (SLA) at a specific time point t. Gap analysis can help identify whether the operating quality of the data center infrastructure meets the SLA requirements and adjust the mapping relationship accordingly.

[0118] Adjustment Factor: and are adjustment factors used to control the degree of influence of deviation on the total gap. These factors can be adjusted according to actual conditions to optimize the gap analysis results.

[0119] Weight coefficient: and are weight coefficients, which respectively represent the weight coefficients of the influence of the ith performance index on the total gap in the time tree. These coefficients reflect the importance of the influence of different performance indicators on the total gap.

[0120] Ideal score: and is the i-th performance indicator at time t and time ideal scores that represent the desired optimal operating conditions.

[0121] Gap calculation formula: The gap calculation formula calculates the gap between the comprehensive performance index and the SLA standard through factors such as the comprehensive performance index, SLA standard score, adjustment factor and weight coefficient.

[0122] In the embodiment of the present application, the gap between the comprehensive performance index and the service level agreement standard is analyzed, and the mapping relationship is adjusted.

[0123] The formula used to analyze the gap between the comprehensive performance index and the service level agreement standard is: ; Hypothesized Moderating Factors and , weight coefficient and Both are 0.1, and the ideal score and All are 1 (full score). Calculate the difference : ; Assuming the score change rate All are 0.01 (for simplification). Calculate the deviation of each score: ; ; ; Calculate the score change rate term: ; Calculate the gap: ; Adjust the mapping relationship: Based on the gap analysis results, the comprehensive performance index Greater than 1.0, and the difference This shows that the data center as a whole has reached the predetermined service level requirements, but there is still a certain gap.

[0124] Storage throughput: The storage throughput is slightly lower than the SLA requirement. We recommend upgrading storage devices or optimizing the storage architecture to increase the throughput.

[0125] Energy efficiency: The energy efficiency is slightly higher than the SLA requirement. Optimize the cooling system or use more efficient power supply equipment to reduce energy consumption.

[0126] Service availability: Service availability is significantly lower than SLA requirements. Strengthen redundancy design, such as adding backup servers, optimizing load balancing strategies, and enhancing failover mechanisms.

[0127] Through the above embodiments, we can see how to analyze the gap between the comprehensive performance index and the service level agreement standard and adjust the mapping relationship accordingly to ensure that the data center infrastructure better meets the requirements of the service level agreement. This method can not only comprehensively evaluate the operation quality of the data center, but also provide targeted optimization suggestions to help the data center continue to improve.

[0128] Figure 2 A schematic diagram of the structure of an intelligent data center infrastructure performance evaluation system is provided for an embodiment of the present application, such as Figure 2 As shown, the system includes: An acquisition module 21 is used to acquire real-time operation data of the data center infrastructure; An adjustment module 22, configured to construct a multi-level performance indicator system according to the real-time operation data, and dynamically adjust a performance evaluation model according to the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operation data of the data center infrastructure and the corresponding performance evaluation results; A calculation module 23, used to calculate the comprehensive performance index of the data center infrastructure using the multi-level performance indicator system; The evaluation module 24 is used to perform a performance evaluation on the operation quality of the data center infrastructure based on the comprehensive performance index and the obtained service level agreement requirements, and provide improvement measures corresponding to the performance evaluation results.

[0129] Figure 2 The intelligent data center infrastructure performance evaluation system can be executed Figure 1 The implementation principle and technical effect of the intelligent data center infrastructure performance evaluation method described in the embodiment are not described in detail. The specific way in which each module and unit performs operations in the intelligent data center infrastructure performance evaluation system in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0130] In one possible design, Figure 2 An intelligent data center infrastructure performance evaluation system of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0131] The processing component 32 is used to: obtain real-time operating data of the data center infrastructure; construct a multi-level performance indicator system based on the real-time operating data, and dynamically adjust the performance evaluation model based on the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operating data of the data center infrastructure and the corresponding performance evaluation results; use the multi-level performance indicator system to calculate the comprehensive performance index of the data center infrastructure; based on the comprehensive performance index and the obtained service level agreement requirements, perform a performance evaluation on the operating quality of the data center infrastructure, and provide improvement measures corresponding to the performance evaluation results.

[0132] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0133] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0134] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0135] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0136] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0137] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0138] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1The illustrated embodiment is an intelligent data center infrastructure performance evaluation method.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0140] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for evaluating the performance of an intelligent data center infrastructure, characterized in that: include: Get real-time operational data of data center infrastructure; Constructing a multi-level performance indicator system according to the real-time operation data, and dynamically adjusting a performance evaluation model according to the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operation data of the data center infrastructure and the corresponding performance evaluation results; Using the multi-level performance indicator system, calculating a comprehensive performance index of the data center infrastructure; Based on the comprehensive performance index and the obtained service level agreement requirements, a performance evaluation is performed on the operation quality of the data center infrastructure, and improvement measures corresponding to the performance evaluation results are provided.

2. The method according to claim 1, characterized in that The constructing a multi-level performance indicator system according to the real-time operation data, and dynamically adjusting the performance evaluation model according to the multi-level performance indicator system, includes: Define a multi-level performance indicator system, construct different levels of performance indicators from the device level, system level to the overall level, the performance indicators include hardware health, device communication network delay, energy efficiency, service availability, and each performance indicator has a corresponding weight and threshold; Using the historical operation data of the data center infrastructure and the corresponding performance evaluation results, training a machine learning model to form an initial performance evaluation model, wherein the initial performance evaluation model is used to perform performance evaluation on the data center infrastructure according to the multi-level performance indicator system; The multi-level performance indicator system is dynamically updated according to the real-time operation data, and the parameter settings in the performance evaluation model are adjusted according to the updated multi-level performance indicator system to ensure that the performance evaluation model can accurately reflect the current operation status of the data center infrastructure.

3. The method according to claim 2, characterized in that The use of the multi-level performance index system to calculate the comprehensive performance index of the data center infrastructure includes: Designing a corresponding scoring algorithm for the performance indicators, wherein the scoring algorithm is determined according to a nonlinear relationship, a synergistic effect, and a time dependency among the plurality of performance indicators; Calculate the score of each performance indicator based on the scoring algorithm corresponding to the performance indicator; The scores of performance indicators at different levels are aggregated to obtain a comprehensive performance index of the data center infrastructure.

4. The method according to claim 3, characterized in that The performing of a performance evaluation on the operation quality of the data center infrastructure based on the comprehensive performance index and the obtained service level agreement requirements includes: According to the service level agreement requirements of the data center infrastructure, a mapping relationship between the comprehensive performance index and the service level agreement standard is established; Based on the mapping relationship, the comprehensive performance index is compared with the service level agreement standard to evaluate whether the data center infrastructure meets the predetermined service level requirements, so as to achieve performance evaluation of the operation quality of the data center infrastructure.

5. The method according to claim 4, characterized in that The step of calculating the score of each performance indicator based on the scoring algorithm corresponding to the performance indicator includes: calculating the score of each performance indicator by the following formula: ； in, represents the score of the i-th performance indicator at time t; is the actual measured value of the i-th performance indicator at time t; is the ideal target value of the i-th performance indicator; is the adjustment factor, which is used to control the steepness of the scoring function and the importance of different influencing factors; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t; is the weight coefficient of the jth performance indicator on the ith performance indicator at time t in the past period of time; n is the total number of performance indicators, refers to the jth performance indicator at time The actual measured value at .

6. The method according to claim 5, characterized in that The scores of performance indicators at different levels are summarized to obtain the comprehensive performance index of the data center infrastructure: The comprehensive performance index of the data center infrastructure is calculated by the following formula: ； in, represents the comprehensive performance index of the data center infrastructure at time t; The base value is the basic level of the comprehensive performance index when the scores of all performance indicators are zero. represents the regression coefficient of the i-th performance indicator at time t, represents the score of the i-th performance indicator at time t, represents the interaction coefficient between the i-th performance indicator and the j-th performance indicator at time t, represents the coefficient related to the rate of change of performance index at time t, represents the weight of the score change rate of the i-th performance indicator at time t, is the score of the jth performance indicator at time t; represents the rate of change of the score of the i-th performance indicator at time t; is the error term at time t.

7. The method according to claim 6, characterized in that After the mapping relationship between the comprehensive performance index and the service level agreement standard is established, the method further includes: Analyzing the gap between the comprehensive performance index and the service level agreement standard to adjust the mapping relationship; The gap between the comprehensive performance index and the service level agreement standard is calculated by the following formula: ； in, It represents the gap between the comprehensive performance index and the service level agreement standard at time t; is the comprehensive performance index of the data center infrastructure at time t; is the standard score specified in the service level agreement at time t; is the adjustment factor, which is used to control the influence of deviation on the total gap at time t; is the weight coefficient of the impact of the i-th performance indicator on the total gap at time t; is the score of the i-th performance indicator at time t; is the i-th performance indicator at time score; is the ideal score of the i-th performance indicator at time t; is the i-th performance indicator at time ideal score.

8. An intelligent data center infrastructure performance evaluation system, characterized in that: include: An acquisition module is used to obtain real-time operation data of the data center infrastructure; An adjustment module, configured to construct a multi-level performance indicator system according to the real-time operation data, and dynamically adjust a performance evaluation model according to the multi-level performance indicator system, wherein the performance evaluation model is trained based on the historical operation data of the data center infrastructure and the corresponding performance evaluation results; A calculation module, for calculating a comprehensive performance index of the data center infrastructure using the multi-level performance indicator system; The evaluation module is used to perform a performance evaluation on the operation quality of the data center infrastructure based on the comprehensive performance index and the obtained service level agreement requirements, and provide improvement measures corresponding to the performance evaluation results.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent data center infrastructure performance evaluation method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an intelligent data center infrastructure performance evaluation method as described in any one of claims 1 to 7 is implemented.

Images