Virtual machine performance evaluation and optimization method and device, equipment, medium and product

Abstract

The invention discloses a virtual machine performance evaluation and optimization method and device, equipment, a medium and a product. The method comprises the following steps: determining a performance evaluation result of the virtual machine based on a plurality of performance indexes; wherein the performance index is determined from at least one of the following performance dimensions: an equipment interaction behavior characteristic, a resource configuration condition, a dynamic load adaptation characteristic, a data recovery characteristic and a data transmission characteristic; and triggering a corresponding virtual machine optimization strategy according to a relationship between the performance evaluation result and a preset threshold value. According to the scheme, the state of the virtual machine is evaluated by constructing a multi-dimensional performance index system, the limitation that the real operation state of the virtual machine cannot be comprehensively reflected by traditional single-dimensional evaluation is broken through, and the objectivity and integrity of a performance evaluation result are ensured; meanwhile, a corresponding optimization strategy is triggered according to the relation between the performance evaluation result and the preset threshold value, and the resource utilization efficiency, the system stability and the service guarantee capacity of the virtual machine in the cloud computing and Internet of Things environment are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of cloud computing technology, and in particular to a method, apparatus, device, medium and product for virtual machine performance evaluation and optimization. Background Technology

[0002] In cloud computing and IoT device management scenarios, effective evaluation and optimization of virtual machine performance is crucial for ensuring service quality and resource efficiency. Current mainstream solutions typically rely on basic resource monitoring tools (such as Zabbix and cloud platform monitoring services) to collect core metrics like CPU utilization and memory consumption, and then use static thresholds for performance assessment and alerts. However, these methods have significant limitations: their metrics are singular and fail to comprehensively reflect the true performance of virtual machines under complex interactions, dynamic loads, and multi-resource collaboration scenarios; furthermore, the rigid response mechanism based on fixed thresholds cannot intelligently match optimization actions of varying finesse according to continuous changes in performance status, resulting in insufficient efficiency when dealing with highly dynamic demands such as those from the IoT, and making it difficult to achieve accurate and adaptive performance assurance. Summary of the Invention

[0003] This invention provides a method, apparatus, device, medium, and product for virtual machine performance evaluation and optimization, in order to solve the problem of poor performance evaluation and optimization of virtual machines in the prior art.

[0004] According to one aspect of the present invention, a method for evaluating and optimizing virtual machine performance is provided, the method comprising:

[0005] The performance evaluation results of the virtual machine are determined based on multiple performance indicators; among which, the performance indicators are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics.

[0006] Based on the relationship between the performance evaluation results and the preset threshold, the corresponding virtual machine optimization strategy is triggered.

[0007] According to another aspect of the present invention, a virtual machine performance evaluation and optimization apparatus is provided, the apparatus comprising:

[0008] The evaluation result determination module is used to determine the performance evaluation result of the virtual machine based on multiple performance indicators; wherein, the performance indicators are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics.

[0009] The optimization strategy triggering module is used to trigger corresponding virtual machine optimization strategies based on the relationship between performance evaluation results and preset thresholds.

[0010] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0011] At least one processor; and

[0012] A memory communicatively connected to the at least one processor; wherein,

[0013] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the virtual machine performance evaluation and optimization method according to any embodiment of the present invention.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the virtual machine performance evaluation and optimization method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the virtual machine performance evaluation and optimization method described in any embodiment of the present invention.

[0016] The technical solution of this invention determines the performance evaluation result of a virtual machine based on multiple performance indicators. These performance indicators are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics. Based on the relationship between the performance evaluation result and a preset threshold, a corresponding virtual machine optimization strategy is triggered. This technical solution evaluates the virtual machine state based on performance indicators determined from multiple dimensions, including device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics. This overcomes the limitation of traditional single-dimensional evaluation, which cannot comprehensively reflect the actual operating state of the virtual machine, ensuring the objectivity and completeness of the performance evaluation result. Simultaneously, by triggering corresponding optimization strategies based on the relationship between the performance evaluation result and a preset threshold, it achieves dynamic and precise virtual machine performance management, thereby significantly improving the resource utilization efficiency, system stability, and service assurance capabilities of virtual machines in cloud computing and IoT environments.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0019] Figure 1 This is a flowchart of a virtual machine performance evaluation and optimization method provided in Embodiment 1 of the present invention;

[0020] Figure 2 This is a flowchart of a virtual machine performance evaluation and optimization method provided in Embodiment 2 of the present invention;

[0021] Figure 3 This is a flowchart of a virtual machine performance evaluation and optimization method provided in Embodiment 3 of the present invention;

[0022] Figure 4 This is a schematic diagram of the structure of a virtual machine performance evaluation and optimization device according to Embodiment 4 of the present invention;

[0023] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the virtual machine performance evaluation and optimization method of this invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to include non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Example 1

[0027] Figure 1 This is a flowchart of a virtual machine performance evaluation and optimization method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the performance of virtual machines in a cloud-based IoT platform is dynamically monitored and intelligently optimized. This method can be executed by a virtual machine performance evaluation and optimization device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown in the figure, the virtual machine performance evaluation and optimization method provided in this embodiment includes the following steps:

[0028] S110. Based on multiple performance indicators, determine the performance evaluation results of the virtual machine; wherein, the performance indicators are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics.

[0029] Among them, performance dimensions can refer to different qualitative aspects or perspectives for observing, analyzing and evaluating the comprehensive performance of virtual machines in cloud-based IoT device management platforms. Each performance dimension describes a specific type of behavioral characteristic or capability attribute of the virtual machine. For example, performance dimensions may include at least one of the following: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics. These performance dimensions together constitute a multi-dimensional virtual machine performance evaluation framework, which aims to comprehensively cover the key performance aspects of virtual machines in complex environments.

[0030] Device interaction behavior characteristics can refer to the core performance characteristics of IoT devices interacting with virtual machines (including synchronous and asynchronous interactions), such as the balance of interaction time distribution, the complexity of interaction modes, and the response quality of asynchronous interactions.

[0031] Resource configuration can refer to the usage status and collaborative performance of various types of resources (such as CPU, memory, storage, bandwidth, etc.) within a virtual machine. For example, it can include the collaborative efficiency of different resources, the degree of balance in resource usage, and the stability of resource change trends.

[0032] Dynamic load adaptability refers to the ability of a virtual machine to cope with dynamic changes in the load of IoT devices (such as data request volume, task complexity, etc.), and is used to quantify the degree of adaptation and matching between load fluctuations and virtual machine resource adjustments.

[0033] Data recovery features can refer to the virtual machine's ability to recover lost data in real time during real-time data processing. These features may include recovery efficiency, recovery integrity, and dynamic stability of the recovery process.

[0034] Data transmission characteristics can refer to the core performance of data transmission between virtual machines and IoT devices, such as the collaborative performance of multiple transmission paths, the efficiency of real-time transmission, and the stability of the transmission process (no fluctuations, no interruptions).

[0035] Performance metrics can refer to specific quantitative parameters used to accurately measure a particular performance dimension, and a performance dimension can be specifically reflected and quantified by one or more performance metrics. For example, under the dimension of device interaction behavior characteristics, the complexity and response efficiency of device interaction can be quantified by performance metrics such as device interaction time distribution entropy and asynchronous device interaction efficiency.

[0036] Performance evaluation results can refer to a quantitative value that represents the overall performance level of a virtual machine, obtained by comprehensively calculating the data of various performance indicators.

[0037] In this embodiment of the invention, in the scenario of cloud-based IoT device management platform, traditional virtual machine performance evaluation based on indicators such as CPU utilization, memory consumption, and network bandwidth usage often fails to fully reflect the actual performance of virtual machines under complex interaction and dynamic load conditions. To address the aforementioned issues, this solution selects one or more relevant performance dimensions from five preset performance dimensions—including device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics—based on the specific application scenarios and core performance requirements of the virtual machine. For each selected performance dimension, specific, quantifiable performance indicators are further determined. For example, for device interaction behavior characteristics, performance indicators such as device interaction time distribution entropy and asynchronous device interaction efficiency can be selected. Then, for the determined performance indicators, real-time and historical data during virtual machine operation are collected, such as time-series data of interactions between the virtual machine and IoT devices, multi-dimensional resource (such as CPU, memory, and bandwidth) usage data, load data of IoT devices connected to the virtual machine, data loss, data recovery, request / response rates, transmission latency, and data transmission volume. Next, based on the collected raw data, the corresponding indicator data for each performance indicator is determined. Finally, by fusing and calculating the above indicator data, a unified performance evaluation result representing the overall performance status of the virtual machine is output.

[0038] S120. Based on the relationship between the performance evaluation results and the preset threshold, trigger the corresponding virtual machine optimization strategy.

[0039] Virtual machine optimization strategies can refer to hierarchical, targeted, and systematic adjustment schemes designed to improve virtual machine performance. The core of these strategies is to adjust virtual machine operating parameters (such as resource allocation ratios, interactive response rules, and transmission path configurations) or configuration rules based on the current performance status of the virtual machine (such as low performance, medium performance, and high performance) to achieve optimal performance for the virtual machine.

[0040] In this embodiment of the invention, the determined performance evaluation result can be compared with a pre-configured preset threshold. If the performance evaluation result is less than the preset threshold, it indicates that the virtual machine performance has dropped to a low level, resources may be severely insufficient or improperly configured, and the system determines to trigger a low-performance optimization strategy, preparing for comprehensive configuration optimization. If the performance evaluation result is greater than or equal to the preset threshold, it indicates that the virtual machine performance is in an acceptable or better state, preparing for targeted fine-tuning. Furthermore, a two-layer threshold comparison mechanism can be used to achieve refined and automated classification of virtual machine performance status. Specifically, two performance thresholds can be pre-configured: a first preset threshold... Second preset threshold (in Then, the determined performance evaluation results respectively with and Compare; if This indicates that the virtual machine's performance has dropped to a low level, resources may be severely insufficient or misconfigured, and the system determines that a low-performance optimization strategy has been triggered, preparing for a comprehensive, resource-level intervention; if This indicates that the virtual machine's performance is in an acceptable but not optimal state, possibly indicating a bottleneck in some aspects. The system determines to trigger a neutral performance optimization strategy and prepares for targeted, metric-level tuning. This indicates that the virtual machine is performing well, and the system has triggered a high-performance optimization strategy, which aims to maintain its high performance through preventative fine-tuning and prevent performance fluctuations or slight degradation.

[0041] The technical solution of this invention determines the performance evaluation result of a virtual machine based on multiple performance indicators. These performance indicators are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics. Based on the relationship between the performance evaluation result and a preset threshold, a corresponding virtual machine optimization strategy is triggered. This technical solution evaluates the virtual machine state based on performance indicators determined from multiple dimensions, including device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics. This overcomes the limitation of traditional single-dimensional evaluation, which cannot comprehensively reflect the actual operating state of the virtual machine, ensuring the objectivity and completeness of the performance evaluation results. Simultaneously, by triggering corresponding optimization strategies based on the relationship between the performance evaluation result and a preset threshold, dynamic and precise virtual machine performance management is achieved, thereby significantly improving the resource utilization efficiency, system stability, and service assurance capabilities of virtual machines in cloud computing and IoT environments.

[0042] Example 2

[0043] Figure 2 This is a flowchart of a virtual machine performance evaluation and optimization method provided in Embodiment 2 of the present invention. It is further optimized and extended based on the above embodiments and can be combined with various optional technical solutions in the above embodiments. For example... Figure 2 As shown in the figure, the virtual machine performance evaluation and optimization method provided in this embodiment includes the following steps:

[0044] S210. Based on multiple performance metrics, determine the performance evaluation results of the virtual machine.

[0045] In this embodiment of the invention, the performance indicators can be determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics.

[0046] Furthermore, based on the above embodiments of the invention, multiple performance indicators include device interaction time distribution entropy and / or asynchronous device interaction efficiency, which reflect the characteristics of device interaction behavior; wherein,

[0047] Device interaction time distribution entropy is used to quantify the uncertainty and complexity of interaction time between virtual machines and IoT devices;

[0048] Asynchronous device interaction efficiency is used to quantify the response efficiency of the virtual machine in handling asynchronous device requests.

[0049] Furthermore, based on the above embodiments of the invention, multiple performance indicators include a multi-dimensional resource synergistic utilization rate and / or a resource distribution imbalance coefficient that reflect resource allocation; wherein,

[0050] Multidimensional resource collaborative utilization rate is used to quantify the collaborative working efficiency of resources within a virtual machine;

[0051] The resource distribution imbalance coefficient is used to quantify the unevenness of resource usage within a virtual machine.

[0052] Furthermore, based on the above embodiments of the invention, multiple performance indicators include dynamic load interaction complexity, which reflects the dynamic load adaptation characteristics; wherein,

[0053] Dynamic load interaction complexity is used to assess the interaction complexity between changes in IoT device load and adjustments to virtual machine resources.

[0054] Furthermore, based on the above embodiments of the invention, multiple performance indicators include the real-time data loss recovery rate, which reflects data recovery characteristics; wherein,

[0055] Real-time data loss recovery rate is used to evaluate the virtual machine's ability to recover from data loss in real time.

[0056] Furthermore, based on the above embodiments of the invention, multiple performance indicators include distributed multipath transmission efficiency and / or real-time data transmission efficiency, which reflect data transmission characteristics; wherein,

[0057] Distributed multipath transmission efficiency is used to evaluate the overall efficiency of a virtual machine in using multiple transmission paths for data transmission.

[0058] Real-time data transmission efficiency is used to evaluate the data transmission efficiency and stability of virtual machines under real-time conditions.

[0059] In one embodiment, the performance evaluation result of the virtual machine can be determined using the following formula. :

[0060]

[0061] In the formula, DITE is the device interaction time distribution entropy; ADIE is the asynchronous device interaction efficiency; MRCE is the multi-dimensional resource collaborative utilization rate; RIC is the resource distribution imbalance coefficient; ALIC is the dynamic load interaction complexity; RDLRR is the real-time data loss recovery rate; DMTE is the distributed multipath transmission efficiency; and RDTE is the real-time data transmission efficiency. These are the weighting factors for each performance metric, used to adjust the contribution of each performance metric, and can be adjusted according to the importance of the business scenario. , and It is a non-linear adjustment factor used to adjust the influence intensity of the corresponding performance index and the shape of the response curve.

[0062] S220. The performance evaluation results are compared with the first preset threshold and the second preset threshold respectively; wherein the first preset threshold is less than the second preset threshold.

[0063] In this embodiment of the invention, two key performance thresholds can be pre-configured, namely a first preset threshold. Second preset threshold And the first preset threshold Less than the second preset threshold These two performance thresholds can be set based on historical performance data statistical analysis or business performance targets. Then, the performance evaluation results calculated above will be used... The results are compared with the two performance thresholds mentioned above to determine the performance range in which the result falls.

[0064] S230. If the performance evaluation result is less than the first preset threshold, then the low performance optimization strategy is triggered.

[0065] Among them, low-performance optimization strategies can refer to optimization strategies designed for virtual machine performance evaluation results that are lower than the first preset threshold (i.e., poor performance and obvious bottlenecks). The core is to quickly improve the overall performance of virtual machines through full-dimensional configuration adjustments (such as resource expansion, load migration, etc.).

[0066] In this embodiment of the invention, a threshold comparison is performed if... If so, the virtual machine is determined to be in a low-performance state, and a low-performance optimization strategy is triggered.

[0067] S240. If the performance evaluation result is greater than or equal to the first preset threshold and less than or equal to the second preset threshold, then determine to trigger the performance optimization strategy.

[0068] Among them, the medium performance optimization strategy can refer to the optimization strategy designed for virtual machine performance evaluation results that are between the first preset threshold and the second preset threshold (i.e., the performance is average and there are local bottlenecks). The core is to balance performance improvement and resource consumption by adjusting the critical state indicators in a targeted manner.

[0069] In this embodiment of the invention, a threshold comparison is performed if... If so, the virtual machine is determined to be in a medium performance state, and a medium performance optimization strategy is triggered.

[0070] S250. If the performance evaluation result is greater than the second preset threshold, then the high-performance optimization strategy will be triggered.

[0071] Among them, the high-performance optimization strategy can refer to the optimization strategy designed for virtual machine performance evaluation results that are higher than the second preset threshold (i.e., good performance and no obvious bottlenecks). The core is to maintain the high performance state through fine adjustments (such as parameter calibration, response priority optimization, etc.) and cope with small performance fluctuations.

[0072] In this embodiment of the invention, a threshold comparison is performed if... If so, the virtual machine is determined to be in a high-performance state, and a high-performance optimization strategy is triggered.

[0073] Furthermore, based on the above embodiments of the invention, when it is determined that a low-performance optimization strategy is triggered, the above method further includes:

[0074] Obtain the preset low-performance maintenance optimization function; the preset low-performance maintenance optimization function is determined based on the function expression of each performance index;

[0075] The virtual machine's operating parameters are adjusted according to the preset low-performance maintenance optimization function.

[0076] Among them, the preset low-performance maintenance optimization function can refer to the pre-configured global optimization function. Its core is a function expression based on full-dimensional performance indicators. Through calculation logic such as integration, weighted summation, and nonlinear mapping, the optimal adjustment scheme of virtual machine running parameters can be output by inputting real-time data of each indicator, which is used to specifically solve the low performance problem of virtual machines.

[0077] Virtual machine operating parameters can refer to core configuration parameters that directly affect the performance of the virtual machine, including but not limited to: resource allocation parameters (such as the number of CPU cores, memory capacity, and bandwidth quota), interaction strategy parameters (such as request-response priority and asynchronous interaction timeout threshold), transmission configuration parameters (such as multi-path transmission weight and data transmission rate threshold), and data recovery parameters (such as the number of data recovery retries and the proportion of recovery resources).

[0078] In this embodiment of the invention, when the virtual machine performance evaluation result is lower than a first preset threshold and a low-performance optimization strategy is triggered, a pre-configured preset low-performance maintenance optimization function can be called (this function has been pre-built based on a function expression of full-dimensional performance indicators). Then, real-time running data of each performance indicator of the virtual machine is collected. After substituting the above data into the optimization function, the optimal adjustment scheme is calculated through the function's built-in integral, weighted summation and other operation logic. Then, the virtual machine's resource allocation, interaction strategy, transmission configuration and other running parameters are adjusted in full dimensions through the cloud platform's dynamic resource management interface. Finally, the changes of each indicator are continuously monitored to verify the optimization effect. If the target is not met, the adjustment process is repeated until the virtual machine performance is improved to a qualified level.

[0079] This invention, through the introduction of a preset optimization function based on a dynamic model of multi-dimensional performance indicators, achieves intelligent and systematic root cause management of low-performance virtual machines. Compared with traditional threshold alarms and manual expansion, this solution can perform cross-resource and cross-dimensional joint analysis and optimization, accurately locate system bottlenecks, and implement globally optimal resource allocation. The entire process is fully automated, greatly improving operational efficiency and response speed.

[0080] Furthermore, based on the above embodiments of the invention, and considering the performance optimization strategy during triggering, the method further includes:

[0081] Continuously monitor a set of preset key performance indicators;

[0082] Based on monitoring data, identify the target performance indicators that have reached the critical state from the key performance indicators;

[0083] The virtual machine's operating parameters are adjusted according to the preset performance maintenance and optimization function associated with the target performance metric.

[0084] Among them, the preset key performance indicators can refer to the core requirements of cloud-based IoT device management scenarios. These are a few core indicators selected from the complete performance indicator system that have a decisive impact on the overall service capabilities and health status of virtual machines. Specifically, they may include device interaction time distribution entropy, dynamic load interaction complexity, distributed multipath transmission efficiency, and real-time data transmission efficiency.

[0085] A critical state can refer to a performance indicator whose value or trend has reached a preset warning level. This state indicates that the corresponding system component or function is under pressure, and if no intervention is taken, it may lead to a significant decline in performance or service impairment. It is the decision boundary that triggers optimization actions.

[0086] Target performance metrics can refer to key performance indicators that are identified as reaching a critical state during continuous monitoring. They are the core optimization objects of performance optimization strategies and directly correspond to the current performance bottleneck of the virtual machine.

[0087] The preset performance maintenance optimization function can refer to a pre-designed and configured function that encapsulates specific optimization rules. When a specific key performance indicator reaches a critical state, the system will call the associated function to calculate the optimal operating parameter adjustment scheme to deal with the current bottleneck problem.

[0088] In this embodiment of the invention, when a medium-performance optimization strategy is triggered, key performance indicators in the dimensions of interaction, load, and transmission can be focused on, namely, device interaction time distribution entropy, dynamic load interaction complexity, distributed multipath transmission efficiency, and real-time data transmission efficiency. These four key performance indicators are continuously monitored using real-time data analysis tools or professional tools. Subsequently, the collected monitoring data is compared with preset critical thresholds to accurately identify the critical indicators (i.e., target performance indicators) that cause the virtual machine to be in a medium-performance state. Finally, a preset medium-performance maintenance and optimization function matching the target performance indicator is called to adjust the virtual machine's resource allocation, interaction response, or transmission configuration and other operating parameters in a targeted manner, thereby completing the precise correction of performance bottlenecks and improving the virtual machine from a medium-performance state to a high-performance state.

[0089] This invention, through a closed-loop logic of "monitoring-identification-adjustment," achieves precise and automated optimization of virtual machines in medium-performance states. This avoids system interference and resource waste caused by blind optimization, while also enabling rapid response to performance changes under dynamic loads, timely correction of critical bottlenecks, and ensuring stable operation of virtual machines in the medium-performance range and their evolution towards the high-performance range. At the same time, automated optimization reduces manual maintenance costs, and targeted adjustments ensure the core business needs of cloud-based IoT device management scenarios (such as real-time interaction and stable transmission). While improving resource utilization efficiency, it effectively guarantees system service quality and user experience.

[0090] Furthermore, based on the above embodiments of the invention, when it is determined that a high-performance optimization strategy is triggered, the above method further includes:

[0091] Identify the smallest performance metric with the worst performance from a set of preset key performance indicators;

[0092] The virtual machine's operating parameters are adjusted according to a pre-defined high-performance maintenance optimization function associated with the minimum performance metric.

[0093] Among them, the minimum performance index can refer to the single index among the preset key performance indicators that has the largest deviation between the actual running data and the high-performance threshold benchmark, whose performance does not meet expectations, and which has a significant negative impact on maintaining the overall high-performance state of the virtual machine. It is the target object of high-performance maintenance and optimization.

[0094] Pre-defined high-performance maintenance optimization functions can refer to models that are pre-defined for each type of key performance indicator and used to achieve local performance fine-tuning. They have a built-in time decay factor, which can ensure smooth and stable optimization results without affecting the performance of other indicators.

[0095] In this embodiment of the invention, when a high-performance optimization strategy is triggered, four key performance indicators can be focused on: device interaction time distribution entropy, dynamic load interaction complexity, distributed multipath transmission efficiency, and real-time data transmission efficiency. By comparing real-time monitoring data, the bottleneck indicator that is currently most severely dragging down performance is identified, i.e., the minimum performance indicator. Then, the corresponding high-performance maintenance optimization function is matched from a preset optimization function library, and the target running parameters of the virtual machine are locally and slightly finely adjusted according to the built-in adjustment logic of the function. Finally, the indicator repair effect is verified by continuous monitoring to ensure that the minimum performance indicator returns to the high-performance range, thereby achieving stable maintenance of the high-performance state of the virtual machine.

[0096] This invention focuses on the core performance bottlenecks (minimum performance indicators) in high-performance scenarios and adopts an optimization logic of "precise identification - targeted matching - local fine-tuning". This avoids the risk of system fluctuations caused by blindly adjusting parameters in traditional high-performance maintenance, and can quickly repair performance bottlenecks, ensuring that virtual machines continue to run at high performance.

[0097] Example 3

[0098] Figure 3 This is a flowchart of a virtual machine performance evaluation and optimization method provided in Embodiment 3 of the present invention. Based on the above embodiments, this embodiment takes a cloud-based IoT device management platform as an example to provide one implementation of the virtual machine performance evaluation and optimization method, which can accurately evaluate and specifically optimize the performance of virtual machines in the cloud-based IoT device management platform. Figure 3 As shown in Embodiment 3 of the present invention, a virtual machine performance evaluation and optimization method specifically includes the following steps:

[0099] S310. Determine the performance indicators of the virtual machine in the cloud-based IoT device management platform, and determine the corresponding performance indicator values ​​based on the collected monitoring data.

[0100] In cloud-based IoT device management platforms, virtual machines primarily undertake the core tasks of data management and analysis. This includes receiving, storing, and processing data from connected IoT devices, monitoring the status of each device in real time, and coordinating the operations between multiple IoT devices to ensure they can work together effectively.

[0101] Therefore, when evaluating the performance of virtual machines, we can consider which specific indicators to use for evaluation and how to implement the evaluation based on the complexity and specific requirements of the virtual machine operating environment in the cloud IoT device management platform, so as to ensure that the selected indicators can comprehensively cover the performance of virtual machines in multiple key aspects such as data processing, resource management and network communication.

[0102] In this embodiment of the invention, eight performance metrics can be used to evaluate the virtual machine, and relevant data within an evaluation period (e.g., T=300 seconds) can be collected from a monitoring system (such as Prometheus) to determine the corresponding performance metric values. The eight performance metrics are described below:

[0103] (1) Based on the complexity of the interaction modes between IoT devices and virtual machines in the cloud-based IoT device management platform, such as periodic, intermittent and random interactions, a Device Interaction Time Distribution Entropy (DITE) is designed as the first performance evaluation index of the virtual machine. Its function expression is as follows:

[0104]

[0105] In the formula, IoT devices connected to virtual machines in time The conditional probability distribution for sending requests can be based on device load and priority. and resource usage Calculated; A dynamic weighting function for the interaction time of IoT devices, reflecting the importance of the interaction time in different time periods; Interaction time of IoT devices connected to virtual machines With resource usage and priority The multidimensional function representing the relationship between IoT devices and virtual machines represents the resource consumption and load status between IoT devices and virtual machines; This is to combine the interaction probability between IoT devices and virtual machines with changes in resources and priorities to adapt to the complexity of the cloud computing environment; I is the preset number of discrete time intervals, such as dividing 1 second into 10 intervals, then I=10.

[0106] The performance metric DITE innovatively incorporates the dynamic changes in responses within a cloud-based IoT device management platform. It not only reflects the uneven temporal distribution of interactions between virtual machines and IoT devices but also quantifies the dynamic changes in this unevenness over time. This design allows DITE to more comprehensively reflect the complexity of the interaction behavior between virtual machines and IoT devices within the cloud-based IoT device management platform and the virtual machine's responsiveness to changes, representing an important supplement and optimization to traditional performance metrics.

[0107] (2) Since virtual machines in cloud-based IoT device management platforms typically involve the collaborative work of multiple resources (CPU, memory, storage, bandwidth, etc.), a Multidimensional Resource Co-utilization (MRCE) is designed as the second performance evaluation metric for virtual machines. Its functional expression is as follows:

[0108]

[0109] In the formula, The resource coordination space in a virtual machine is a space that considers all resource dimensions and defines a multi-dimensional resource configuration environment. A function describing the j-th type of resource collaboration relationship; ( ), ( )and ( ) represents the CPU, memory, and network resource usage of virtual machine i, respectively; M represents the number of collaborative resources, i.e., the number of virtual machines participating in the collaboration; N represents the number of resource dimensions; and dV represents the integral infinitesimal element within the resource collaboration space.

[0110] The performance metric MRCE measures the overall performance of resource allocation by quantifying the ratio of the interaction (coordination efficiency) between different resource types to the efficiency of individual resource usage. It is more suitable for complex application scenarios that require a high degree of resource coordination, such as cloud-based IoT device management platforms, including big data processing and real-time multitasking.

[0111] (3) Based on the highly dynamic nature of data flow and control commands of IoT devices, a Dynamic Load Interaction Complexity (ALIC) is designed as the third performance evaluation index for virtual machines. Its function expression is as follows:

[0112]

[0113] In the formula, The load of IoT devices connected to the virtual machine at time t reflects the intensity of requests from the virtual machine. The resource adjustment amount of the virtual machine at time t represents how the virtual machine responds to changes in device load; T is the evaluation period.

[0114] The ALIC performance metric comprehensively considers the changing trends of the load and responsiveness of IoT devices connected to a virtual machine, in order to cope with the ever-changing environmental conditions in cloud-based IoT device management platforms. Furthermore, this metric not only reflects the virtual machine's ability to handle high dynamic loads but also reveals its potential to predict future changes and make corresponding adjustments, thus improving the accuracy of virtual machine performance evaluation.

[0115] (4) Based on the uneven distribution of virtual machine resources, a resource unevenness coefficient (RIC) is designed as the fourth performance evaluation index of virtual machine. Its function expression is as follows:

[0116]

[0117] In the formula, ( () represents the usage of the i-th resource by the virtual machine at time t; K represents the average usage of all resources in the virtual machine; K represents the number of resource types in the virtual machine, such as CPU, memory, bandwidth, etc.

[0118] The performance metric RIC reflects the virtual machine's high sensitivity to resource distribution and changes. For example, it provides quantification of resource usage variability and focuses not only on immediate resource usage but also on the abruptness and suddenness of changes in these trends. This allows for prediction of future resource demand changes and more proactive adjustments to virtual machine resource deployment. Furthermore, it emphasizes the virtual machine's sensitivity to dynamic changes in resource usage, increasing the complexity and depth of performance evaluation.

[0119] In summary, the RIC metric provides a comprehensive and in-depth perspective for virtual machine performance evaluation, helping to understand and optimize virtual machine behavior in complex IoT environments. It ensures efficient utilization of virtual machine resources while improving system stability and responsiveness, meeting the high standards of real-time performance and reliability required by IoT device management platforms.

[0120] (5) Based on the virtual machine's ability to recover lost data during real-time data processing, a Real-Time Data Loss Recovery Rate (RDLRR) was designed as the fifth performance evaluation metric for the virtual machine. Its functional expression is as follows:

[0121]

[0122] In the formula, ( () represents the amount of lost data recovered at time t; This represents the amount of data lost at time t. The amount of data waiting to be recovered at time t.

[0123] The performance metric RDLRR takes into account the real-time recovery dynamics of the virtual machine, including the recovery that has already occurred and the amount of data still to be processed, thus more accurately reflecting the real-time effectiveness of the virtual machine during data recovery. Secondly, by incorporating the dynamic changes in recovery data, the evaluation becomes more sensitive to rate changes during the data recovery process, helping to identify potential recovery problems or efficiency spikes and further optimize data recovery strategies. Finally, it allows the performance evaluation results of the virtual machine to be independent of the length of the evaluation period, making it applicable to data recovery scenarios of different scales and durations.

[0124] (6) Based on the asynchronous interaction between IoT devices and virtual machines in the cloud-based IoT device management platform, an asynchronous device interaction efficiency (ADIE) is designed as the sixth performance evaluation index of the virtual machine. Its function expression is as follows:

[0125]

[0126] In the formula, Q represents the number of IoT devices connected to the virtual machine; ( () represents the response rate of the virtual machine to the i-th IoT device at time t; Let t be the request rate of the i-th IoT device connected to the virtual machine.

[0127] The ADIE performance metric considers the effectiveness and efficiency of the virtual machine's response, rather than simply the existence of a response, providing a robust measure of response quality relative to request quality. Secondly, it highlights the virtual machine's adaptability and responsiveness to changing demands from IoT devices. Furthermore, it comprehensively evaluates the efficiency of device interactions throughout the entire evaluation period, rather than the instantaneous state at a single moment, thus accurately assessing the virtual machine's performance in handling asynchronous device requests.

[0128] (7) Based on the transmission efficiency of multiple transmission paths between IoT devices and virtual machines in the cloud IoT device management platform, a Distributed Multipath Transmission Efficiency (DMTE) is designed as the seventh performance evaluation index of the virtual machine. Its function expression is as follows:

[0129]

[0130] In the formula, ( Let be the bandwidth of the p-th transmission path between the IoT device and the virtual machine in the cloud-based IoT device management platform at time t; Let p be the transmission delay of the p-th transmission path between the IoT device and the virtual machine at time t. ( Let be the data transmission success rate of the p-th transmission path between the IoT device and the virtual machine at time t; P is the total number of transmission paths.

[0131] The performance metric DMTE enhances the stability and adaptability to complex network environments of this virtual machine performance evaluation method through time integration and logarithmic operations, making it particularly suitable for high-end systems such as cloud computing and data centers that rely on multi-path transmission. Furthermore, it integrates transmission bandwidth, path length, and success rate, and accurately captures the temporal variation characteristics of these parameters through higher-order derivatives, providing a highly dynamic and comprehensive virtual machine performance evaluation method.

[0132] (8) Based on the virtual machine's transmission capability in real-time data processing, a Real-Time Data Transmission Efficiency (RDTE) was designed as the eighth performance evaluation index for the virtual machine, and its functional expression is as follows:

[0133]

[0134] In the formula, The amount of data successfully transferred by the virtual machine at time t; This represents the total amount of data transferred by the virtual machine at time t.

[0135] The performance metric RDTE measures not only the real-time efficiency of data transmission but also the trend of speed changes during transmission, capturing acceleration or deceleration during transmission and providing a basis for optimizing virtual machine configuration. On the other hand, it adds an assessment of the sensitivity to changes in transmission speed, focusing not only on average efficiency but also on how efficiency changes over time. This allows RDTE to reflect the smoothness and stability of the data transmission process, helping to identify potential fluctuations or interruptions during transmission and thus promoting the realization of more stable services.

[0136] S320. Determine the performance evaluation results of the virtual machine based on the values ​​of each performance indicator.

[0137] In this embodiment of the invention, the performance evaluation result of the virtual machine can be determined using the following formula. :

[0138]

[0139] As can be seen from this formula, the nonlinear characteristics of the evaluation process are increased, making the evaluation model more dynamic, adaptive, and complex; secondly, this can be achieved through cross-product terms (such as...). and This approach introduces complex relationships between metrics to reveal the mutual influence between different performance metrics. Furthermore, trigonometric and inverse trigonometric operations can be used to increase the dynamic range and sensitivity of the evaluation results, making them more sensitive to minor changes in the metrics. This improves the technical level of the virtual machine performance evaluation model while more accurately reflecting the true performance status of the virtual machine, making it suitable for highly dynamic and demand-driven cloud computing environments.

[0140] S330, based on the performance evaluation results, the first preset threshold and the second preset threshold, determines the triggering conditions for the virtual machine's optimization strategy.

[0141] In an embodiment of the present invention, if If so, the virtual machine is determined to be in a low-performance state, and a low-performance optimization strategy is triggered; if If so, the virtual machine is determined to be in a medium-performance state, and a medium-performance optimization strategy is triggered; if If so, the virtual machine is determined to be in a high-performance state, and a high-performance optimization strategy is triggered.

[0142] In one embodiment, performance threshold and These settings can be configured based on historical data and system performance requirements. For example, they can be determined in the following ways:

[0143] ① Data Analysis: Collect historical performance evaluation data and apply statistical analysis (such as percentiles) to determine thresholds. For example, It can be set to the 25th percentile of historical evaluation results. It can be set to the 75th percentile of historical evaluation results.

[0144] ②Performance benchmark testing: By conducting stress tests and benchmark tests on the virtual machine system, observe the comprehensive score corresponding to different performance levels, and set reasonable performance thresholds accordingly.

[0145] S340. When a low-performance optimization policy is triggered, perform low-performance maintenance optimization on the virtual machine.

[0146] In this embodiment of the invention, the process of performing low-performance maintenance optimization on a virtual machine may include:

[0147] (1) Obtain the function expressions of the above eight performance indicators as a function of time.

[0148] (2) Based on the function expressions, optimize the low-performance maintenance function according to the following preset rules. Perform low-performance maintenance and optimization:

[0149]

[0150] In the formula, This is a functional expression for how each performance indicator changes over time. By solving this function, a comprehensive evaluation and optimization of all performance indicators can be performed. Through significant adjustments to resource allocation, overall performance can be rapidly improved, reversing unsatisfactory conditions.

[0151] S350: When the performance optimization strategy is triggered, the virtual machine performs performance maintenance optimization.

[0152] In this embodiment of the invention, the process of performance maintenance and optimization during virtual machine execution may include:

[0153] (1) Use real-time data analysis tools, such as Prometheus in combination with Grafana, or other professional IT monitoring tools such as Nagios, Zabbix, etc., to continuously monitor four key performance indicators (DITE, ALIC, DMTE, RDTE).

[0154] (2) Based on the monitoring data, determine which of the above four key performance indicators have reached the critical state, that is, which resources are most strained or which operations consume the most resources at a specific time.

[0155] (3) Utilize the dynamic resource management functions of cloud platforms or virtualization platforms, such as VMware DRS (Distributed Resource Scheduler), and optimize according to the monitored metric data using the following preset function. Dynamically adjust performance indicators that reach the critical state:

[0156]

[0157] In the formula, A function expression for how the performance metrics of a virtual machine change over time in order to reach a critical state.

[0158] Specifically, if the DITE metric reaches a critical state, adjustments will be made according to the following preset performance maintenance optimization function:

[0159]

[0160] In the formula, This is the optimization function corresponding to the DITE metric. This optimization function aims to allow the virtual machine to adjust the request-response distribution when the interaction time is uneven, so as to reduce volatility.

[0161] If the DMTE metric reaches a critical state, adjustments will be made according to the following preset performance maintenance optimization function:

[0162]

[0163] In the formula, This is the optimization function corresponding to the DMTE indicator. This optimization function aims to improve data transmission efficiency by optimizing the virtual machine's path transmission rate and latency.

[0164] If the metrics ALIC or MRCE reach a critical state, adjustments will be made according to the following preset performance maintenance optimization function:

[0165]

[0166] In the formula, For predicted future transmission delay; This is the optimization function corresponding to the metrics ALIC and MRCE. This optimization function aims to ensure the interaction balance and resource coordination of virtual machines under dynamic load.

[0167] S360: When the high-performance optimization policy is triggered, perform high-performance maintenance optimization on the virtual machine.

[0168] In this embodiment of the invention, the process of performing high-performance maintenance optimization on a virtual machine may include:

[0169] (1) Identify which of the four key performance indicators (DITE, ALIC, DMTE, RDTE) performs the worst at a specific time, that is, identify the minimum performance indicator.

[0170] (2) Apply the time decay factor and combine it with the identified minimum performance index to perform high-performance maintenance optimization on the virtual machine according to the following preset high-performance maintenance optimization function:

[0171]

[0172] In the formula, This is a functional expression for the minimum performance index as a function of time. This is a time decay factor, ensuring that the optimization effect gradually decreases over time, thereby maintaining stability; This is the optimization function corresponding to the minimum performance metric. This optimization function aims to perform preventative, incremental, and small-scale optimizations on the weakest single metric to prevent slight performance degradation and maintain it in its optimal operating state.

[0173] The technical solution of this invention measures the overall efficiency of resource allocation by quantifying the ratio of the interaction (coordination efficiency) between different resource types to the efficiency of individual resource usage. This approach is more suitable for complex application scenarios such as cloud-based IoT device management platforms that require high resource coordination. Furthermore, when evaluating efficiency, the changing trends of the load and response capabilities of the IoT devices connected to the virtual machine are comprehensively considered to address the constantly changing environmental conditions in the cloud-based IoT device management platform. This method not only demonstrates the virtual machine's ability to handle high dynamic loads but also reveals its potential to predict future changes and make corresponding adjustments, thereby improving the accuracy of virtual machine efficiency evaluation.

[0174] Secondly, after evaluating the performance of virtual machines, specific optimization methods matching the performance evaluation results can be used to adjust the virtual machine configuration, thereby ensuring that the system can continuously operate at its optimal performance state when facing constantly changing loads and demands. This approach not only improves resource utilization efficiency but also significantly enhances system reliability and user satisfaction.

[0175] Example 4

[0176] Figure 4 This is a schematic diagram of a virtual machine performance evaluation and optimization device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device includes:

[0177] The performance metric determination module 41 is used to determine the performance evaluation result of the virtual machine based on multiple performance metrics; wherein the performance metrics are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics.

[0178] The optimization strategy triggering module 42 is used to trigger the corresponding virtual machine optimization strategy based on the relationship between the performance evaluation results and the preset threshold.

[0179] Furthermore, based on the above embodiments of the invention, multiple performance indicators include device interaction time distribution entropy and / or asynchronous device interaction efficiency, which reflect the characteristics of device interaction behavior; wherein,

[0180] Device interaction time distribution entropy is used to quantify the uncertainty and complexity of interaction time between virtual machines and IoT devices;

[0181] Asynchronous device interaction efficiency is used to quantify the response efficiency of the virtual machine in handling asynchronous device requests.

[0182] Furthermore, based on the above embodiments of the invention, multiple performance indicators include a multi-dimensional resource synergistic utilization rate and / or a resource distribution imbalance coefficient that reflect resource allocation; wherein,

[0183] Multidimensional resource collaborative utilization rate is used to quantify the collaborative working efficiency of resources within a virtual machine;

[0184] The resource distribution imbalance coefficient is used to quantify the unevenness of resource usage within a virtual machine.

[0185] Furthermore, based on the above embodiments of the invention, multiple performance indicators include dynamic load interaction complexity, which reflects the dynamic load adaptation characteristics; wherein,

[0186] Dynamic load interaction complexity is used to assess the interaction complexity between changes in IoT device load and adjustments to virtual machine resources.

[0187] Furthermore, based on the above embodiments of the invention, multiple performance indicators include the real-time data loss recovery rate, which reflects data recovery characteristics; wherein,

[0188] Real-time data loss recovery rate is used to evaluate the virtual machine's ability to recover from data loss in real time.

[0189] Furthermore, based on the above embodiments of the invention, multiple performance indicators include distributed multipath transmission efficiency and / or real-time data transmission efficiency, which reflect data transmission characteristics; wherein,

[0190] Distributed multipath transmission efficiency is used to evaluate the overall efficiency of a virtual machine in using multiple transmission paths for data transmission.

[0191] Real-time data transmission efficiency is used to evaluate the data transmission efficiency and stability of virtual machines under real-time conditions.

[0192] Furthermore, based on the above embodiments of the invention, the optimization strategy triggering module 42 is specifically used for:

[0193] The performance evaluation results are compared with a first preset threshold and a second preset threshold, respectively; wherein the first preset threshold is less than the second preset threshold.

[0194] If the performance evaluation result is less than the first preset threshold, then a low performance optimization strategy is triggered.

[0195] If the performance evaluation result is greater than or equal to the first preset threshold and less than or equal to the second preset threshold, then the performance optimization strategy is determined to be triggered.

[0196] If the performance evaluation result is greater than the second preset threshold, then the high-performance optimization strategy will be triggered.

[0197] Furthermore, based on the above embodiments of the invention, the device further includes a low-performance optimization strategy execution module, used for:

[0198] If a low-performance optimization strategy is triggered, a preset low-performance maintenance optimization function is obtained; the preset low-performance maintenance optimization function is determined based on the function expressions of each performance metric.

[0199] The virtual machine's operating parameters are adjusted according to the preset low-performance maintenance optimization function.

[0200] Furthermore, based on the above embodiments of the invention, the device further includes a performance optimization strategy execution module, used for:

[0201] Once the low-to-medium energy optimization strategy is determined to be triggered, a set of preset key performance indicators will be continuously monitored.

[0202] Based on monitoring data, identify the target performance indicators that have reached the critical state from the key performance indicators;

[0203] The virtual machine's operating parameters are adjusted according to the preset performance maintenance and optimization function associated with the target performance metric.

[0204] Furthermore, based on the above embodiments of the invention, the device further includes a low-high energy optimization strategy execution module, used for:

[0205] Given a predetermined high-performance optimization strategy, identify the lowest performance metric from a set of pre-defined key performance indicators.

[0206] The virtual machine's operating parameters are adjusted according to a pre-defined high-performance maintenance optimization function associated with the minimum performance metric.

[0207] The virtual machine performance evaluation and optimization apparatus provided in this embodiment of the invention can execute the virtual machine performance evaluation and optimization method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0208] Example 5

[0209] Figure 5 A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0210] like Figure 5 As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded from storage unit 58 into the RAM 53. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0211] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0212] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as virtual machine performance evaluation and optimization methods.

[0213] In some embodiments, the virtual machine performance evaluation and optimization method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the virtual machine performance evaluation and optimization method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured to perform the virtual machine performance evaluation and optimization method by any other suitable means (e.g., by means of firmware).

[0214] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0215] In some embodiments, the virtual machine performance evaluation and optimization method may be implemented as a computer program, which is implicitly included in a computer program product. When executed by a processor, the computer program implements the virtual machine performance evaluation and optimization method of the present invention. The computer program product can be understood as a software product that primarily implements its solution through a computer program. The computer program used to implement the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a standalone software package, or entirely on a remote machine or server.

[0216] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0217] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0218] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0219] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0220] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0221] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for evaluating and optimizing virtual machine performance, characterized in that, The method comprises: determining a performance evaluation result of the virtual machine based on a plurality of performance indicators, wherein the performance indicators are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics; triggering a corresponding virtual machine optimization strategy according to the relationship between the performance evaluation result and a preset threshold.

2. The method of claim 1, wherein, The plurality of performance indicators include device interaction time distribution entropy and / or asynchronous device interaction efficiency reflecting the device interaction behavior characteristics, wherein The device interaction time distribution entropy is used to quantify the uncertainty and complexity of the interaction time between the virtual machine and the Internet of Things device; The asynchronous device interaction efficiency is used to quantify the response efficiency of the virtual machine in processing asynchronous device requests.

3. The method of claim 1, wherein, The plurality of performance indicators include multi-dimensional resource collaborative utilization rate and / or resource distribution imbalance coefficient reflecting the resource configuration, wherein The multi-dimensional resource collaborative utilization rate is used to quantify the collaborative working efficiency of the internal resources of the virtual machine; The resource distribution imbalance coefficient is used to quantify the imbalance of the use of internal resources of the virtual machine.

4. The method of claim 1, wherein, The plurality of performance indicators include dynamic load interaction complexity reflecting the dynamic load adaptation characteristics, wherein The dynamic load interaction complexity is used to evaluate the interaction complexity between the load change of the Internet of Things device and the resource adjustment of the virtual machine.

5. The method of claim 1, wherein, The plurality of performance indicators include real-time data loss recovery rate reflecting the data recovery characteristics, wherein The real-time data loss recovery rate is used to evaluate the real-time recovery capability of the virtual machine for data loss.

6. The method of claim 1, wherein, The plurality of performance indicators include distributed multi-path transmission efficiency and / or real-time data transmission efficiency reflecting the data transmission characteristics, wherein The distributed multi-path transmission efficiency is used to evaluate the comprehensive efficiency of the virtual machine in using multiple transmission paths for data transmission; The real-time data transmission efficiency is used to evaluate the data transmission efficiency and stability of the virtual machine under real-time conditions.

7. The method of claim 1, wherein, The triggering of the corresponding virtual machine optimization strategy according to the relationship between the performance evaluation result and the preset threshold comprises: comparing the performance evaluation result with a first preset threshold and a second preset threshold respectively, wherein the first preset threshold is smaller than the second preset threshold; if the performance evaluation result is smaller than the first preset threshold, it is determined to trigger a low-performance optimization strategy; if the performance evaluation result is greater than or equal to the first preset threshold and smaller than or equal to the second preset threshold, it is determined to trigger a medium-performance optimization strategy; if the performance evaluation result is greater than the second preset threshold, it is determined to trigger a high-performance optimization strategy.

8. The method of claim 1, wherein, In the case of determining to trigger the low-performance optimization strategy, the method further comprises: obtaining a preset low-performance maintenance optimization function, wherein the preset low-performance maintenance optimization function is determined based on a function expression of each performance indicator; adjusting the running parameters of the virtual machine according to the preset low-performance maintenance optimization function.

9. The method of claim 1, wherein, In the case of determining to trigger the medium-performance optimization strategy, the method further comprises: continuously monitoring a group of preset key performance indicators; According to the monitoring data, a target performance indicator reaching a critical state is identified from the key performance indicators; According to a preset high performance maintenance optimization function associated with the target performance indicator, the running parameter of the virtual machine is adjusted.

10. The method of claim 1, wherein, In a case where it is determined that the high performance optimization strategy is triggered, the method further comprises: A minimum performance indicator with the worst performance is identified from a group of preset key performance indicators; According to a preset high performance maintenance optimization function associated with the minimum performance indicator, the running parameter of the virtual machine is adjusted.

11. A virtual machine performance evaluation and optimization apparatus, comprising: The device comprises: An evaluation result determination module configured to determine a performance evaluation result of a virtual machine based on a plurality of performance indicators, wherein the performance indicators are determined from at least one of the following performance dimensions: device interaction behavior characteristics, resource configuration conditions, dynamic load adaptation characteristics, data recovery characteristics, and data transmission characteristics; An optimization strategy triggering module configured to trigger a corresponding virtual machine optimization strategy according to a relationship between the performance evaluation result and a preset threshold.

12. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the virtual machine performance evaluation and optimization method of any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to execute when the virtual machine performance evaluation and optimization method of any one of claims 1-10 is implemented.

14. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program implements the virtual machine performance evaluation and optimization method of any one of claims 1-10 when executed by the processor. The computer program product comprises a computer program, and the computer program implements the virtual machine performance evaluation and optimization method of any one of claims 1-10 when executed by the processor.

Images