Cloud computing system resource load prediction method and system based on full life cycle data

Abstract

The invention relates to a cloud computing system resource load prediction method and system based on full life cycle data, electronic equipment and a computer readable storage medium. Comprising the steps of obtaining full-life-cycle data of cloud computing, extracting features for calculation after preprocessing, and generating prediction data; the method comprises the steps of constructing corresponding prediction models according to different system characteristics, inputting prediction data into the prediction models, generating load prediction results, formulating resource allocation and scheduling strategies based on the load prediction results and resource states, and adjusting the resource allocation and scheduling strategies according to a difference value between an actual value and a prediction value. According to the scheme disclosed by the invention, the influence of full-life-cycle data on the load can be considered, dynamically changing load requirements can be adapted, new class, reconstruction class and optimized systems can be predicted and evaluated, the characteristics of different systems are considered, a design scheme is planned and differentiated analysis is performed, the prediction accuracy and stability are improved, and the prediction efficiency is improved. And the resource utilization rate and performance are optimized.

Description

Technical Field

[0001] The present invention relates to the field of big data cloud computing technology, and in particular to a cloud computing system resource load prediction method, system, electronic device and computer-readable storage medium based on full life cycle data. Background Art

[0002] In recent years, cloud computing, as an emerging computing model, has been widely used in various fields due to its elastic scalability and pay-as-you-go characteristics. However, the resource load of the cloud computing environment is dynamically changing, and how to effectively manage and allocate cloud computing resources has become an important issue.

[0003] For example, the Chinese invention patent disclosure CN117234870A discloses a method and system for heterogeneous CPU resource load scheduling prediction, which obtains CPU resource-related utilization data in a heterogeneous CPU server, preprocesses the utilization data, and divides the preprocessed utilization data into a training set and a test set at a preset ratio; trains the model and brings the feature sequence into the Bagging algorithm module for learning to obtain a prediction model for heterogeneous CPU resource load scheduling prediction; obtains the target utilization data related to the CPU resources of the target heterogeneous CPU server, and inputs the target utilization data into the prediction model for calculation. However, this method can only obtain specific data, and does not consider the impact of the full life cycle data on the load, resulting in a large granularity of the analysis results and a lack of pertinence.

[0004] The resource management prediction methods in the existing technology often perform load prediction and resource allocation based on static historical rules or experience, which cannot adapt to dynamically changing load demands, and do not consider the characteristics of different systems for differentiated analysis. They cannot predict and evaluate new, reconstructed, and optimized systems well, and the daily optimization, upgrade, and iteration of the system are normalized. Therefore, a cloud computing system resource load prediction and disposal method based on full life cycle data is needed to improve prediction accuracy and stability, optimize resource utilization and performance, and avoid waste caused by over-configuration. Summary of the invention

[0005] To address the deficiencies in the prior art, the present invention proposes a cloud computing system resource load prediction method, system, electronic device, and computer-readable storage medium based on full life cycle data.

[0006] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0007] A cloud computing system resource load prediction method based on full life cycle data, characterized by comprising:

[0008] S1. Acquire full life cycle data of cloud computing, wherein the full life cycle data is data of the cloud computing system in the planning, design, development, testing, and operation stages;

[0009] S2, preprocessing the full life cycle data, extracting features for calculation, and generating prediction data;

[0010] S3, construct corresponding prediction models according to system characteristics, and train and optimize the prediction models;

[0011] S4, inputting the prediction data into the prediction model to generate a load prediction result;

[0012] S5. Based on the load prediction result and resource status, formulate a resource allocation and scheduling strategy, wherein the resource status is obtained by collecting the resource usage of the cloud computing system in real time.

[0013] Furthermore, after step S5, the following steps are further included:

[0014] S6. Input the operating status data and the resource status into the prediction model to obtain performance data, compare and analyze the performance data with the load prediction result to obtain a difference value, and adjust the resource allocation and scheduling strategy based on the difference value.

[0015] Optionally, constructing corresponding prediction models for system characteristics in step S3 further includes:

[0016] The prediction model is constructed by using multiple linear regression or support vector regression or gradient boosting regression tree. The multiple linear regression takes throughput as a prediction target and estimates regression coefficients by using methods such as the least squares method.

[0017] Furthermore, the training and optimization of the prediction model in step S3 further includes:

[0018] The historical data is divided into a training set, a validation set and a test set. The prediction model uses the training set for model training, uses the validation set for hyperparameter tuning and model selection, uses the test set to evaluate model performance, and selects the optimal model based on the model performance.

[0019] Optionally, the step S3 further includes:

[0020] The prediction model was validated using a cross-validation method.

[0021] Optionally, preprocessing the full life cycle data in step S2 further includes: standardizing the full life cycle data and aligning the time series, and performing outlier detection and processing.

[0022] In addition, the present invention also relates to a cloud computing system resource load prediction system based on full life cycle data, which is characterized by comprising:

[0023] An acquisition module is used to acquire full life cycle data of cloud computing, wherein the full life cycle data is data of the cloud computing system in the planning, design, development, testing, and operation stages;

[0024] A preprocessing module, used to preprocess the full life cycle data, extract features for calculation, and generate prediction data, wherein the preprocessing is to standardize the full life cycle data and align the time series, and perform outlier detection and processing;

[0025] A prediction model building module is used to build corresponding prediction models according to system characteristics, train and optimize the prediction models, and verify the prediction models using a cross-validation method; the prediction models are built using multiple linear regression or support vector regression or gradient boosting regression tree, the multiple linear regression takes throughput as the prediction target, and estimates the regression coefficients using methods such as the least squares method;

[0026] A prediction module, used for inputting the prediction data into the prediction model to generate a load prediction result;

[0027] A resource adjustment module, used to formulate a resource allocation and scheduling strategy according to the load prediction result and resource status, wherein the resource status is obtained by collecting the resource usage of the cloud computing system in real time;

[0028] A feedback module is used to input the operating status data and the resource status into the prediction model to obtain performance data, compare and analyze the performance data with the load prediction result to obtain a difference value, and adjust the resource allocation and scheduling strategy based on the difference value.

[0029] Furthermore, the prediction model building module is also used for:

[0030] The historical data is divided into a training set, a validation set and a test set. The prediction model uses the training set for model training, uses the validation set for hyperparameter tuning and model selection, uses the test set to evaluate model performance, and selects the optimal model based on the model performance.

[0031] In addition, the present invention also relates to an electronic device, characterized in that it comprises a processor and a memory;

[0032] The memory is used to store operation instructions;

[0033] The processor is used to execute the above method by calling the operation instruction.

[0034] In addition, the present invention also relates to a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and the computer program implements the above method when executed by a processor.

[0035] Adopt the scheme provided by this application, by obtaining the data of the whole life cycle of cloud computing, including the data of planning, design, development, testing, and operation stages, extracting features for calculation after preprocessing, and generating prediction data. Then, a corresponding prediction model is constructed for different system characteristics. The model can adopt construction methods such as multivariate linear regression, support vector regression or gradient boosting regression tree, and is trained and optimized. The prediction data is input into the prediction model to generate load prediction results, and resource allocation and scheduling strategies are formulated based on the load prediction results and resource status. In addition, a feedback link is provided to input the actual operation status data and resource status into the prediction model again to obtain performance data, compare and analyze with the previous load prediction results, and adjust the resource allocation and scheduling strategy according to the difference value. Therefore, the above technical scheme can consider the impact of the whole life cycle data on the load, can adapt to the dynamically changing load demand, can predict and evaluate the newly built class, reconstructed class and optimized system, and consider the characteristics of different systems, plan and design schemes and perform differentiated analysis, improve prediction accuracy and stability, optimize resource utilization and performance, and avoid waste caused by over-configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a method for predicting resource load of a cloud computing system based on full life cycle data provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of the structure of a cloud computing system resource load prediction system based on full life cycle data provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

[0040] Those skilled in the art can understand that, unless otherwise stated, the singular forms "one", "an", "said" and "the" used herein may also include plural forms, and the "first", "second", etc., are only used to distinguish and define objects for the purpose of introducing the scheme clearly, and do not limit the objects themselves. Of course, the objects defined by "first" and "second" may be the same terminal, device, user, etc., or the same type of terminal, device and user. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0041] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments.

[0042] The embodiments of the present invention provide a method and system for predicting resource load of a cloud computing system based on full life cycle data, which can take into account the impact of full life cycle data on the load, adapt to dynamically changing load requirements, and consider the characteristics of different systems to perform differentiated analysis, improve prediction accuracy and stability, optimize resource utilization and performance, and avoid waste caused by over-configuration.

[0043] Different system types are considered in the present invention, including high CPU type, high memory type, high GPU type and high bandwidth type system, wherein:

[0044] High CPU type system: mainly relies on the computing power of the CPU, such as large-scale scientific computing, data analysis, etc. In the design phase, focus on collecting data on algorithm complexity, computing intensity, and multi-threading / process design; in the stress testing phase, gradually increase concurrent requests, observe changes in CPU usage and throughput, and record response time and performance bottlenecks under different concurrency levels; in the running phase, monitor real-time CPU usage and system load, and analyze the reasons for performance degradation and hot issues after long-term operation.

[0045] High-memory systems: require a large amount of memory resources, such as databases, cache systems, etc. In the design phase, evaluate the effectiveness of data structures and memory management strategies, and analyze the logic of memory allocation and release; in the stress testing phase, increase data load, observe the growth trend of memory consumption, and record memory leaks and fragmentation; in the running phase, monitor memory usage and memory allocation rate, analyze the efficiency of garbage collection or memory defragmentation and its impact on system performance.

[0046] High GPU system: Use GPU for high-performance computing, such as deep learning, graphics rendering, etc. In the design phase, evaluate the complexity of graphics rendering and the degree of algorithm optimization, and analyze the design and implementation of parallel computing; in the stress testing phase, increase the rendering load, observe the changing trend of GPU usage and frame rate, and record the usage of video memory and rendering delay; in the running phase, monitor the GPU usage and video memory occupancy, and analyze the reasons for performance degradation and hot issues after long-term operation.

[0047] High-bandwidth systems: have high demands on network bandwidth, such as video streaming, large data transmission, etc. In the design phase, evaluate the size and frequency of data transmission and the effectiveness of network protocols and buffering strategies; in the stress testing phase, increase network load, observe the changing trends of bandwidth utilization and data transmission rate, and record network delays and packet losses; in the operation phase, monitor network bandwidth utilization and data transmission volume, and analyze network stability and performance bottlenecks after long-term operation.

[0048] Figure 1 The present invention provides a schematic flow chart of a method for predicting resource load of a cloud computing system based on full life cycle data, including:

[0049] S1. Acquire full life cycle data of cloud computing, wherein the full life cycle data is data of the cloud computing system in the planning, design, development, testing, and operation stages;

[0050] In order to more clearly introduce the full life cycle data disclosed in this application, the specific content of the full life cycle is now provided:

[0051] Planning data: including system requirements, hardware configuration, network topology and other planning information;

[0052] Design data: Design information including system architecture, module design, interface design, etc.

[0053] Development data: including code base, development tools, development environment and other development related information;

[0054] Test environment stress test data: simulate different load scenarios in the test environment and record performance indicators such as throughput, response time, and number of concurrent users. This data helps understand the system's behavior and performance bottlenecks under high load;

[0055] Real-time operating parameters of the production environment: Key indicators such as CPU usage, memory usage, disk I / O, and network bandwidth are regularly collected through system monitoring tools. This data reflects the resource consumption of the system under real-time load.

[0056] System configuration and software information: Collect information such as the application system's hardware configuration (such as CPU model, memory size, disk type), operating system version, and software dependencies (such as middleware and database version). This data is crucial for analyzing factors that affect system performance and resource consumption.

[0057] S2. Preprocessing the life cycle data, extracting features, performing calculations, and generating prediction data. The preprocessing specifically includes:

[0058] Standardization: standardize the data of different indicators to eliminate dimensional differences and facilitate subsequent analysis and comparison. For example, convert proportional indicators such as CPU usage and memory occupancy into relative values ​​between 0 and 1.

[0059] Time series alignment: For time series data, ensure that timestamps are aligned so that data of different indicators at the same time point can be correctly associated;

[0060] Outlier detection and processing: use statistical methods or machine learning algorithms to detect outliers, and perform interpolation, smoothing or elimination based on actual conditions.

[0061] The feature extraction and calculation of the preprocessed data specifically include:

[0062] Derived feature calculation: Calculate derived features based on original data, such as the moving average of CPU usage and the growth rate of memory usage, to capture the dynamic change trend of indicators;

[0063] Correlation analysis, calculating the correlation coefficient between the real-time operating parameters of the production environment and the performance indicators of the test environment, identifying key influencing factors and potential relationships;

[0064] Feature scaling and regularization: scaling features (such as normalization and standardization) to improve the convergence speed and performance of machine learning algorithms, and using regularization techniques to prevent overfitting;

[0065] Feature selection: Based on correlation analysis and domain knowledge, select feature subsets that have a significant impact on the prediction target, reduce model complexity and improve generalization ability;

[0066] S3. Construct corresponding prediction models for system characteristics respectively, and train and optimize the prediction models; the prediction models are constructed by multiple linear regression or support vector regression or gradient boosting regression tree, the multiple linear regression takes throughput as the prediction target, and estimates the regression coefficients by methods such as least squares method; divide the historical data into a training set, a validation set and a test set, the prediction model uses the training set for model training, the validation set for hyperparameter tuning and model selection, the test set for evaluating model performance, and the optimal model is selected based on the model performance, and the prediction model is validated by a cross-validation method;

[0067] S4, inputting the prediction data into the prediction model to generate a load prediction result;

[0068] S5. Formulate a resource allocation and scheduling strategy based on the load prediction result and resource status, wherein the resource status is obtained by collecting the resource usage of the cloud computing system in real time;

[0069] In actual use, since cloud computing is based on multiple virtual machines to achieve operations, resource allocation and scheduling is the control of virtual machines. The number and configuration of virtual machines are dynamically adjusted according to the prediction results to meet the resource requirements of different time periods. By monitoring the real-time load situation, the resource allocation strategy is dynamically adjusted. For example, when the load is low, some virtual machines can be destroyed to save resources; when the load is high, more virtual machines need to be created to share the load. At the same time, tasks are assigned to different virtual machines or physical machines for execution based on factors such as task priority, resource requirements and prediction results.

[0070] S6. Input the operating status data and the resource status into the prediction model to obtain performance data, compare and analyze the performance data with the load prediction result to obtain a difference value, and adjust the resource allocation and scheduling strategy based on the difference value.

[0071] In actual applications, by calculating the difference between performance data and load forecast results, the resource allocation strategy can be adjusted and optimized in a timely manner. For example, when the CPU usage of a virtual machine is continuously too high, the CPU quota of the virtual machine can be dynamically increased or some tasks can be migrated to other virtual machines for execution. When it is predicted that the network bandwidth demand will increase significantly in a certain period of time in the future, the network bandwidth allocation strategy can be adjusted in advance to meet the demand.

[0072] By adopting the solution, we can consider the impact of full life cycle data on the load, adapt to dynamically changing load demands, predict and evaluate new classes, reconstructed classes and optimized systems, and consider the characteristics of different systems to plan design solutions and conduct differentiated analysis to improve prediction accuracy and stability, optimize resource utilization and performance, and avoid waste caused by over-configuration.

[0073] based on Figure 1 The cloud computing system resource load prediction method based on the full life cycle data is shown, and on the other hand, it also relates to a cloud computing system resource load prediction system based on the full life cycle data, and its structure is as follows Figure 2 As shown, including:

[0074] The acquisition module 201 is used to acquire the full life cycle data of cloud computing, wherein the full life cycle data is the data of the cloud computing system in the planning, design, development, testing, and operation stages;

[0075] A preprocessing module 202 is used to preprocess the full life cycle data, extract characteristic values ​​for calculation, and generate prediction data, wherein the preprocessing is to standardize the full life cycle data and align the time series, and perform outlier detection and processing;

[0076] The prediction model building module 203 is used to build corresponding prediction models according to system characteristics, train and optimize the prediction models, and verify the prediction models by using a cross-validation method; the prediction models are built by using multiple linear regression or support vector regression or gradient boosting regression tree, the multiple linear regression takes throughput as the prediction target, and estimates the regression coefficients by using methods such as the least squares method;

[0077] A prediction module 204, configured to input the prediction data into the prediction model to generate a load prediction result;

[0078] The resource adjustment module 205 is used to formulate a resource allocation and scheduling strategy according to the load prediction result and the resource status, wherein the resource status is obtained by collecting the resource usage of the cloud computing system in real time;

[0079] The feedback module 206 is used to input the operating status data and the resource status into the prediction model to obtain performance data, compare and analyze the performance data with the load prediction result to obtain a difference value, and adjust the resource allocation and scheduling strategy based on the difference value.

[0080] Furthermore, the prediction model building module 203 is also used for:

[0081] The historical data is divided into a training set, a validation set and a test set. The prediction model uses the training set for model training, uses the validation set for hyperparameter tuning and model selection, uses the test set to evaluate model performance, and selects the optimal model based on the model performance.

[0082] By using this system, the above method can be executed and the corresponding technical effects can be achieved.

[0083] An embodiment of the present invention further provides an electronic device for executing the above method, as an implementation device of the method, comprising a processor and a memory;

[0084] A memory, used for storing operation instructions;

[0085] The processor is used to execute the long-term and short-term investment risk preference determination method provided in any embodiment of the present application by calling operation instructions.

[0086] As an example, Figure 3 A schematic diagram of the structure of an electronic device applicable to an embodiment of the present application is shown, and the electronic device 300 includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one. It is understandable that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the specific structure of the electronic device 300. In other embodiments of the present application, the electronic device 300 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. Optionally, the electronic device may also include a display screen 305 for displaying images, or receiving user operation instructions when necessary.

[0087] The processor 301 is applied in the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 304 may include a receiver and a transmitter. The transceiver 304 is applied in the embodiment of the present application to implement the function of the electronic device of the embodiment of the present application communicating with other devices when executed.

[0088] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0089] The processor 301 may also include one or more processing units, for example, the processor 301 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processor (NPU). Among them, different processing units may be independent devices or integrated into one or more processors. Among them, the controller may be the nerve center and command center of the electronic device 300. The controller may generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. A memory may also be set in the processor 301 for storing instructions and data. In some embodiments, the memory in the processor 301 is a high-speed cache memory. The memory may store instructions or data that the processor 301 has just used or circulated. If the processor 301 needs to use the instruction or data again, it may be directly called from the memory. Repeated access is avoided, the waiting time of the processor 301 is reduced, and the efficiency of the system is improved.

[0090] The processor 301 can run the database configuration method provided in the embodiment of the present application to reduce the user's operation complexity, improve the intelligence of the terminal device, and enhance the user experience. The processor 301 can include different devices. For example, when the CPU and GPU are integrated, the CPU and GPU can cooperate to execute the database configuration method provided in the embodiment of the present application. For example, part of the algorithm in the database configuration method is executed by the CPU, and the other part of the algorithm is executed by the GPU to obtain faster processing efficiency.

[0091] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0092] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or may include a high-speed random access memory, or may include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0093] Optionally, the memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the long-term and short-term investment risk preference determination method provided in any embodiment of the present application.

[0094] The memory 303 can be used to store computer executable program codes, which include instructions. The processor 301 executes various functional applications and data processing of the electronic device 300 by running the instructions stored in the memory 303. The memory 303 may include a program storage area and a data storage area. Among them, the program storage area may store the code of the operating system, application program, etc. The data storage area may store data created during the use of the electronic device 300 (such as images, videos, etc. collected by the camera application), etc.

[0095] The memory 303 may also store one or more computer programs corresponding to the long-term and short-term investment risk preference discrimination method provided in the embodiment of the present application. The one or more computer programs are stored in the above-mentioned memory 303 and are configured to be executed by the one or more processors 301. The one or more computer programs include instructions, and the above-mentioned instructions can be used to execute each step in the above-mentioned corresponding embodiment.

[0096] Of course, the code of the long-term and short-term investment risk preference discrimination method provided in the embodiment of the present application can also be stored in an external memory. In this case, the processor 301 can run the code of the database configuration method stored in the external memory through the external memory interface, and the processor 301 can control the operation of the database configuration process.

[0097] The display screen 305 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 300 may include 1 or N display screens 305, where N is a positive integer greater than 1. The display screen 305 can be used to display information input by a user or information provided to a user and various graphical user interfaces (GUI). For example, the display screen 305 can display photos, videos, web pages, or files.

[0098] The electronic device provided in the embodiment of the present application is applicable to any embodiment of the above method. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0099] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0100] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0102] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0104] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A cloud computing system resource load prediction method based on full life cycle data, characterized in that: include: S1. Acquire full life cycle data of cloud computing, wherein the full life cycle data is data of the cloud computing system in the planning, design, development, testing, and operation stages; S2, preprocessing the full life cycle data, extracting features for calculation, and generating prediction data; S3, construct corresponding prediction models according to system characteristics, and train and optimize the prediction models; S4, inputting the prediction data into the prediction model to generate a load prediction result; S5. Based on the load prediction result and resource status, formulate a resource allocation and scheduling strategy, wherein the resource status is obtained by collecting the resource usage of the cloud computing system in real time.

2. The method according to claim 1, characterized in that: The step S5 further includes: S6. Input the operating status data and the resource status into the prediction model to obtain performance data, compare and analyze the performance data with the load prediction result to obtain a difference value, and adjust the resource allocation and scheduling strategy based on the difference value.

3. The method according to claim 1, characterized in that The step S3 of constructing corresponding prediction models for system characteristics further includes: The prediction model is constructed by using multiple linear regression or support vector regression or gradient boosting regression tree. The multiple linear regression takes throughput as a prediction target and estimates regression coefficients by using methods such as the least squares method.

4. The method according to claim 3, characterized in that: The step S3 of training and optimizing the prediction model further includes: The historical data is divided into a training set, a validation set and a test set. The prediction model uses the training set for model training, uses the validation set for hyperparameter tuning and model selection, uses the test set to evaluate model performance, and selects the optimal model based on the model performance.

5. The method according to claim 4, characterized in that The step S3 further comprises: The prediction model was validated using a cross-validation method.

6. The method according to claim 1, characterized in that The preprocessing of the full life cycle data in step S2 further includes: standardizing the full life cycle data and aligning the time series, and performing outlier detection and processing.

7. A cloud computing system resource load prediction system based on full life cycle data, characterized in that: include: An acquisition module is used to acquire full life cycle data of cloud computing, wherein the full life cycle data is data of the cloud computing system in the planning, design, development, testing, and operation stages; A preprocessing module, used to preprocess the full life cycle data, extract features for calculation, and generate prediction data, wherein the preprocessing is to standardize the full life cycle data and align the time series, and perform outlier detection and processing; A prediction model building module is used to build corresponding prediction models according to system characteristics, train and optimize the prediction models, and verify the prediction models using a cross-validation method; the prediction models are built using multiple linear regression or support vector regression or gradient boosting regression tree, the multiple linear regression takes throughput as the prediction target, and estimates the regression coefficients using methods such as the least squares method; A prediction module, used for inputting the prediction data into the prediction model to generate a load prediction result; A resource adjustment module, used to formulate a resource allocation and scheduling strategy according to the load prediction result and resource status, wherein the resource status is obtained by collecting the resource usage of the cloud computing system in real time; A feedback module is used to input the operating status data and the resource status into the prediction model to obtain performance data, compare and analyze the performance data with the load prediction result to obtain a difference value, and adjust the resource allocation and scheduling strategy based on the difference value.

8. The system according to claim 7, characterized in that The prediction model building module is also used to: The historical data is divided into a training set, a validation set and a test set. The prediction model uses the training set for model training, uses the validation set for hyperparameter tuning and model selection, uses the test set to evaluate model performance, and selects the optimal model based on the model performance.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store operation instructions; The processor is used to execute the method according to any one of claims 1 to 6 by calling the operation instruction.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images