A Paas platform based on cloud computing

Abstract

The present application is applicable to the field of cloud computing technology, and provides a Paas platform based on cloud computing, which includes: a real-time monitoring module for real-time monitoring of resource monitoring data of the PaaS platform; a load prediction module for inputting resource monitoring data into a preset load prediction model to obtain a predicted load quantity; a resource management operation module for executing resource management operations corresponding to the predicted load data based on the predicted load quantity; a first acquisition module for obtaining user business requests; a resource allocation module for dynamically allocating resource nodes according to resource monitoring data and user business requests based on a preset load balancing strategy. It can be seen that the present application can allocate resources in real time according to load conditions by realizing dynamic resource increase and decrease and automatic load balancing, thereby improving resource utilization, avoiding resource waste, and thus improving overall resource management efficiency.

Description

Technical Field

[0001] The present application belongs to the field of cloud computing technology, and in particular to a PaaS platform based on cloud computing. Background Art

[0002] Currently, cloud computing is developing rapidly, and more and more enterprises and individuals choose to migrate their businesses to cloud platforms. Due to the large scale of cloud platforms, the allocation and management of resources are often complex, and existing technologies often cannot achieve efficient resource monitoring and management, resulting in technical problems such as low resource utilization and resource waste. Summary of the invention

[0003] The embodiment of the present application provides a PaaS platform based on cloud computing, which can solve the problems of low resource utilization and resource waste in the prior art.

[0004] In a first aspect, the present application provides a Paas platform based on cloud computing, including:

[0005] Real-time monitoring module, used to monitor the resource monitoring data of the PaaS platform in real time;

[0006] A load prediction module, used for inputting the resource monitoring data into a preset load prediction model to obtain a predicted load quantity;

[0007] A resource management operation module, configured to perform a resource management operation corresponding to the predicted load quantity based on the predicted load quantity;

[0008] A first acquisition module, used to acquire a user service request;

[0009] The resource allocation module is used to dynamically allocate resource nodes according to the resource monitoring data and the user service request based on a preset load balancing strategy.

[0010] In a possible implementation of the first aspect, the cloud computing-based Paas platform further includes:

[0011] The second acquisition module is used to acquire historical training data;

[0012] A preprocessing module, used for preprocessing the historical training data;

[0013] An extraction module, used for extracting feature training data from the preprocessed historical data;

[0014] The training module is used to train the preset load prediction model based on the preset loss function and the characteristic training data to obtain the trained preset load prediction model.

[0015] In a possible implementation manner of the first aspect, the preset loss function is:

[0016]

[0017] in, represents the preset loss function, represents the true value, represents the predicted value of the preset load prediction model, Indicates the sample size.

[0018] In a possible implementation of the first aspect, the preset load prediction model includes a preset input layer, a preset long-term and short-term network layer, a preset multi-layer perception layer, and a preset output layer;

[0019] The load prediction module comprises:

[0020] A vectorization processing submodule, used for performing vectorization processing on the resource monitoring data according to a preset input layer to obtain a feature vector;

[0021] A time correlation extraction submodule is used to extract the time correlation of the feature vector according to the preset long-term and short-term network layers to obtain the hidden state;

[0022] A nonlinear transformation submodule, used for performing a nonlinear transformation on the hidden state according to a preset multi-layer perception layer to obtain a high-dimensional vector;

[0023] The classification processing submodule is used to classify the high-dimensional vector according to a preset output layer to obtain a predicted load quantity.

[0024] In a possible implementation manner of the first aspect, the classification processing submodule includes:

[0025] The load prediction unit is used to obtain the predicted load quantity according to the following formula:

[0026] ;

[0027] ;

[0028] ;

[0029] ;

[0030] in, Indicates Resource monitoring data, represents a vectorized function, represents the feature vector, Indicates the current time point The characteristic vector of Indicates the previous time point The hidden state of Represents the long short-term memory operation corresponding to the preset long short-term network layer, Indicates the current time point The hidden state of represents the weight matrix, represents the bias vector, Indicates the activation operation corresponding to the preset multi-layer perception layer, represents a high-dimensional vector, Indicates that the high-dimensional vector belongs to The scores of the categories, represents the total number of categories, Indicates the predicted load quantity.

[0031] In a possible implementation manner of the first aspect, the resource management operation module includes:

[0032] A first resource management operation submodule, configured to perform a first resource management operation when the predicted load quantity is greater than a preset load quantity threshold;

[0033] or,

[0034] The second resource management operation submodule is used to perform a second resource management operation when the predicted load quantity is less than a preset load quantity threshold.

[0035] In a possible implementation manner of the first aspect, the user service request is a first user service request;

[0036] The resource allocation module comprises:

[0037] A first calling submodule, used to call a first load balancing strategy corresponding to the first user service request;

[0038] The first resource allocation submodule is used to dynamically allocate resource nodes according to the resource monitoring data based on the first load balancing strategy.

[0039] In a possible implementation manner of the first aspect, the user service request is a second user service request;

[0040] The resource allocation module comprises:

[0041] A second calling submodule, calling a second load balancing strategy corresponding to the second user service request;

[0042] The second resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the second load balancing strategy.

[0043] In a possible implementation manner of the first aspect, the user service request is a third user service request;

[0044] The resource allocation module comprises:

[0045] A third calling submodule calls a third load balancing strategy corresponding to the third user service request;

[0046] The third resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the third load balancing strategy.

[0047] In a possible implementation manner of the first aspect, the user service request is a fourth user service request;

[0048] The resource allocation module comprises:

[0049] A fourth calling submodule, calling a fourth load balancing strategy corresponding to the fourth user service request;

[0050] The fourth resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the fourth load balancing strategy.

[0051] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0052] In the embodiment of the present application, the Paas platform based on cloud computing includes: a real-time monitoring module for real-time monitoring of the resource monitoring data of the PaaS platform; a load prediction module for inputting the resource monitoring data into a preset load prediction model to obtain a predicted load quantity; a resource management operation module for executing a resource management operation corresponding to the predicted load quantity based on the predicted load quantity; a first acquisition module for obtaining user service requests; a resource allocation module for dynamically allocating resource nodes according to the resource monitoring data and the user service request based on a preset load balancing strategy. It can be seen that by realizing dynamic resource increase and decrease and automatic load balancing in the embodiment of the present application, the PaaS platform can allocate resources in real time according to the load situation, improve resource utilization, avoid resource waste, and thus improve the overall resource management efficiency.

[0053] In addition, the embodiments of the present application can accurately understand the current status and resource requirements of the PaaS platform by real-time monitoring of resource monitoring data on the PaaS platform. By analyzing historical data and resource monitoring data, and combining with a preset load prediction model, it can predict future loads and output the predicted load quantity, providing an accurate basis for resource allocation. When the predicted load increases, the PaaS platform can automatically increase resources, such as virtual machine instances, storage capacity, etc., to meet user needs, ensure that the PaaS platform can dynamically expand resources, improve system performance and stability, and avoid resource waste. By obtaining user business requests, load distribution is automatically performed according to the characteristics of resource monitoring data and business requests to ensure load balancing between various resource nodes. By selecting appropriate load balancing strategies, such as polling, least connections, IP hashing, etc., optimal resource allocation can be achieved to improve system performance and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 It is a structural diagram of a Paas platform based on cloud computing provided in an embodiment of the present application;

[0056] Figure 2 It is a schematic diagram of the structure of the server provided in the embodiment of the present application. DETAILED DESCRIPTION

[0057] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0058] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0059] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0060] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0061] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0062] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0063] The technical solution of the embodiment of the present application is introduced below.

[0064] See also Figure 1 , is a structural diagram of the cloud computing-based Pass platform provided in an embodiment of the present application. The system may include a real-time monitoring module 11, a load prediction module 12, a resource management operation module 13, a first acquisition module 14 and a resource allocation module 15.

[0065] The real-time monitoring module 11 is used to monitor the resource monitoring data of the PaaS platform in real time.

[0066] Among them, resource monitoring data includes CPU, memory, network bandwidth, etc. These resource monitoring data are used to determine the current status and resource requirements of the Paas platform.

[0067] The load prediction module 12 is used to input the resource monitoring data into a preset load prediction model to obtain a predicted load quantity.

[0068] Among them, the preset load prediction model can be a load prediction model trained based on a deep learning model (such as a convolutional neural network model, etc.) using historical training data, or it can be a trained load prediction model directly obtained.

[0069] In a possible implementation, the cloud computing-based Paas platform further includes:

[0070] The second acquisition module is used to acquire historical training data;

[0071] A preprocessing module, used for preprocessing the historical training data;

[0072] An extraction module, used for extracting feature training data from the preprocessed historical data;

[0073] The training module is used to train the preset load prediction model based on the preset loss function and the characteristic training data to obtain the trained preset load prediction model.

[0074] Exemplarily, the preset loss function is:

[0075]

[0076] in, represents the preset loss function, represents the true value, represents the predicted value of the preset load prediction model, Indicates the sample size.

[0077] Exemplarily, the historical training data refers to user historical request information and corresponding historical resource monitoring data.

[0078] The preprocessing module is specifically used to perform operations such as data cleaning, resampling, and data smoothing on historical training data.

[0079] Feature data refers to data that can extract features that can reflect the load change trend in order to train the prediction model, such as timestamp, load change trend, historical load quantity, resource utilization, etc.

[0080] Exemplarily, the extraction module is specifically used to extract feature training data from historical data through statistical analysis, time series analysis or data mining.

[0081] Training modules are specifically used for:

[0082] Input the characteristic data into the preset load prediction model and calculate the output of the model through forward propagation;

[0083] Calculate the loss function, compare the model prediction value with the true label, and calculate the loss value; calculate the gradient through the back propagation algorithm, and solve the gradient of the preset load prediction model parameters; use the optimization algorithm to update the preset load prediction model parameters according to the calculated gradient; repeat the above process until the preset stop condition is reached.

[0084] In a possible implementation, the preset load prediction model includes a preset input layer, a preset long-term and short-term network layer, a preset multi-layer perception layer, and a preset output layer;

[0085] The load prediction module comprises:

[0086] A vectorization processing submodule, used for performing vectorization processing on the resource monitoring data according to a preset input layer to obtain a feature vector;

[0087] A time correlation extraction submodule is used to extract the time correlation of the feature vector according to the preset long-term and short-term network layers to obtain the hidden state;

[0088] A nonlinear transformation submodule, used for performing a nonlinear transformation on the hidden state according to a preset multi-layer perception layer to obtain a high-dimensional vector;

[0089] The classification processing submodule is used to classify the high-dimensional vector according to a preset output layer to obtain a predicted load quantity.

[0090] The classification processing submodule includes:

[0091] The load prediction unit is used to obtain the predicted load quantity according to the following formula:

[0092] ;

[0093] ;

[0094] ;

[0095] ;

[0096] in, Indicates Resource monitoring data, represents a vectorized function, represents the feature vector, Indicates the current time point The characteristic vector of Indicates the previous time point The hidden state of Represents the long short-term memory operation corresponding to the preset long short-term network layer, Indicates the current time point The hidden state of represents the weight matrix, represents the bias vector, Indicates the activation operation corresponding to the preset multi-layer perception layer, represents a high-dimensional vector, Indicates that the high-dimensional vector belongs to The scores of the categories, represents the total number of categories, Indicates the predicted load quantity.

[0097] In the embodiment of the present application, resource monitoring data is converted into feature vectors through a preset vectorization function, which can effectively convert different types of monitoring data into a unified feature representation, and can be more convenient for subsequent processing and analysis; using a preset long-term and short-term network layer, such as LSTM, time correlation is extracted from the feature vector to obtain a hidden state. This processing can capture long-term dependencies and short-term fluctuations in time series data. For the load forecasting model, it can better model and predict the temporal changes of data and maintain the memory of historical data; using a preset multi-layer perception layer, the hidden state is nonlinearly transformed to obtain a high-dimensional vector, which can increase the fitting ability and expression ability of the model, so that the model can better learn the nonlinear relationship in the data. The multi-layer perception layer can abstract and transform the hidden state layer by layer, thereby extracting a higher-level feature representation; applying a preset output layer to classify the high-dimensional vector to obtain the predicted load quantity. Taking the output of the prediction model as the target, the high-dimensional vector is classified by a classifier and mapped to a specific load quantity. The high-dimensional vector can be effectively mapped to different categories to achieve the task of predicting the load quantity.

[0098] The resource management operation module 13 is used to perform a resource management operation corresponding to the predicted load quantity based on the predicted load quantity.

[0099] Exemplarily, the resource management operation module includes:

[0100] The first resource management operation submodule is used to perform a first resource management operation when the predicted load quantity is greater than a preset load quantity threshold.

[0101] Specifically, the first resource management operation is: when the predicted load quantity is greater than a preset load quantity threshold, increasing computing resources (such as virtual machines, containers, etc.) or storage resources (such as expanding disk capacity) to meet higher load requirements.

[0102] Exemplarily, the resource management operation module includes:

[0103] The second resource management operation submodule is used to perform a second resource management operation when the predicted load quantity is less than a preset load quantity threshold.

[0104] Specifically, the second resource management operation is to release computing resources or storage resources that are no longer needed to save costs and resource usage.

[0105] The first acquisition module 14 is used to acquire a user service request.

[0106] The user service request is a first user service request, a second user service request, a third user service request or a fourth user service request. For example, the first user service request may be a development service requirement, the second user service request may refer to a testing service requirement, the third user service request may refer to a deployment service requirement, and the fourth user service requirement may refer to a management service requirement.

[0107] The resource allocation module 15 is used to dynamically allocate resource nodes according to the resource monitoring data and the user service request based on a preset load balancing strategy.

[0108] In a specific application, the user service request is a first user service request;

[0109] The resource allocation module comprises:

[0110] A first calling submodule, used to call a first load balancing strategy corresponding to the first user service request;

[0111] The first resource allocation submodule is used to dynamically allocate resource nodes according to the resource monitoring data based on the first load balancing strategy.

[0112] The first load balancing strategy refers to deciding which resource node to assign the development business request to based on a pre-set load balancing strategy (such as polling, least connections, IP hashing, etc.), taking into account factors such as the current resource node load, network bandwidth, and response time to ensure that the developer's request can be responded to quickly and with high-quality service.

[0113] In a specific application, the user service request is a second user service request;

[0114] The resource allocation module comprises:

[0115] A second calling submodule, calling a second load balancing strategy corresponding to the second user service request;

[0116] The second resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the second load balancing strategy.

[0117] Among them, the second load balancing strategy refers to different resource allocation and simulation according to the test requirements (such as the need to simulate high concurrency or large data volume, etc.), and using corresponding load balancing strategies (such as polling, least connections, IP hashing, etc.) to evenly distribute test business requests to different resource nodes for processing.

[0118] In a specific application, the user service request is a third user service request;

[0119] The resource allocation module comprises:

[0120] A third calling submodule calls a third load balancing strategy corresponding to the third user service request;

[0121] The third resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the third load balancing strategy.

[0122] Among them, the third load balancing strategy refers to giving priority to system stability and throughput indicators based on the characteristics of management business requests, calling corresponding load balancing strategies (such as polling, least connections, IP hashing, etc.), and evenly distributing management business requests to different resource nodes for processing.

[0123] In a specific application, the user service request is a fourth user service request;

[0124] The resource allocation module comprises:

[0125] A fourth calling submodule, calling a fourth load balancing strategy corresponding to the fourth user service request;

[0126] The fourth resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the fourth load balancing strategy.

[0127] Among them, the fourth load balancing strategy refers to giving priority to resource utilization and deployment task priority according to the characteristics of deployment business requests, calling corresponding load balancing strategies (such as polling, least connections, IP hashing, etc.), and evenly distributing deployment business requests to different resource nodes for processing.

[0128] It can be understood that the embodiment of the present application achieves the purpose of dynamically allocating resource nodes based on resource monitoring data and user business requests based on a preset load balancing strategy. By calling different sub-modules to select different load balancing strategies, different load balancing strategies are selected for different types of user business requests to provide efficient, fast and high-quality services.

[0129] In an embodiment of the present application, a Paas platform based on cloud computing includes: a real-time monitoring module for monitoring resource monitoring data of the PaaS platform in real time; a load prediction module for inputting the resource monitoring data into a preset load prediction model to obtain a predicted load quantity; a resource management operation module for executing a resource management operation corresponding to the predicted load quantity based on the predicted load quantity; a first acquisition module for acquiring user business requests; and a resource allocation module for dynamically allocating resource nodes according to the resource monitoring data and the user business requests based on a preset load balancing strategy.

[0130] It can be seen that the embodiments of the present application realize dynamic resource increase and decrease and automatic load balancing, and the PaaS platform can allocate resources in real time according to the load conditions, improve resource utilization, avoid resource waste, and thus improve the overall resource management efficiency.

[0131] In addition, the embodiments of the present application can accurately understand the current status and resource requirements of the PaaS platform by real-time monitoring of resource monitoring data on the PaaS platform. By analyzing historical data and resource monitoring data, and combining with a preset load prediction model, it can predict future loads and output the predicted load quantity, providing an accurate basis for resource allocation. When the predicted load increases, the PaaS platform can automatically increase resources, such as virtual machine instances, storage capacity, etc., to meet user needs, ensure that the PaaS platform can dynamically expand resources, improve system performance and stability, and avoid resource waste. By obtaining user business requests, load distribution is automatically performed according to the characteristics of resource monitoring data and business requests to ensure load balancing between various resource nodes. By selecting appropriate load balancing strategies, such as polling, least connections, IP hashing, etc., optimal resource allocation can be achieved to improve system performance and user experience.

[0132] Figure 2 This is a schematic diagram of the structure of the server provided in the embodiment of the present application. Figure 2 As shown, the server 2 of this embodiment includes: at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the method steps of applying the above-mentioned cloud computing-based Pass platform are implemented.

[0133] The server 2 may be a computing device such as a cloud server. The server may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will appreciate that Figure 2It is only an example of server 2 and does not constitute a limitation on server 2. Server 2 may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0134] The processor 20 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0135] In some embodiments, the memory 21 may be an internal storage unit of the server 2, such as a hard disk or memory of the server 2. In other embodiments, the memory 21 may also be an external storage device of the server 2, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the server 2. Further, the memory 21 may also include both an internal storage unit of the server 2 and an external storage device. The memory 21 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 21 may also be used to temporarily store data that has been output or is to be output.

[0136] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0137] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method steps of applying the above-mentioned cloud computing-based Pass platform can be implemented.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the server, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0139] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A Paas platform based on cloud computing, characterized in that: include: Real-time monitoring module, used to monitor the resource monitoring data of Paas platform in real time; A load prediction module, used for inputting the resource monitoring data into a preset load prediction model to obtain a predicted load quantity; A resource management operation module, configured to perform a resource management operation corresponding to the predicted load quantity based on the predicted load quantity; A first acquisition module, used to acquire a user service request; A resource allocation module, configured to dynamically allocate resource nodes according to the resource monitoring data and the user service request based on a preset load balancing strategy; The preset load prediction model includes a preset input layer, a preset long-term and short-term network layer, a preset multi-layer perception layer and a preset output layer; The load prediction module comprises: A vectorization processing submodule, used for performing vectorization processing on the resource monitoring data according to a preset input layer to obtain a feature vector; A time correlation extraction submodule is used to extract the time correlation of the feature vector according to the preset long-term and short-term network layers to obtain the hidden state; A nonlinear transformation submodule, used for performing a nonlinear transformation on the hidden state according to a preset multi-layer perception layer to obtain a high-dimensional vector; A classification processing submodule, used for classifying the high-dimensional vector according to a preset output layer to obtain a predicted load quantity; Wherein, the classification processing submodule includes: The load prediction unit is used to obtain the predicted load quantity according to the following formula: ； ； ； ； in, Indicates Resource monitoring data, represents a vectorized function, represents the feature vector, Indicates the current time point The characteristic vector of Indicates the previous time point The hidden state of Represents the long short-term memory operation corresponding to the preset long short-term network layer, Indicates the current time point The hidden state of represents the weight matrix, represents the bias vector, Indicates the activation operation corresponding to the preset multi-layer perception layer, represents a high-dimensional vector, Indicates that the high-dimensional vector belongs to The scores of the categories, represents the total number of categories, Indicates the predicted load quantity.

2. The Paas platform based on cloud computing according to claim 1, characterized in that: The Paas platform based on cloud computing also includes: The second acquisition module is used to acquire historical training data; A preprocessing module, used for preprocessing the historical training data; An extraction module, used for extracting feature training data from the preprocessed historical training data; The training module is used to train the preset load prediction model based on the preset loss function and the characteristic training data to obtain the trained preset load prediction model.

3. The Paas platform based on cloud computing as claimed in claim 2, characterized in that: The preset loss function is: in, represents the preset loss function, represents the true value, represents the predicted value of the preset load prediction model, Indicates the sample size.

4. The cloud computing-based Paas platform of claim 1, characterized in that: The resource management operation module includes: A first resource management operation submodule, configured to perform a first resource management operation when the predicted load quantity is greater than a preset load quantity threshold; or, The second resource management operation submodule is used to perform a second resource management operation when the predicted load quantity is less than a preset load quantity threshold.

5. The Paas platform based on cloud computing according to claim 1, characterized in that: The user service request is a first user service request; The resource allocation module comprises: A first calling submodule, used to call a first load balancing strategy corresponding to the first user service request; The first resource allocation submodule is used to dynamically allocate resource nodes according to the resource monitoring data based on the first load balancing strategy.

6. The Paas platform based on cloud computing according to claim 1, characterized in that: The user service request is a second user service request; The resource allocation module comprises: A second calling submodule, calling a second load balancing strategy corresponding to the second user service request; The second resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the second load balancing strategy.

7. The Paas platform based on cloud computing according to claim 1, characterized in that: The user service request is a third user service request; The resource allocation module comprises: A third calling submodule calls a third load balancing strategy corresponding to the third user service request; The third resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the third load balancing strategy.

8. The Paas platform based on cloud computing according to claim 1, characterized in that: The user service request is a fourth user service request; The resource allocation module comprises: A fourth calling submodule, calling a fourth load balancing strategy corresponding to the fourth user service request; The fourth resource allocation submodule dynamically allocates resource nodes according to the resource monitoring data based on the fourth load balancing strategy.

Images