Block storage scheduling method, device, electronic device and storage medium

Abstract

The present application discloses a block storage scheduling method, device, electronic device, and computer-readable storage medium. The method includes: determining the influencing factors of block storage scheduling, calculating the correlation coefficient between each of the influencing factors and the scheduling time; determining the influencing factors whose correlation coefficient with the scheduling time is greater than a preset value as target influencing factors; obtaining the target influencing factors corresponding to this scheduling task, inputting the target influencing factors corresponding to this scheduling task into a trained deep neural network model, and obtaining the target node corresponding to this scheduling task. The block storage scheduling method provided in the present application comprehensively analyzes multiple influencing factors of block storage scheduling, introduces the correlation coefficients between the influencing factors and the scheduling time, analyzes and obtains the importance of each influencing factor, and on this basis uses a deep neural network to obtain the scheduling node of this scheduling task, thereby improving the accuracy of storage scheduling.

Description

Technical Field

[0001] The present application relates to the field of storage technology, and more specifically, to a block storage scheduling method and device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Cloud storage is an essential component of cloud computing. Cinder is the block storage module of OpenStack. Its default scheduling algorithm consists of two phases: filtering and weighing. Specifically, when a storage request arrives, a filtering process first selects nodes that meet the requirements. Each node has only two possible outcomes during the filtering process: those that meet the requirements are placed in a queue for weighing, while those that do not meet the requirements are eliminated. Weighing is then performed to sort the qualified nodes and select the most suitable node to service the request. The current filtering process verifies whether a node meets the requirements based on whether it has sufficient storage space to fulfill the storage request. If so, it is placed in a queue for use in the subsequent weighing process; otherwise, it is eliminated. The subsequent weighing process sorts qualified nodes based on their remaining storage space, selecting the node with the largest remaining storage space to provide the service.

[0003] However, current Cinder scheduling suffers from the following issues: The current scheduling method, which solely prioritizes remaining storage space, cannot guarantee the quality of cloud storage services. For example, if a physical node experiences severe network congestion but has the largest remaining storage space, Cinder will not recognize this and will still select that node to handle the storage request. However, due to the network congestion, the node is clearly not the most ideal service node, resulting in low block storage accuracy.

[0004] Therefore, how to improve the accuracy of block storage scheduling is a technical problem that those skilled in the art need to solve. Summary of the Invention

[0005] The purpose of the present application is to provide a block storage scheduling method, device, electronic device and computer-readable storage medium, which improve the accuracy of block storage scheduling.

[0006] To achieve the above objectives, the present application provides a block storage scheduling method, comprising:

[0007] Determining factors affecting block storage scheduling, and calculating a correlation coefficient between each of the factors and the scheduling time;

[0008] Determine an influencing factor whose correlation coefficient with the scheduling time is greater than a preset value as a target influencing factor;

[0009] Obtain the target influencing factors corresponding to this scheduling task, input the target influencing factors corresponding to this scheduling task into the trained deep neural network model, and obtain the target node corresponding to this scheduling task.

[0010] The correlation coefficient is specifically the Pearson product-moment correlation coefficient.

[0011] The step of calculating the correlation coefficient between each of the influencing factors and the scheduling time includes:

[0012] Constructing a calculation sample corresponding to a single influencing factor; wherein the value of the single influencing factor is different between different calculation samples, and the values ​​of other influencing factors are the same;

[0013] The Pearson product-moment correlation coefficient between the single influencing factor and the scheduling time is calculated based on the scheduling time of each calculation sample and the value of the single influencing factor.

[0014] The influencing factors include any one or a combination of any two of the node indicators, data indicators and network indicators.

[0015] The node indicators include any one or a combination of any two of the following: node failure rate, remaining storage space, and memory occupancy rate;

[0016] The data indicators include data transmission distance and / or data size;

[0017] The network indicators include node network bandwidth and / or network delay.

[0018] The target influencing factors corresponding to the current scheduling task are input into the trained deep neural network model to obtain the target node corresponding to the current scheduling task, including:

[0019] Determine the candidate nodes corresponding to this scheduling task;

[0020] Input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model to obtain the probability of each candidate node;

[0021] The candidate node with the highest probability is determined as the target node corresponding to the current scheduling task.

[0022] Among them, also include:

[0023] Obtaining training samples and determining a scheduling node corresponding to each training sample;

[0024] Initialize the deep neural network model, and train the deep neural network model using the training samples and the corresponding scheduling nodes to obtain a trained deep neural network model.

[0025] The initialization of the deep neural network model includes:

[0026] Determining the number of input nodes of the deep neural network model according to the number of the target influencing factors;

[0027] Determining the number of output nodes of the deep neural network model according to the number of candidate nodes;

[0028] The number of hidden layer nodes in the deep neural network model is determined based on the number of input nodes and the number of output nodes.

[0029] To achieve the above objectives, the present application provides a block storage scheduling device, comprising:

[0030] A calculation module, configured to determine factors influencing block storage scheduling and calculate a correlation coefficient between each of the influencing factors and the scheduling time;

[0031] A determination module, configured to determine an influencing factor whose correlation coefficient with the scheduling time is greater than a preset value as a target influencing factor;

[0032] The input module is used to obtain the target influencing factors corresponding to this scheduling task, input the target influencing factors corresponding to this scheduling task into the trained deep neural network model, and obtain the target node corresponding to this scheduling task.

[0033] To achieve the above objectives, the present application provides an electronic device, comprising:

[0034] memory for storing computer programs;

[0035] A processor is configured to implement the steps of the above-mentioned block storage scheduling method when executing the computer program.

[0036] To achieve the above objectives, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the block storage scheduling method described above are implemented.

[0037] From the above scheme, it can be seen that a block storage scheduling method provided by this application includes: determining the influencing factors of block storage scheduling, calculating the correlation coefficient between each of the influencing factors and the scheduling time; determining the influencing factors whose correlation coefficient with the scheduling time is greater than a preset value as target influencing factors; obtaining the target influencing factors corresponding to this scheduling task, and inputting the target influencing factors corresponding to this scheduling task into the trained deep neural network model to obtain the target node corresponding to this scheduling task.

[0038] The block storage scheduling method provided in this application comprehensively analyzes multiple factors influencing block storage scheduling, introduces the correlation coefficient between the influencing factors and the scheduling time, analyzes the importance of each influencing factor, and then uses a deep neural network to determine the scheduling node for the current scheduling task, thereby improving the accuracy of storage scheduling. This application also discloses a block storage scheduling device, an electronic device, and a computer-readable storage medium, which can also achieve the above technical effects.

[0039] It should be understood that the foregoing general description and the following detailed description are merely illustrative and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the embodiments or the description of the prior art. 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 creative work. The drawings are used to provide a further understanding of the present disclosure and constitute part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure, but do not constitute a limitation of the present disclosure. In the drawings:

[0041] Figure 1 is a flowchart of a block storage scheduling method according to an exemplary embodiment;

[0042] Figure 2 is a flowchart of another block storage scheduling method according to an exemplary embodiment;

[0043] Figure 3 is a structural diagram of a block storage scheduling device according to an exemplary embodiment;

[0044] Figure 4 The figure is a structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. In addition, in the embodiments of the present application, "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0046] The embodiment of the present application discloses a block storage scheduling method, which improves the accuracy of block storage scheduling.

[0047] See also Figure 1 , according to an exemplary embodiment, a flowchart of a block storage scheduling method is shown, such as Figure 1 Shown, including:

[0048] S101: Determine influencing factors of block storage scheduling, and calculate the correlation coefficient between each influencing factor and scheduling time;

[0049] In this embodiment, a comprehensive analysis is performed on multiple influencing factors of block storage scheduling, where the influencing factors include node indicators, data indicators, and network indicators. Node indicators include node failure rate, remaining storage space, memory occupancy, etc. Data indicators include data transmission distance, data size, etc. Network indicators include node network bandwidth, network delay, etc.

[0050] It should be noted that taking all of the above factors into account will greatly increase the difficulty of indicator collection, thereby indirectly affecting scheduling speed. Therefore, in this step, the correlation between each influencing factor and scheduling time is analyzed. In other words, the correlation coefficient between each influencing factor and scheduling time is calculated to identify the factors that have a significant impact on block storage scheduling.

[0051] Preferably, the correlation coefficient is specifically the Pearson product-moment correlation coefficient, and the formula is as follows:

[0052]

[0053] Among them, for a single influencing factor, γ represents the Pearson product-moment correlation coefficient between the single influencing factor and the scheduling time, n represents n samples, and x i Represents the specific value of the influencing factor in the i-th sample, Represents the average value of the influencing factor, y i Indicates the scheduling time of the i-th sample when this influencing factor is added, Represents the average scheduling time of n samples.

[0054] In a specific implementation, a calculation sample corresponding to a single influencing factor is constructed; wherein, the numerical value of the single influencing factor is different between different calculation samples, and the numerical values ​​of other influencing factors are the same; based on the scheduling time of each of the calculation samples and the numerical value of the single influencing factor, the Pearson product-moment correlation coefficient between the single influencing factor and the scheduling time is calculated.

[0055] S102: determining an influencing factor whose correlation coefficient with the scheduling time is greater than a preset value as a target influencing factor;

[0056] In a specific implementation, the influencing factors whose correlation coefficient with the scheduling time is greater than a preset value are determined as target influencing factors for participating in this scheduling task. The specific value of the preset value is not limited here, for example, it can be set to 0.8.

[0057] S103: Obtain the target influencing factors corresponding to the current scheduling task, input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model, and obtain the target node corresponding to the current scheduling task.

[0058] In the specific implementation, the candidate nodes corresponding to this scheduling task are determined, the target influencing factors corresponding to this scheduling task are input into the trained deep neural network model, the probability of each candidate node is obtained, and the candidate node with the largest probability is determined as the target node corresponding to the scheduling task.

[0059] The block storage scheduling method provided in the embodiment of the present application comprehensively analyzes multiple influencing factors of block storage scheduling, introduces the correlation coefficient between the influencing factors and the scheduling time, analyzes the importance of each influencing factor, and uses a deep neural network to obtain the scheduling node of this scheduling task on this basis, thereby improving the accuracy of storage scheduling.

[0060] This example will introduce the training process of a deep neural network model, specifically:

[0061] See also Figure 2 , according to an exemplary embodiment, a flowchart of another block storage scheduling method is shown, such as Figure 2 Shown, including:

[0062] S201: Acquire training samples and determine the scheduling node corresponding to each training sample;

[0063] S202: Initialize the deep neural network model, and train the deep neural network model using the training samples and the corresponding scheduling nodes to obtain a trained deep neural network model.

[0064] The deep neural network model initialized in this embodiment can be a BP (back propagation) neural network. The hierarchical structure of this neural network can be expressed as three layers: input layer, hidden layer and output layer. There can be more than one hidden layer, which is set according to the specific needs of the network.

[0065] As a feasible implementation method, the initialization of the deep neural network model includes: determining the number of input nodes of the deep neural network model according to the number of target influencing factors; determining the number of output nodes of the deep neural network model according to the number of candidate nodes; and determining the number of hidden layer nodes in the deep neural network model according to the number of input nodes and the number of output nodes.

[0066] In the specific implementation, the number of input layer nodes is the dimension of the training sample, that is, the number of target influencing factors selected in the previous embodiment. The number of output nodes is the scheduling result of the block storage, that is, the number of candidate nodes. The number of hidden layer nodes is determined according to the empirical formula of the number of hidden layer nodes in the neural network:

[0067]

[0068] Where m is the number of input nodes, n is the number of output nodes, and the hyperparameter α is a random integer between 1 and 10. Repeated training and comparison of the model revealed that a BP neural network with 4 hidden layer nodes achieved the lowest error and the best approximation effect on the sample. Therefore, in this embodiment, the number of hidden layer nodes can be set to 4.

[0069] After initializing the deep neural network model, the training samples and the corresponding scheduling nodes are used to obtain the trained deep neural network model. The trained deep neural network model is used for scheduling block storage.

[0070] A block storage scheduling device provided in an embodiment of the present application is introduced below. The block storage scheduling device described below and the block storage scheduling method described above can be referenced to each other.

[0071] See also Figure 3 , according to an exemplary embodiment, a structural diagram of a block storage scheduling device is shown, such as Figure 3 Shown, including:

[0072] A calculation module 301 is used to determine the influencing factors of block storage scheduling and calculate the correlation coefficient between each of the influencing factors and the scheduling time;

[0073] A determination module 302 is configured to determine an influencing factor having a correlation coefficient with the scheduling time greater than a preset value as a target influencing factor;

[0074] The input module 303 is used to obtain the target influencing factors corresponding to the current scheduling task, input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model, and obtain the target node corresponding to the current scheduling task.

[0075] The block storage scheduling device provided in the embodiment of the present application comprehensively analyzes multiple influencing factors of block storage scheduling, introduces the correlation coefficient between the influencing factors and the scheduling time, analyzes the importance of each influencing factor, and uses a deep neural network to obtain the scheduling node of this scheduling task on this basis, thereby improving the accuracy of storage scheduling.

[0076] Based on the above embodiment, as a preferred implementation, the correlation coefficient is specifically a Pearson product-moment correlation coefficient.

[0077] Based on the above embodiment, as a preferred implementation, the calculation module 301 includes:

[0078] a first determining unit, configured to determine factors influencing block storage scheduling;

[0079] A construction unit, configured to construct a calculation sample corresponding to a single influencing factor; wherein the value of the single influencing factor is different between different calculation samples, and the values ​​of other influencing factors are the same;

[0080] A calculation unit is used to calculate the Pearson product-moment correlation coefficient between the single influencing factor and the scheduling time based on the scheduling time of each calculation sample and the value of the single influencing factor.

[0081] Based on the above embodiment, as a preferred implementation, the influencing factors include any one or a combination of any several of the node indicators, data indicators and network indicators;

[0082] The node indicators include any one or a combination of any two of the following: node failure rate, remaining storage space, and memory occupancy rate;

[0083] The data indicators include data transmission distance and / or data size;

[0084] The network indicators include node network bandwidth and / or network delay.

[0085] Based on the above embodiment, as a preferred implementation, the input module 303 includes:

[0086] An acquisition unit is used to obtain the target influencing factors corresponding to this scheduling task;

[0087] The second determining unit is used to determine the candidate node corresponding to the current scheduling task;

[0088] An input unit, configured to input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model to obtain the probability of each candidate node;

[0089] The third determining unit is configured to determine the candidate node with the highest probability as the target node corresponding to the current scheduling task.

[0090] Based on the above embodiment, as a preferred implementation, it further includes:

[0091] An acquisition module, configured to acquire training samples and determine a scheduling node corresponding to each training sample;

[0092] The training module is used to initialize the deep neural network model, train the deep neural network model using the training samples and the corresponding scheduling nodes, and obtain a trained deep neural network model.

[0093] Based on the above embodiment, as a preferred implementation, the training module includes:

[0094] a fourth determining unit, configured to determine the number of input nodes of the deep neural network model according to the number of the target influencing factors;

[0095] a fifth determining unit, configured to determine the number of output nodes of the deep neural network model according to the number of candidate nodes;

[0096] a sixth determining unit, configured to determine the number of hidden layer nodes in the deep neural network model according to the number of input nodes and the number of output nodes;

[0097] A training unit is used to train the deep neural network model using the training samples and the corresponding scheduling nodes to obtain a trained deep neural network model.

[0098] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0099] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiment of the present application, the embodiment of the present application further provides an electronic device, Figure 4 FIG. 1 is a structural diagram of an electronic device according to an exemplary embodiment. Figure 4 As shown, the electronic equipment includes:

[0100] Communication interface 1, capable of exchanging information with other devices such as network devices;

[0101] The processor 2 is connected to the communication interface 1 to implement information exchange with other devices and is used to execute the block storage scheduling method provided by one or more of the above technical solutions when running a computer program. The computer program is stored in the memory 3.

[0102] Of course, in actual application, the various components in the electronic device are coupled together through the bus system 4. It can be understood that the bus system 4 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 4 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 4 Various buses are labeled as bus system 4.

[0103] The memory 3 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device. Examples of such data include: any computer program used to operate on the electronic device.

[0104] It is understood that the memory 3 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a magnetic disk memory or a magnetic tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memory 2 described in the embodiments of the present application is intended to include but is not limited to these and any other suitable types of memory.

[0105] The method disclosed in the above-mentioned embodiment of the present application can be applied to processor 2 or implemented by processor 2. Processor 2 may be an integrated circuit chip with signal processing capabilities. During the implementation process, each step of the above-mentioned method can be completed by the integrated logic circuit of the hardware in processor 2 or instructions in the form of software. The above-mentioned processor 2 can be a general-purpose processor, DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 2 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in memory 3. Processor 2 reads the program in memory 3 and completes the steps of the above-mentioned method in combination with its hardware.

[0106] When the processor 2 executes the program, the corresponding processes in the various methods of the embodiments of the present application are implemented. For the sake of brevity, they are not repeated here.

[0107] In an exemplary embodiment, the present application also provides a storage medium, namely, a computer storage medium, specifically a computer-readable storage medium, such as a memory 3 storing a computer program. The computer program can be executed by a processor 2 to perform the steps of the aforementioned method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface storage, optical disk, or CD-ROM.

[0108] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, ROM, RAM, disks or optical disks, etc. Various media that can store program codes.

[0109] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0110] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A block storage scheduling method, characterized in that: include: Determining factors affecting block storage scheduling, and calculating a correlation coefficient between each of the factors and the scheduling time; Determine an influencing factor whose correlation coefficient with the scheduling time is greater than a preset value as a target influencing factor; Obtain the target influencing factors corresponding to the current scheduling task, input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model, and obtain the target node corresponding to the current scheduling task; Among them, also include: Obtaining training samples and determining a scheduling node corresponding to each training sample; Initializing a deep neural network model, and training the deep neural network model using the training samples and the corresponding scheduling nodes to obtain a trained deep neural network model; wherein the deep neural network model is a BP neural network, and the hierarchical structure of the deep neural network model includes an input layer, multiple hidden layers, and an output layer; The initialization of the deep neural network model includes: Determining the number of input nodes of the deep neural network model according to the number of the target influencing factors; Determining the number of output nodes of the deep neural network model according to the number of candidate nodes; The number of hidden layer nodes in the deep neural network model is determined based on the number of input nodes and the number of output nodes.

2. The block storage scheduling method according to claim 1, characterized in that: The correlation coefficient is specifically the Pearson product-moment correlation coefficient.

3. The block storage scheduling method according to claim 2, characterized in that: The calculating of the correlation coefficient between each of the influencing factors and the scheduling time includes: Constructing a calculation sample corresponding to a single influencing factor; wherein the value of the single influencing factor is different between different calculation samples, and the values ​​of other influencing factors are the same; The Pearson product-moment correlation coefficient between the single influencing factor and the scheduling time is calculated based on the scheduling time of each calculation sample and the value of the single influencing factor.

4. The block storage scheduling method according to claim 1, characterized in that: The influencing factors include any one or a combination of node indicators, data indicators and network indicators; The node indicators include any one or a combination of any two of the following: node failure rate, remaining storage space, and memory occupancy rate; The data indicators include data transmission distance and / or data size; The network indicators include node network bandwidth and / or network delay.

5. The block storage scheduling method according to claim 1, characterized in that: Input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model to obtain the target node corresponding to the current scheduling task, including: Determine the candidate nodes corresponding to this scheduling task; Input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model to obtain the probability of each candidate node; The candidate node with the highest probability is determined as the target node corresponding to the current scheduling task.

6. A block storage scheduling device, characterized in that: include: A calculation module, configured to determine factors influencing block storage scheduling and calculate a correlation coefficient between each of the influencing factors and the scheduling time; A determination module, configured to determine an influencing factor whose correlation coefficient with the scheduling time is greater than a preset value as a target influencing factor; An input module is used to obtain the target influencing factors corresponding to the current scheduling task, input the target influencing factors corresponding to the current scheduling task into the trained deep neural network model, and obtain the target node corresponding to the current scheduling task; Among them, also include: An acquisition module, configured to acquire training samples and determine a scheduling node corresponding to each training sample; A training module, configured to initialize a deep neural network model, train the deep neural network model using the training samples and the corresponding scheduling nodes, and obtain a trained deep neural network model; wherein the deep neural network model is a BP neural network, and the hierarchical structure of the deep neural network model includes an input layer, multiple hidden layers, and an output layer; Wherein, the training module includes: a fourth determining unit, configured to determine the number of input nodes of the deep neural network model according to the number of the target influencing factors; a fifth determining unit, configured to determine the number of output nodes of the deep neural network model according to the number of candidate nodes; a sixth determining unit, configured to determine the number of hidden layer nodes in the deep neural network model according to the number of input nodes and the number of output nodes; A training unit is used to train the deep neural network model using the training samples and the corresponding scheduling nodes to obtain a trained deep neural network model.

7. An electronic device, characterized in that: include: memory for storing computer programs; A processor, configured to implement the steps of the block storage scheduling method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the block storage scheduling method according to any one of claims 1 to 5.

Images