Resource scheduling method and device, electronic equipment and storage medium

By filtering and preprocessing CPU usage data, the problem of CPU usage being affected by temperature and cores is solved, the accuracy and efficiency of resource scheduling are improved, and the resource utilization is optimized.

CN118939372APending Publication Date: 2024-11-12CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410989389.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, the CPU usage rate is affected by the CPU temperature and number of cores, resulting in slow resource calculation rate, inaccurate calculation results, and low resource utilization rate, resulting in low network resource scheduling efficiency.

Method used

By obtaining the timing information of the usage data, calculating the usage null value ratio, filtering the processing to obtain the target usage sequence, determining whether it is greater than the usage peak and duration, and pre-processing is performed to optimize resource scheduling.

Benefits of technology

It improves the timeliness and accuracy of resource scheduling, reduces the complexity of resource scheduling, avoids the long-term low CPU usage rate, and optimizes the equipment loss rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118939372A_ABST
    Figure CN118939372A_ABST
Patent Text Reader

Abstract

According to the resource scheduling method and device, the electronic equipment and the storage medium provided by the invention, the obtained utilization rate data are arranged according to the time sequence information corresponding to the utilization rate data to obtain the utilization rate sequence, and the utilization rate null value ratio is calculated; whether the utilization rate null value ratio is larger than a preset null value ratio threshold value or not is judged, the utilization rate sequence is screened according to the judgment result, and a target utilization rate sequence is obtained; judging whether the target usage rate data is greater than a usage rate peak value and whether the first time is greater than a preset time threshold value; if the target usage rate data is greater than a usage rate peak value and the first time is greater than a preset time threshold value, preprocessing the target usage rate sequence to obtain a preprocessing result; and under the condition of determining that the target utilization rate data is not reduced according to the preprocessing result, performing resource scheduling processing on the target equipment. The CPU usage rate which is larger than the usage rate peak value and lasts for a long time is preprocessed, and resource scheduling is carried out according to the preprocessing result, so that the accuracy of resource scheduling is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a resource scheduling method and device, an electronic device, and a storage medium. Background Art

[0002] With the further development of cloud computing technology, much of the information of network servers is stored in container clouds, making resource management issues increasingly prominent. The average resource utilization rate of resources in container clouds is low, and most servers are idle, but they consume a lot of power, resulting in high energy consumption and low efficiency of existing network resource scheduling.

[0003] The CPU resource calculation is usually carried out by obtaining the instantaneous value of the CPU utilization of the virtual machine to be detected within a preset time, and using array transformation to calculate the stored instantaneous value to obtain the peak value of the CPU utilization; and performing data processing on the peak value of the CPU utilization to obtain the final value of the CPU utilization that characterizes the computing resources of the virtual machine, thereby reflecting the usage of the computing resources, so as to perform resource scheduling according to the usage of the resources.

[0004] However, the CPU resource calculation solution in the prior art has a slow resource calculation rate and inaccurate resource calculation results because the CPU utilization rate is affected by the CPU temperature, the number of cores, etc., and the CPU utilization rate may be low for a long time. Summary of the invention

[0005] The present disclosure provides a method and device for resource scheduling, an electronic device and a storage medium. The main purpose is to solve the problem of a CPU resource calculation solution in the prior art that the CPU utilization rate is affected by the CPU temperature, the number of cores, etc., and the CPU utilization rate may be low for a long time, which may lead to a slow resource calculation rate and inaccurate resource calculation results.

[0006] According to a first aspect of the present disclosure, a method for resource scheduling is provided, comprising:

[0007] Arrange the acquired usage rate data according to the time series information corresponding to each of the usage rate data to obtain a usage rate sequence, and calculate the usage rate null value ratio in the usage rate sequence; wherein the usage rate null value ratio is the ratio between the usage rate data greater than a first preset threshold and all the usage rate data in the usage rate sequence;

[0008] Determine whether the usage rate to null value ratio is greater than a preset null value ratio threshold, and filter the usage rate sequence according to the determination result to obtain a target usage rate sequence;

[0009] Determine whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than a preset time threshold; wherein the target usage rate data is any usage rate data in the target usage rate sequence, and the first time is obtained according to the number of target usage rate data that are continuously greater than the usage rate peak value;

[0010] When the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold, adding the target usage rate sequence to a preprocessing queue for preprocessing operation to obtain a preprocessing result;

[0011] When it is determined according to the preprocessing result that the target usage rate data has not decreased, a target device is added to a scheduling stack for resource scheduling processing, wherein the target device is a device that generates the usage rate data.

[0012] Optionally, calculating the usage rate null value ratio in the usage rate series includes:

[0013] Acquire the quantity of the usage rate data in the usage rate series to obtain a first data quantity;

[0014] Acquire the number of usage rate data in the usage rate series that is not greater than the first preset threshold value to obtain a second data number;

[0015] The second data quantity is divided by the first data quantity to obtain the usage rate-to-null ratio.

[0016] Optionally, the filtering the usage rate sequence according to the judgment result to obtain the target usage rate sequence includes:

[0017] When the usage rate to empty value ratio is greater than or equal to the preset empty value ratio threshold, the usage rate data in the usage rate sequence that is less than a first usage rate threshold is deleted to obtain the target usage rate sequence; wherein the first usage rate threshold is calculated by the usage rate peak value;

[0018] When the usage rate null value ratio is less than the preset null value ratio threshold, the usage data in the usage rate sequence that is less than the second usage rate threshold is deleted to obtain the target usage rate sequence; wherein the second usage rate threshold is obtained by calculating the average value of all the usage data in the usage rate sequence.

[0019] Optionally, the determining whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than a preset time threshold includes:

[0020] Setting a sliding window representing a time period, wherein the width of the sliding window is used to represent the time during which the target usage rate data is continuously greater than the usage rate peak value;

[0021] Traversing the target usage rate sequence, fixing the left side of the sliding window at the first target usage rate data; wherein the first target usage rate data is the target usage rate data in the target usage rate sequence that is greater than the usage rate peak value for the first time;

[0022] When the second target usage rate data is greater than the usage rate peak value, slide the right side of the sliding window to the right, and continue to traverse the target usage rate sequence to obtain the target width of the sliding window; wherein the second target usage rate data is the target usage rate data adjacent to the right side of the first target usage rate data in the target usage rate sequence;

[0023] When the second target usage rate data is not greater than the usage rate peak value, adding the second target usage rate data to the backup data sequence;

[0024] Determining whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtaining the target width according to the determination result;

[0025] When the target width is greater than the preset time threshold, it is determined that the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold.

[0026] Optionally, judging whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtaining the target width according to the judging result includes:

[0027] Adding a preset number of backup usage rate data to the backup data sequence; wherein the backup usage rate data is the preset number of target usage rate data adjacent to the right of the second target usage rate data in the target usage rate sequence;

[0028] Acquire the number of the backup usage rate data in the backup data sequence that is greater than the usage rate peak value to obtain a third data number, and calculate the average value of all the backup usage rate data in the backup data sequence to obtain a first average value data;

[0029] When the first average value data is not greater than the first usage rate threshold, and the third data quantity is not greater than the preset quantity threshold, the right side of the sliding window is kept stationary to obtain the target width, and the backup data sequence is cleared;

[0030] When the first average value data is greater than the first usage threshold, or the third data quantity is greater than the preset quantity threshold, the right side of the sliding window is slid to the right, and the target usage sequence is continued to be traversed to obtain the target width of the sliding window.

[0031] Optionally, before adding the target usage rate sequence to a preprocessing queue for preprocessing to obtain a preprocessing result, the method further includes:

[0032] Obtaining all influencing factors affecting the target usage rate data, and obtaining an initial confidence level corresponding to each of the influencing factors;

[0033] Predicting the main influencing factors among the influencing factors by a preset probability algorithm, and performing resource scheduling processing on the designated target usage rate data according to the main influencing factors to obtain a first scheduling result; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage rate data, and the designated target usage rate data is the target usage rate data that is greater than the usage rate peak value;

[0034] In the case where the first scheduling result indicates that the designated target usage rate data is less than the usage rate peak, the initial confidence corresponding to the main influencing factor is updated to a first confidence, and the initial confidence corresponding to other influencing factors is updated to a second confidence; wherein the other influencing factors are all influencing factors except the main influencing factor among the influencing factors;

[0035] Calculating a first feedback coefficient according to the first confidence level, and updating the usage peak according to the first feedback coefficient to obtain an updated usage peak; wherein the updated usage peak is used as a parameter for resource scheduling of a usage sequence at a next adjacent moment of the target usage sequence;

[0036] When the first scheduling result indicates that the designated target usage rate data is not less than the usage rate peak, updating the initial confidence level corresponding to the main influencing factor to a third confidence level, and updating the initial confidence levels corresponding to other influencing factors to a fourth confidence level;

[0037] A second feedback coefficient is calculated according to the third confidence level, and the usage peak value is updated according to the second feedback coefficient to obtain the updated usage peak value.

[0038] Optionally, the adding the target usage rate sequence to a preprocessing queue for preprocessing operation to obtain a preprocessing result includes:

[0039] Acquire all influencing factors that affect the target usage rate data, and predict the main influencing factors among the influencing factors through a preset probability algorithm; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage rate data;

[0040] Merging all the target usage rate data in the target usage rate sequence to obtain merged data;

[0041] The combined data is subjected to resource scheduling processing according to the main influencing factors to obtain the preprocessing result.

[0042] Optionally, after adding the target usage rate sequence to a preprocessing queue for preprocessing and obtaining a preprocessing result, the method further includes:

[0043] In the case where it is determined according to the preprocessing result that the target usage rate data is reduced, resource scheduling processing is performed on the merged data according to the main influencing factors, and the target usage rate sequence is deleted from the preprocessing queue.

[0044] Optionally, before determining whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, the method further includes:

[0045] Determine whether a historical usage peak value is obtained; wherein the historical usage peak value is obtained by updating the usage sequence at the previous adjacent moment of the target usage sequence during the resource scheduling process through a feedback coefficient;

[0046] When the historical usage peak value is obtained, the historical usage peak value is used as the usage peak value;

[0047] When the historical usage peak value is not obtained, a preset usage peak value is obtained as the usage peak value.

[0048] According to a second aspect of the present disclosure, a resource scheduling device is provided, including:

[0049] An arranging unit, configured to arrange the acquired usage rate data according to the time series information corresponding to each of the usage rate data to obtain a usage rate sequence;

[0050] A calculation unit, used to calculate the usage rate null value ratio in the usage rate sequence; wherein the usage rate null value ratio is the ratio between the usage rate data greater than a first preset threshold and all the usage rate data in the usage rate sequence;

[0051] a screening unit, configured to determine whether the usage rate to null value ratio is greater than a preset null value ratio threshold, and to screen the usage rate sequence according to the determination result to obtain a target usage rate sequence;

[0052] A first judgment unit is used to judge whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than a preset time threshold; wherein the target usage rate data is any usage rate data in the target usage rate sequence, and the first time is obtained according to the number of target usage rate data that are continuously greater than the usage rate peak value;

[0053] an adding unit, configured to add the target usage rate sequence to a preprocessing queue for preprocessing operation to obtain a preprocessing result when the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold;

[0054] The scheduling unit is used to add the target device to the scheduling stack for resource scheduling processing when it is determined according to the preprocessing result that the target usage data has not decreased, wherein the target device is the device that generates the usage data.

[0055] Optionally, the computing unit includes:

[0056] An acquisition module, used for acquiring the quantity of the usage rate data in the usage rate series to obtain a first data quantity;

[0057] The acquisition module is further used to acquire the number of usage rate data that is not greater than the first preset threshold in the usage rate series to obtain a second data number;

[0058] A calculation module is used to divide the second data quantity and the first data quantity to obtain the usage rate null value ratio.

[0059] Optionally, the screening unit is further used for:

[0060] When the usage rate to empty value ratio is greater than or equal to the preset empty value ratio threshold, the usage rate data in the usage rate sequence that is less than a first usage rate threshold is deleted to obtain the target usage rate sequence; wherein the first usage rate threshold is calculated by the usage rate peak value;

[0061] When the usage rate null value ratio is less than the preset null value ratio threshold, the usage data in the usage rate sequence that is less than the second usage rate threshold is deleted to obtain the target usage rate sequence; wherein the second usage rate threshold is obtained by calculating the average value of all the usage data in the usage rate sequence.

[0062] Optionally, the first judging unit includes:

[0063] A setting module, used to set a sliding window representing a time period, wherein the width of the sliding window is used to represent the time during which the target usage rate data is continuously greater than the usage rate peak value;

[0064] A fixing module, used for traversing the target usage rate sequence and fixing the left side of the sliding window at the first target usage rate data; wherein the first target usage rate data is the target usage rate data in the target usage rate sequence that is greater than the usage rate peak value for the first time;

[0065] a sliding module, configured to slide the right side of the sliding window to the right and continue to traverse the target usage rate sequence to obtain a target width of the sliding window when the second target usage rate data is greater than the usage rate peak value; wherein the second target usage rate data is the target usage rate data adjacent to the right side of the first target usage rate data in the target usage rate sequence;

[0066] An adding module, configured to add the second target usage rate data to the backup data sequence when the second target usage rate data is not greater than the usage rate peak value;

[0067] The sliding module is further used to determine whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtain the target width according to the determination result;

[0068] A determination module is used to determine, when the target width is greater than the preset time threshold, that the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold.

[0069] Optionally, the sliding module is also used for:

[0070] Adding a preset number of backup usage rate data to the backup data sequence; wherein the backup usage rate data is the preset number of target usage rate data adjacent to the right of the second target usage rate data in the target usage rate sequence;

[0071] Acquire the number of the backup usage rate data in the backup data sequence that is greater than the usage rate peak value to obtain a third data number, and calculate the average value of all the backup usage rate data in the backup data sequence to obtain a first average value data;

[0072] When the first average value data is not greater than the first usage rate threshold, and the third data quantity is not greater than the preset quantity threshold, the right side of the sliding window is kept stationary to obtain the target width, and the backup data sequence is cleared;

[0073] When the first average value data is greater than the first usage threshold, or the third data quantity is greater than the preset quantity threshold, the right side of the sliding window is slid to the right, and the target usage sequence is continued to be traversed to obtain the target width of the sliding window.

[0074] Optionally, the device further comprises:

[0075] An acquisition unit, used to acquire all influencing factors affecting the target usage rate data, and acquire an initial confidence level corresponding to each of the influencing factors;

[0076] a processing unit, configured to predict the main influencing factor among the influencing factors by a preset probability algorithm, and perform resource scheduling processing on the designated target usage rate data according to the main influencing factor to obtain a first scheduling result; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage rate data, and the designated target usage rate data is the target usage rate data that is greater than the usage rate peak value;

[0077] an updating unit, configured to update the initial confidence corresponding to the main influencing factor to a first confidence, and update the initial confidence corresponding to other influencing factors to a second confidence, when the first scheduling result indicates that the designated target usage rate data is less than the usage rate peak; wherein the other influencing factors are all influencing factors among the influencing factors except the main influencing factor;

[0078] The updating unit is further configured to calculate a first feedback coefficient according to the first confidence level, and to update the usage peak value according to the first feedback coefficient to obtain an updated usage peak value; wherein the updated usage peak value is used as a parameter for resource scheduling processing of a usage sequence at a next adjacent moment of the target usage sequence;

[0079] The updating unit is further configured to, when the first scheduling result indicates that the designated target usage rate data is not less than the usage rate peak value, update the initial confidence corresponding to the main influencing factor to a third confidence, and update the initial confidence corresponding to other influencing factors to a fourth confidence;

[0080] The updating unit is further configured to calculate a second feedback coefficient according to the third confidence level, and update the usage peak value according to the second feedback coefficient to obtain the updated usage peak value.

[0081] Optionally, the adding unit includes:

[0082] An acquisition module, used to acquire all influencing factors affecting the target usage rate data, and predict the main influencing factors among the influencing factors through a preset probability algorithm; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage rate data;

[0083] A merging module, used for merging all the target usage rate data in the target usage rate sequence to obtain merged data;

[0084] The scheduling module is used to perform resource scheduling processing on the merged data according to the main influencing factors to obtain the preprocessing result.

[0085] Optionally, the scheduling unit is further used to, when it is determined according to the preprocessing result that the target usage data is reduced, perform resource scheduling processing on the merged data according to the main influencing factors, and delete the target usage sequence from the preprocessing queue.

[0086] Optionally, the device further comprises:

[0087] A second judgment unit is used to judge whether a historical usage peak value is obtained; wherein the historical usage peak value is obtained by updating the usage sequence at the previous adjacent moment of the target usage sequence during the resource scheduling process through a feedback coefficient;

[0088] a determining unit, configured to, when the historical usage peak value is obtained, use the historical usage peak value as the usage peak value;

[0089] The determining unit is further configured to, when the historical usage peak value is not obtained, obtain a preset usage peak value as the usage peak value.

[0090] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0091] at least one processor; and

[0092] a memory communicatively connected to the at least one processor; wherein,

[0093] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0094] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0095] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.

[0096] The resource scheduling method and device, electronic device and storage medium provided by the present disclosure arrange the acquired usage data according to the time series information corresponding to each of the usage data to obtain a usage sequence, and calculate the usage null value ratio in the usage sequence; wherein the usage null value ratio is the ratio between the usage data greater than a first preset threshold and all the usage data in the usage sequence; judge whether the usage null value ratio is greater than a preset null value ratio threshold, and filter the usage sequence according to the judgment result to obtain a target usage sequence; judge whether the target usage data in the target usage sequence is greater than the usage peak value, and the first Whether the time is greater than a preset time threshold; wherein the target usage data is any usage data in the target usage sequence, and the first time is obtained according to the number of target usage data that are continuously greater than the usage peak; when the target usage data is greater than the usage peak, and the first time is greater than the preset time threshold, the target usage sequence is added to the preprocessing queue for preprocessing operations to obtain a preprocessing result; when it is determined according to the preprocessing result that the target usage data has not decreased, the target device is added to the scheduling stack for resource scheduling processing, wherein the target device is the device that generates the usage data. Compared with the related art, the embodiment of the present disclosure can avoid the situation where the CPU usage is low for a long time by filtering out points where the CPU usage is low for a long time, and mainly preprocessing the CPU usage that is greater than the usage peak and lasts for a long time, and performing resource scheduling according to the preprocessing result, thereby reducing the complexity of resource scheduling, and improving the timeliness of resource scheduling and the accuracy of resource scheduling results.

[0097] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0099] Figure 1 A schematic diagram of a resource scheduling method provided by an embodiment of the present disclosure;

[0100] Figure 2 A schematic diagram of the principle of a resource scheduling method provided by an embodiment of the present disclosure;

[0101] Figure 3 A schematic diagram of a calculation flow of a utilization rate to null value ratio provided by an embodiment of the present disclosure;

[0102] Figure 4 A schematic diagram of a screening process of a usage rate sequence provided by an embodiment of the present disclosure;

[0103] Figure 5 A flowchart of a method for determining a first time provided by an embodiment of the present disclosure;

[0104] Figure 6 A flowchart of another method for determining a first time provided by an embodiment of the present disclosure;

[0105] Figure 7 A schematic diagram of a flow chart of a dynamic sliding window computing resource allocation evaluation index provided by an embodiment of the present disclosure;

[0106] Figure 8 A flowchart of a method for updating a usage rate peak value provided by an embodiment of the present disclosure;

[0107] Fig. 9 A schematic diagram of the structure of a resource scheduling device provided by an embodiment of the present disclosure;

[0108] Fig.10 A schematic diagram of the structure of another resource scheduling device provided by an embodiment of the present disclosure;

[0109] Fig.11 A schematic block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0110] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0111] The resource scheduling method, apparatus, electronic device, and storage medium of the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0112] Figure 1 A flowchart of a resource scheduling method provided in an embodiment of the present disclosure.

[0113] like Figure 1 As shown, the method comprises the following steps:

[0114] Step 101, arrange the acquired usage data according to the timing information corresponding to each of the usage data to obtain a usage sequence, and calculate the usage null value ratio in the usage series; wherein the usage null value ratio is the ratio between the usage data greater than a first preset threshold and all the usage data in the usage sequence.

[0115] In the embodiments of the present disclosure, the usage data includes but is not limited to: CPU usage, the timing information is the time when the usage data is generated, the CPU usage is an indicator to measure the busyness of the computer central processing unit (CPU), indicating the relative frequency or intensity of requests processed and tasks executed by the CPU over a period of time, and the CPU usage is usually expressed as a percentage. In order to facilitate the description of the embodiments of the present disclosure, the usage data is described using the CPU usage as an example, and the timing information is described using the time when the CPU usage is generated as an example.

[0116] The usage sequence may be in the form of an array, a sequence, etc. When performing the usage data, the usage data may be implemented in the following manner, but not limited to: storing the CPU usage (usage data) in an array C (usage sequence) in time sequence, where C = [c1, c2, ..., c n ].

[0117] In order to avoid a long period of low CPU usage (usage data) which affects the effect of resource scheduling, it is necessary to filter the usage data. By calculating the usage-to-null value ratio and based on the size of the usage-to-null value ratio, the filtering conditions corresponding to filtering the usage data can be determined to accurately filter the usage data.

[0118] Step 102, determining whether the usage rate to empty value ratio is greater than a preset empty value ratio threshold, and screening the usage rate sequence according to the determination result to obtain a target usage rate sequence.

[0119] In the embodiment of the present disclosure, the preset null value ratio threshold is a custom-set value, such as 0.5, 0.6, etc. Specifically, the embodiment of the present disclosure does not limit the setting of the preset null value ratio threshold.

[0120] Among them, the judgment result includes: the usage rate empty value ratio is greater than the preset empty value ratio threshold, and the usage rate empty value ratio is less than the preset empty value ratio threshold. The filtering and processing of the usage rate sequence according to the judgment result means: when the usage rate empty value ratio is greater than the preset empty value ratio threshold, the usage rate sequence is filtered and processed by one filtering condition; when the usage rate empty value ratio is less than the preset empty value ratio threshold, the usage rate sequence is filtered and processed by another filtering condition.

[0121] The target usage rate sequence is a usage rate sequence obtained after filtering the usage rate sequence.

[0122] Step 103, determine whether the target usage data in the target usage sequence is greater than the usage peak, and whether the first time is greater than a preset time threshold; wherein the target usage data is any usage data in the target usage sequence, and the first time is obtained based on the number of target usage data that are continuously greater than the usage peak.

[0123] In the disclosed embodiment, the preset usage peak refers to the CPU usage peak, and the preset time threshold refers to the threshold of the peak duration, wherein the preset usage peak and the preset time threshold both represent the triggering conditions of the resource scheduling task (the CPU usage peak (preset usage peak) is not the maximum value of the CPU usage, but the critical value for triggering the resource scheduling task. Similarly, the threshold of the peak duration (preset time threshold) is not the maximum value of the CPU usage peak duration, but the critical value for triggering the resource scheduling task). When the CPU usage is greater than the CPU usage peak and the width of the sliding window is greater than the peak duration, the scheduling task is triggered, that is, when the target usage data is greater than the usage peak and the first time is greater than the preset time threshold, the scheduling task is triggered. By using the CPU usage peak duration (first time) as a resource allocation evaluation indicator, it is possible to objectively reflect the resource usage and improve the accuracy of resource scheduling.

[0124] The usage peak value is a preset usage peak value or a historical usage peak value, and the historical usage peak value is obtained by updating the usage sequence at the last adjacent moment of the target usage sequence during the resource scheduling process through a feedback coefficient.

[0125] It should be noted that, when determining the first time, it is determined based on the number of target usage data that are continuously greater than the usage peak. The determination of the first time includes but is not limited to: by setting a sliding window representing the time period, the target usage data that are continuously greater than the usage peak are included in a sliding window, and the width of the sliding window represents the time when the target usage data is continuously greater than the usage peak, namely, the first time.

[0126] Step 104, when the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold, the target usage rate sequence is added to a preprocessing queue for preprocessing operation to obtain a preprocessing result.

[0127] In an embodiment of the present disclosure, when the target usage data is greater than the usage peak and the first time is greater than the preset time threshold, a scheduling task is triggered, indicating that the target usage sequence requires resource scheduling. At this time, the target usage sequence is added to the preprocessing queue for preprocessing to perform simple resource scheduling, thereby reducing CPU usage, improving the timeliness and resource utilization of resource scheduling, and optimizing the problem of equipment loss rate.

[0128] Among them, the preprocessing of the target usage sequence refers to: performing simple resource scheduling processing on the target usage sequence first, and the preprocessing results include: the target usage data in the target usage sequence has not decreased, the target usage data in the target usage sequence has decreased, etc.

[0129] Step 105 : When it is determined according to the preprocessing result that the target usage rate data has not decreased, adding the target device to the scheduling stack for resource scheduling processing, wherein the target device is the device that generates the usage rate data.

[0130] In the embodiment of the present disclosure, when the target utilization data does not decrease, it indicates that the method of adding the target utilization sequence to the preprocessing queue for preprocessing to perform simple resource processing to reduce CPU utilization is less effective. Therefore, it is necessary to add the target device to the scheduling stack for resource scheduling processing to complete resource scheduling.

[0131] The target device is a device that generates the usage data, including but not limited to: a server, a mobile device, an embedded device, a cluster and a distributed system, etc. Specifically, the embodiment of the present disclosure does not limit the target device.

[0132] In order to facilitate understanding of the implementation process of the embodiment of the present disclosure, the embodiment of the present disclosure provides a schematic diagram of the principle of a resource scheduling method, as shown in FIG. Figure 2As shown, there are three modules, namely, a preprocessing module, a computing module, and a resource scheduling module. In the preprocessing module, points with low CPU usage (usage data) for a long time are filtered out to obtain a CPU usage array (target usage sequence); in the computing module, according to the CPU temperature, number of cores and other influencing factors, the conditions for triggering resource scheduling are dynamically obtained (determining whether the target usage data in the target usage sequence is greater than the usage peak value, and whether the first time is greater than the preset time threshold), and it is added to the preprocessing queue. In the scheduling module, resource scheduling is performed according to the scheduling stack.

[0133] The resource scheduling method provided by the present disclosure arranges the acquired usage data according to the time series information corresponding to each of the usage data to obtain a usage sequence, and calculates the usage null value ratio in the usage sequence; wherein the usage null value ratio is the ratio between the usage data greater than a first preset threshold and all the usage data in the usage sequence; determines whether the usage null value ratio is greater than a preset null value ratio threshold, and screens the usage sequence according to the determination result to obtain a target usage sequence; determines whether the target usage data in the target usage sequence is greater than the usage peak value, and whether the first time is greater than Preset time threshold; wherein the target usage data is any usage data in the target usage sequence, and the first time is obtained according to the number of target usage data that are continuously greater than the usage peak; when the target usage data is greater than the usage peak, and the first time is greater than the preset time threshold, the target usage sequence is added to the preprocessing queue for preprocessing operation to obtain a preprocessing result; when it is determined according to the preprocessing result that the target usage data has not decreased, the target device is added to the scheduling stack for resource scheduling processing, wherein the target device is the device that generates the usage data. Compared with the related art, the embodiment of the present disclosure can avoid the situation of long-term low CPU usage by filtering out points where the CPU usage is low for a long time, and mainly preprocessing the CPU usage that is greater than the usage peak and lasts for a long time, and performing resource scheduling according to the preprocessing result, thereby reducing the complexity of resource scheduling, improving the timeliness of resource scheduling, and the accuracy of resource scheduling results.

[0134] In one possible implementation of the embodiment of the present disclosure, as a refinement of the above step 101, regarding the calculation of the usage rate null value ratio in the usage rate series, the embodiment of the present disclosure provides a schematic diagram of the calculation process of the usage rate null value ratio, such as Figure 3 As shown, including:

[0135] Step 301, obtaining the quantity of the usage rate data in the usage rate series to obtain a first data quantity.

[0136] In the embodiment of the present disclosure, since the usage rate null value ratio is the ratio of the usage rate data greater than the first preset threshold to all the usage rate data in the usage rate sequence, it is necessary to obtain the number of usage rate data in the usage rate series, that is, the first data number. The first data number can be directly obtained from the usage rate series.

[0137] Step 302: Obtain the number of usage rate data in the usage rate series that is not greater than the first preset threshold value to obtain a second data number.

[0138] In the embodiment of the present disclosure, the first preset threshold is a custom-set value, such as 0, 0.1, etc., wherein the first preset threshold is generally set to 0, and is used to distinguish between data with usage rate greater than 0 and data with usage rate equal to 0. The second data quantity can be obtained directly from the usage rate series or through marking.

[0139] Regarding obtaining the second data quantity by marking, for example, the usage rate sequence C is, C=[c1, c2, ..., c n ], when the CPU usage rate is 0, take 1, otherwise take 0, the number of 0s in array C (the second data quantity) is T0, the number of 1s is T1, and the number of usage data (the first data quantity) is T0+T1.

[0140] Step 303: Divide the second data quantity and the first data quantity to obtain the usage-to-null ratio.

[0141] In the embodiment of the present disclosure, the calculation of the usage rate-to-empty ratio may be implemented by, but not limited to, formula (1):

[0142]

[0143] Wherein, α is the usage-to-null ratio, T0 is the second data quantity, and T0+T1 is the first data quantity.

[0144] In an implementable manner of the embodiment of the present disclosure, as a refinement of the above step 102, regarding the screening process of the usage rate sequence, the embodiment of the present disclosure provides a schematic diagram of the screening process of the usage rate sequence, such as Figure 4 As shown, including:

[0145] Step 401, when the usage rate null value ratio is greater than or equal to the preset null value ratio threshold, the usage data in the usage sequence that is less than a first usage threshold is deleted to obtain the target usage sequence; wherein the first usage threshold is calculated by the usage peak value.

[0146] In the embodiment of the present disclosure, the calculation of the first usage rate threshold may be implemented by, but not limited to, formula (2):

[0147]

[0148] Wherein, A is the first usage rate threshold, U max is the peak usage rate.

[0149] Step 402, when the usage rate null value ratio is less than the preset null value ratio threshold, the usage data in the usage sequence that is less than the second usage threshold is deleted to obtain the target usage sequence; wherein the second usage threshold is obtained by calculating the average value of all the usage data in the usage sequence.

[0150] In the embodiment of the present disclosure, the calculation of the second usage rate threshold may be implemented by, but not limited to, formula (3):

[0151]

[0152] Wherein, B is the second usage rate threshold, U i is the i-th CPU usage in array C (usage sequence), and k indicates that there are k data in the array (the first data quantity).

[0153] In one possible implementation of the embodiment of the present disclosure, as a refinement of the above step 103, when judging whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than the preset time threshold, the embodiment of the present disclosure provides a flow chart of a method for determining the first time, such as Figure 5 As shown, including:

[0154] Step 501: Set a sliding window representing a time period, wherein the width of the sliding window is used to represent the time during which the target usage rate data is continuously greater than the usage rate peak value.

[0155] In the embodiment of the present disclosure, since the first time is determined based on the number of target usage data that are continuously greater than the usage peak, a sliding window representing the time period can be set to include the target usage data that are continuously greater than the usage peak into a sliding window, and the width of the sliding window represents the time when the target usage data are continuously greater than the usage peak, i.e., the first time.

[0156] Step 502, traverse the target usage sequence, and fix the left side of the sliding window at the first target usage data; wherein the first target usage data is the target usage data in the target usage sequence that is greater than the usage peak for the first time.

[0157] In the embodiment of the present disclosure, the CPU usage array (the target usage sequence) is traversed to change the width of the sliding window. First, the left side of the sliding window is fixed at the point where the CPU usage is higher than U for the first time. max (Usage peak) (at the first target usage data), the right side slides according to the elements in the traversal CPU usage array to determine the first time according to the width of the sliding window.

[0158] Step 503, when the second target usage data is greater than the usage peak, slide the right side of the sliding window to the right, and continue to traverse the target usage sequence to obtain the target width of the sliding window; wherein, the second target usage data is the target usage data adjacent to the right side of the first target usage data in the target usage sequence.

[0159] In the embodiment of the present disclosure, when the element is greater than U max When the usage peaks, the right side of the sliding window slides to the right, and at the same time, it is determined whether the width of the sliding window is greater than T max (Preset time threshold).

[0160] Step 504: When the second target usage rate data is not greater than the usage rate peak value, add the second target usage rate data to the backup data sequence.

[0161] In the embodiment of the present disclosure, when the element is not greater than U max When the usage peaks, the element is added to the backup array (backup data sequence) and the array is traversed. At this time, the width of the sliding window is not checked to see if it is greater than T. max After determining whether to slide the right side of the sliding window to the right according to the backup array (backup data sequence), the final sliding window width is obtained according to the determination result, and then according to the final sliding window width, it is determined whether it is greater than T max .

[0162] Step 505: determine whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtain the target width according to the determination result.

[0163] In the embodiment of the present disclosure, after determining whether to slide the right side of the sliding window to the right according to the backup array (backup data sequence), the final width of the sliding window is obtained according to the determination result, and then according to the final width of the sliding window, it is determined whether it is greater than T max .

[0164] Specifically, regarding determining whether to slide the right side of the sliding window to the right based on the backup data sequence, for example: when the backup data sequence meets the preset conditions, slide the right side of the sliding window to the right; when the backup data sequence does not meet the preset conditions, keep the right side of the sliding window stationary, etc.

[0165] Step 506: When the target width is greater than the preset time threshold, determine that the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold.

[0166] In the embodiment of the present disclosure, when the target width is greater than the preset time threshold, it can be determined that the first time is greater than the preset time threshold. Since the first time is the duration when the target usage data is greater than the usage peak, it can be further known that the target usage data is greater than the usage peak and the first time is greater than the preset time threshold.

[0167] In an implementable manner of the embodiment of the present disclosure, related to the above embodiment, when judging whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtaining the target width according to the judgment result, the embodiment of the present disclosure provides a flow chart of another first time determination method, such as Figure 6 As shown, including:

[0168] Step 601, adding a preset number of backup usage rate data to the backup data sequence; wherein the backup usage rate data is the preset number of target usage rate data adjacent to the right side of the second target usage rate data in the target usage rate sequence.

[0169] In the embodiment of the present disclosure, when the element (the second target usage rate data) is not greater than U max (usage peak), the element is added to the backup array (backup data sequence), and the preset number of target usage data to the right of the second target usage data is added to the backup data sequence, wherein the preset number is a number of custom settings, for example: 2, 3, 4, etc.

[0170] Among them, when the preset quantity is set to 2, there will be 3 elements (3 backup utilization rate data) in the backup data sequence. For example: x1, x2, x3.

[0171] Step 602: Obtain the data quantity of the backup utilization rate data in the backup data sequence that is greater than the utilization rate peak value, to obtain a third data quantity, and calculate the average value of all the backup utilization rate data in the backup data sequence, to obtain a first average value data.

[0172] In the embodiment of the present disclosure, the third data quantity can be directly obtained in the backup data sequence. Regarding the calculation of the first average value data, it can be implemented by, but not limited to, formula (4):

[0173]

[0174] Among them, C is the first average value, m is the quantity of all the backup utilization rate data in the backup data sequence, and x1, x2,..., x m are the backup utilization rate data in the backup data sequence.

[0175] Step 603: In the case where the first average value data is not greater than the first utilization rate threshold and the third data quantity is not greater than a preset quantity threshold, keep the right side of the sliding window stationary, to obtain the target width, and empty the backup data sequence.

[0176] In the embodiment of the present disclosure, the preset quantity threshold is a value set by customization. The setting of the preset quantity threshold is determined according to the quantity of all the backup utilization rate data in the backup data sequence. For example: if there are 3 backup utilization rate data in the backup data sequence, the preset quantity threshold can be set to 2; if there are m backup utilization rate data in the backup data sequence, the preset quantity threshold can be set to 80%m, etc. Specifically, regarding the setting of the preset quantity threshold, the embodiment of the present disclosure does not make any limitations.

[0177] Taking the example that there are 3 backup utilization rate data in the backup data sequence, the first average value data is not greater than the first utilization rate threshold, and the third data quantity is not greater than the preset quantity threshold, which can be represented by formula (5):

[0178] And x i <U max , x j <U max (0 < i, j < 4) Formula (5)

[0179] When the first average value data is less than the first utilization rate threshold and the third data quantity is less than the preset quantity threshold, it indicates that the CPU utilization rate has decreased. At this time, the backup array is cleared, and the width of the sliding window at this time is used as the target width.

[0180] Step 604, in the case where the first average value data is greater than the first utilization rate threshold or the third data quantity is greater than the preset quantity threshold, slide the right side of the sliding window to the right, and continue to traverse the target utilization rate sequence to obtain the target width of the sliding window.

[0181] In the embodiment of the present disclosure, taking the example that there are 3 backup utilization rate data in the backup data sequence, the first average value data is greater than the first utilization rate threshold or the third data quantity is greater than the preset quantity threshold, which can be represented by formula (6):

[0182] And x i >U max ,x j >U max (0 < i, j < 4) Formula (6)

[0183] When the first average value data is greater than the first utilization rate threshold or the third data quantity is greater than the preset quantity threshold, it indicates that the CPU utilization rate has mutated and is still exceeding the peak value in a short period of time. Slide the right side of the sliding window to the right, and continue to traverse the CPU utilization rate array (target utilization rate sequence) until the target utilization rate sequence is traversed or the condition for stopping sliding the right side of the sliding window to the right is met, and the final width of the sliding window is obtained as the target width.

[0184] To facilitate understanding of the implementation process of the above embodiments, the embodiment of the present disclosure provides a flow diagram of calculating a resource allocation evaluation index of a dynamic sliding window, as Figure 7 shown.

[0185] In a feasible implementation manner of the embodiment of the present disclosure, the main factors for high CPU utilization rate include high CPU temperature, hyper-threading, etc. The high CPU temperature seriously affects the service life of the CPU. If the resource scheduling trigger conditions are set without discrimination, when it is caused by high CPU utilization rate, it cannot be processed quickly. Therefore, the embodiment of the present disclosure provides a flow diagram of a method for updating the utilization rate peak value, as Figure 8 shown, including:

[0186] Step 801, obtain all influencing factors affecting the target utilization rate data, and obtain the initial confidence level corresponding to each influencing factor.

[0187] In the embodiment of the present disclosure, the factors that affect the excessive CPU usage are quantified and normalized (except for the CPU temperature) and are represented by Q1, Q2, ..., Q n The confidence level of each factor is

[0188] Step 802, predicting the main influencing factors among the influencing factors through a preset probability algorithm, and performing resource scheduling processing on the designated target usage data according to the main influencing factors to obtain a first scheduling result; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage data, and the designated target usage data is the target usage data that is greater than the usage peak.

[0189] In the embodiment of the present disclosure, the method of predicting the main influencing factors among the influencing factors by using a preset probability algorithm can be expressed by, but not limited to, formula (7):

[0190]

[0191] Among them, it means that the kth factor is the main reason for the high CPU usage, that is, Q k is the main influencing factor.

[0192] When resource scheduling is performed on the specified target usage data according to the main influencing factors, it means that corresponding utilization reduction operations are performed according to the main influencing factors in a targeted manner. For example: if the main influencing factor is temperature, cooling measures are performed; if the main influencing factor is threads, thread reduction measures are performed.

[0193] Step 803, when the first scheduling result indicates that the specified target usage data is less than the usage peak, the initial confidence corresponding to the main influencing factor is updated to a first confidence, and the initial confidence corresponding to other influencing factors is updated to a second confidence; wherein the other influencing factors are all the influencing factors except the main influencing factor.

[0194] In the embodiment of the present disclosure, if it is determined that the specified target usage data is less than the usage peak, it means that the CPU usage drops below the usage peak, and it can be determined that the predicted main influencing factors are accurate. At this time, it is necessary to set a larger confidence level for the main influencing factors. The update of the initial confidence level can be achieved by but not limited to formula (8):

[0195]

[0196] in, is the first straight confidence level, For the second confidence level, ε represents a custom coefficient, which is set empirically, where ε is greater than The larger the coefficient is defined, the slower the confidence adjustment speed is and the higher the accuracy is.

[0197] Step 804, calculate a first feedback coefficient based on the first confidence level, and update the usage peak based on the first feedback coefficient to obtain an updated usage peak; wherein the updated usage peak is used as a parameter for resource scheduling of the usage sequence at the next adjacent moment of the target usage sequence.

[0198] In the embodiment of the present disclosure, the calculation of the first feedback coefficient may be implemented by, but not limited to, formula (9):

[0199]

[0200] Among them, γ is the first feedback coefficient, Q1 is the main influencing factor, is the first confidence level.

[0201] The updated usage peak value may be implemented by, but not limited to, formula (10):

[0202] U max '=U max (1-γ) Formula (10)

[0203] Among them, U′ max is the updated usage peak value.

[0204] It should be noted that if the usage sequence at the next adjacent moment of the target usage sequence cannot trigger the restriction condition of the updated usage peak, the updated usage peak will be initialized as the usage peak. At the same time, since the usage peak will decrease each time the usage peak is updated, and continuous updates of the usage peak will result in a lower usage peak, a preset usage threshold can be set. If the updated usage peak is less than or equal to the preset usage threshold, the preset usage threshold will be used as the updated usage peak.

[0205] Step 805, when the first scheduling result indicates that the designated target usage data is not less than the usage peak, the initial confidence corresponding to the main influencing factor is updated to a third confidence, and the initial confidence corresponding to other influencing factors is updated to a fourth confidence.

[0206] In the embodiment of the present disclosure, if it is determined that the specified target usage data is not less than the usage peak, it means that the CPU usage has not dropped below the usage peak, and it can be determined that the predicted main influencing factor is inaccurate. At this time, it is necessary to set a smaller confidence for the main influencing factor. The update of the initial confidence can be achieved by but not limited to formula (11):

[0207]

[0208] in,, is the third straight confidence level, For the fourth confidence level, ε represents a custom coefficient, which is set based on experience, where ε is greater than The larger the coefficient is defined, the slower the confidence adjustment speed is and the higher the accuracy is.

[0209] Step 806: Calculate a second feedback coefficient according to the third confidence level, and update the usage peak value according to the second feedback coefficient to obtain the updated usage peak value.

[0210] In the embodiment of the present disclosure, regarding the acquisition of the second feedback coefficient and the updated usage peak value, reference may be made to the description in the above step 804, and therefore, they will not be described in detail here.

[0211] In one implementable manner of the embodiment of the present disclosure, as a refinement of the above-mentioned step 104, when the target usage sequence is added to the preprocessing queue for preprocessing operations and the preprocessing results are obtained, it can also be implemented in but not limited to the following manner: obtaining all influencing factors affecting the target usage data, and predicting the main influencing factors among the influencing factors through a preset probability algorithm; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage data; merging all the target usage data in the target usage sequence to obtain merged data; performing resource scheduling processing on the merged data according to the main influencing factors to obtain the preprocessing results.

[0212] In the embodiment of the present disclosure, data that meets the resource scheduling conditions is pushed into the preprocessing queue, the data in the preprocessing queue is first merged, the time-continuous data is merged, and then the situation of excessive CPU usage is preprocessed (for example: if The biggest influencing factor is too many threads, which is handled by releasing threads).

[0213] In one implementable manner of the disclosed embodiment, after preprocessing the target usage sequence, if the CPU usage still does not decrease at the next moment, the data is pushed into the scheduling stack and processed by scheduling resources; if the CPU usage decreases at the next moment, the data is deleted from the preprocessing queue. Therefore, after adding the target usage sequence to the preprocessing queue for preprocessing and obtaining the preprocessing result, the following method can be used but is not limited to: when it is determined that the target usage data has decreased according to the preprocessing result, resource scheduling processing is performed on the merged data according to the main influencing factors, and the target usage sequence is deleted from the preprocessing queue.

[0214] In one implementable manner of the embodiment of the present disclosure, since the usage peak is a preset usage peak or a historical usage peak, it is necessary to determine whether there is a historical usage peak to determine the accurate data of the usage peak. Therefore, in order to accurately determine the usage peak, the following method may also be used but is not limited to: determine whether the historical usage peak is obtained; wherein the historical usage peak is obtained by updating the feedback coefficient of the usage sequence at the previous adjacent moment of the target usage sequence during the resource scheduling process; when the historical usage peak is obtained, the historical usage peak is used as the usage peak; when the historical usage peak is not obtained, the preset usage peak is obtained as the usage peak.

[0215] In the embodiment of the present disclosure, it is determined whether the trigger condition of the scheduled task is set. If not, the initial trigger condition is set by custom setting (the initial condition includes: the peak value of CPU usage U max , peak duration T max , the width of the sliding window is 1). If set, the CPU usage peak value U is modified according to the feedback coefficient. max , peak duration T max The width of the sliding window remains unchanged, and the fixed positions on the left and right sides of the sliding window are cancelled.

[0216] In summary, the embodiments of the present disclosure can achieve the following effects:

[0217] 1. The disclosed embodiment can avoid the situation where the CPU usage rate is low for a long time by filtering out points where the CPU usage rate is low for a long time, and mainly schedules resources for CPU usage rates that are greater than the peak usage rate and last for a long time, thereby improving the timeliness of resource scheduling and the accuracy of resource scheduling results.

[0218] 2. The disclosed embodiment uses the width of the sliding window as an evaluation indicator for resource scheduling, thereby solving the problem that the evaluation indicators for resource allocation are one-sided and reflect the problem inaccurately, thereby improving resource utilization.

[0219] 3. The disclosed embodiment determines the confidence of different factors with the results of queue processing and calculates the feedback coefficient, thereby solving the problem of excessive equipment loss rate caused by indiscriminate setting of trigger resource allocation conditions.

[0220] 4. The embodiment of the present disclosure pre-processes the CPU usage rate and generates a scheduling stack according to a negative feedback mechanism and a dynamic sliding window, thereby improving the timeliness and resource utilization of resource scheduling and optimizing the problem of equipment loss rate.

[0221] 5. The embodiment of the present disclosure uses preprocessing and feedback coefficient calculation methods to quickly deal with the problem of excessive CPU usage caused by major influencing factors, thereby increasing the service life of the equipment.

[0222] Corresponding to the above resource scheduling method, the present invention also provides a resource scheduling device. Since the device embodiment of the present invention corresponds to the above method embodiment, details not disclosed in the device embodiment can be referred to the above method embodiment, and will not be repeated in the present invention.

[0223] Fig. 9 A schematic diagram of a resource scheduling device provided in an embodiment of the present disclosure is shown in FIG. Fig. 9 As shown, including:

[0224] An arrangement unit 901 is used to arrange the acquired usage rate data according to the time series information corresponding to each of the usage rate data to obtain a usage rate sequence;

[0225] The calculation unit 902 is used to calculate the usage rate null value ratio in the usage rate sequence; wherein the usage rate null value ratio is the ratio between the usage rate data greater than a first preset threshold and all the usage rate data in the usage rate sequence;

[0226] A screening unit 903 is used to determine whether the usage rate to null value ratio is greater than a preset null value ratio threshold, and screen the usage rate sequence according to the determination result to obtain a target usage rate sequence;

[0227] A first judgment unit 904 is used to judge whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than a preset time threshold; wherein the target usage rate data is any usage rate data in the target usage rate sequence, and the first time is obtained according to the number of target usage rate data that are continuously greater than the usage rate peak value;

[0228] An adding unit 905 is configured to add the target usage rate sequence to a preprocessing queue for preprocessing to obtain a preprocessing result when the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold;

[0229] The scheduling unit 906 is configured to add a target device to a scheduling stack for resource scheduling processing if it is determined according to the preprocessing result that the target usage data has not decreased, wherein the target device is a device that generates the usage data.

[0230] The resource scheduling device provided by the present disclosure arranges the acquired usage data according to the time series information corresponding to each of the usage data to obtain a usage sequence, and calculates the usage null value ratio in the usage sequence; wherein the usage null value ratio is the ratio between the usage data greater than a first preset threshold and all the usage data in the usage sequence; determines whether the usage null value ratio is greater than a preset null value ratio threshold, and screens the usage sequence according to the determination result to obtain a target usage sequence; determines whether the target usage data in the target usage sequence is greater than the usage peak value, and whether the first time is greater than Preset time threshold; wherein the target usage data is any usage data in the target usage sequence, and the first time is obtained according to the number of target usage data that are continuously greater than the usage peak; when the target usage data is greater than the usage peak, and the first time is greater than the preset time threshold, the target usage sequence is added to the preprocessing queue for preprocessing operation to obtain a preprocessing result; when it is determined according to the preprocessing result that the target usage data has not decreased, the target device is added to the scheduling stack for resource scheduling processing, wherein the target device is the device that generates the usage data. Compared with the related art, the embodiment of the present disclosure can avoid the situation of long-term low CPU usage by filtering out points where the CPU usage is low for a long time, and mainly preprocessing the CPU usage that is greater than the usage peak and lasts for a long time, and performing resource scheduling according to the preprocessing result, thereby reducing the complexity of resource scheduling, improving the timeliness of resource scheduling, and the accuracy of resource scheduling results.

[0231] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Fig.10 As shown, the calculation unit 902 includes:

[0232] The acquisition module 9021 is used to acquire the quantity of the usage rate data in the usage rate series to obtain a first data quantity;

[0233] The acquisition module 9021 is further used to acquire the number of usage rate data in the usage rate series that is not greater than the first preset threshold value to obtain a second data number;

[0234] The calculation module 9022 is used to divide the second data quantity and the first data quantity to obtain the usage rate null value ratio.

[0235] Furthermore, in a possible implementation of the embodiment of the present disclosure, the screening unit 903 is further configured to:

[0236] When the usage rate to empty value ratio is greater than or equal to the preset empty value ratio threshold, the usage rate data in the usage rate sequence that is less than a first usage rate threshold is deleted to obtain the target usage rate sequence; wherein the first usage rate threshold is calculated by the usage rate peak value;

[0237] When the usage rate null value ratio is less than the preset null value ratio threshold, the usage data in the usage rate sequence that is less than the second usage rate threshold is deleted to obtain the target usage rate sequence; wherein the second usage rate threshold is obtained by calculating the average value of all the usage data in the usage rate sequence.

[0238] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Fig.10 As shown, the first judging unit 904 includes:

[0239] A setting module 9041 is used to set a sliding window representing a time period, wherein the width of the sliding window is used to represent the time during which the target usage rate data is continuously greater than the usage rate peak value;

[0240] A fixing module 9042 is used to traverse the target usage rate sequence and fix the left side of the sliding window at the first target usage rate data; wherein the first target usage rate data is the target usage rate data that is greater than the usage rate peak value for the first time in the target usage rate sequence;

[0241] The sliding module 9043 is used to slide the right side of the sliding window to the right and continue to traverse the target usage rate sequence to obtain the target width of the sliding window when the second target usage rate data is greater than the usage rate peak value; wherein the second target usage rate data is the target usage rate data adjacent to the right side of the first target usage rate data in the target usage rate sequence;

[0242] An adding module 9044 is used to add the second target usage rate data to the backup data sequence when the second target usage rate data is not greater than the usage rate peak value;

[0243] The sliding module 9043 is further used to determine whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtain the target width according to the determination result;

[0244] The determination module 9045 is used to determine that the target usage rate data is greater than the usage rate peak and the first time is greater than the preset time threshold when the target width is greater than the preset time threshold.

[0245] Furthermore, in a possible implementation of the embodiment of the present disclosure, the sliding module 9043 is also used for:

[0246] Adding a preset number of backup usage rate data to the backup data sequence; wherein the backup usage rate data is the preset number of target usage rate data adjacent to the right of the second target usage rate data in the target usage rate sequence;

[0247] Acquire the number of the backup usage rate data in the backup data sequence that is greater than the usage rate peak value to obtain a third data number, and calculate the average value of all the backup usage rate data in the backup data sequence to obtain a first average value data;

[0248] When the first average value data is not greater than the first usage rate threshold, and the third data quantity is not greater than the preset quantity threshold, the right side of the sliding window is kept stationary to obtain the target width, and the backup data sequence is cleared;

[0249] When the first average value data is greater than the first usage threshold, or the third data quantity is greater than the preset quantity threshold, the right side of the sliding window is slid to the right, and the target usage sequence is continued to be traversed to obtain the target width of the sliding window.

[0250] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Fig.10 As shown, the device also includes:

[0251] An acquisition unit 907 is used to acquire all influencing factors that affect the target usage rate data, and acquire an initial confidence level corresponding to each of the influencing factors;

[0252] The processing unit 908 is configured to predict the main influencing factor among the influencing factors by using a preset probability algorithm, and perform resource scheduling processing on the designated target usage rate data according to the main influencing factor to obtain a first scheduling result; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage rate data, and the designated target usage rate data is the target usage rate data that is greater than the usage rate peak value;

[0253] An updating unit 909 is configured to update the initial confidence corresponding to the main influencing factor to a first confidence, and update the initial confidence corresponding to other influencing factors to a second confidence, when the first scheduling result indicates that the designated target usage rate data is less than the usage rate peak; wherein the other influencing factors are all influencing factors among the influencing factors except the main influencing factor;

[0254] The updating unit 909 is further configured to calculate a first feedback coefficient according to the first confidence level, and update the usage peak according to the first feedback coefficient to obtain an updated usage peak; wherein the updated usage peak is used as a parameter for resource scheduling processing of the usage sequence at the next adjacent moment of the target usage sequence;

[0255] The updating unit 909 is further configured to, when the first scheduling result indicates that the designated target usage rate data is not less than the usage rate peak value, update the initial confidence corresponding to the main influencing factor to a third confidence, and update the initial confidence corresponding to other influencing factors to a fourth confidence;

[0256] The updating unit 909 is further configured to calculate a second feedback coefficient according to the third confidence level, and update the usage peak value according to the second feedback coefficient to obtain the updated usage peak value.

[0257] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Fig.10 As shown, the adding unit 905 includes:

[0258] The acquisition module 9051 is used to acquire all influencing factors that affect the target usage rate data, and predict the main influencing factors among the influencing factors through a preset probability algorithm; wherein the main influencing factor is the factor that has the greatest impact on the target usage rate data among the influencing factors;

[0259] A merging module 9052, configured to merge all the target usage rate data in the target usage rate sequence to obtain merged data;

[0260] The scheduling module 9053 is used to perform resource scheduling processing on the merged data according to the main influencing factors to obtain the preprocessing result.

[0261] Furthermore, in a possible implementation of the embodiment of the present disclosure, the scheduling unit 906 is also used to, when it is determined according to the preprocessing result that the target utilization data is reduced, perform resource scheduling processing on the merged data according to the main influencing factors, and delete the target utilization sequence from the preprocessing queue.

[0262] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Fig.10 As shown, the device also includes:

[0263] The second judgment unit 910 is used to judge whether a historical usage peak value is obtained; wherein the historical usage peak value is obtained by updating the usage sequence at the previous adjacent moment of the target usage sequence during the resource scheduling process through a feedback coefficient;

[0264] A determining unit 911 is configured to, when the historical usage peak value is obtained, use the historical usage peak value as the usage peak value;

[0265] The determining unit 911 is further configured to, when the historical usage peak value is not obtained, obtain a preset usage peak value as the usage peak value.

[0266] It should be noted that the above explanation of the method embodiment is also applicable to the device of the embodiment of the present disclosure, and the principle is the same, which is no longer limited in the embodiment of the present disclosure.

[0267] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0268] Fig.11 A schematic block diagram of an example electronic device 1100 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0269] like Fig.11As shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 1102 or a computer program loaded from a storage unit 1108 to a RAM (Random Access Memory) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An I / O (Input / Output) interface 1105 is also connected to the bus 1104.

[0270] A number of components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0271] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as a method for resource scheduling. For example, in some embodiments, the method for resource scheduling may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to execute the aforementioned resource scheduling method in any other appropriate manner (for example, by means of firmware).

[0272] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0273] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0274] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or a flash memory, an optical fiber, a CD-ROM (Compact Dis sc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0275] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0276] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0277] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0278] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0279] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0280] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A resource scheduling method, characterized in that: include: Arrange the acquired usage rate data according to the time series information corresponding to each of the usage rate data to obtain a usage rate sequence, and calculate the usage rate null value ratio in the usage rate sequence; wherein the usage rate null value ratio is the ratio between the usage rate data greater than a first preset threshold and all the usage rate data in the usage rate sequence; Determine whether the usage rate to null value ratio is greater than a preset null value ratio threshold, and filter the usage rate sequence according to the determination result to obtain a target usage rate sequence; Determine whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than a preset time threshold; wherein the target usage rate data is any usage rate data in the target usage rate sequence, and the first time is obtained according to the number of target usage rate data that are continuously greater than the usage rate peak value; When the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold, adding the target usage rate sequence to a preprocessing queue for preprocessing operation to obtain a preprocessing result; When it is determined according to the preprocessing result that the target usage rate data has not decreased, a target device is added to a scheduling stack for resource scheduling processing, wherein the target device is a device that generates the usage rate data.

2. The method according to claim 1, characterized in that The calculating of the usage rate null value ratio in the usage rate series comprises: Acquire the quantity of the usage rate data in the usage rate series to obtain a first data quantity; Acquire the number of usage rate data in the usage rate series that is not greater than the first preset threshold value to obtain a second data number; The second data quantity is divided by the first data quantity to obtain the usage rate-to-null ratio.

3. The method according to claim 1, characterized in that The filtering of the usage rate sequence according to the judgment result to obtain the target usage rate sequence includes: When the usage rate to empty value ratio is greater than or equal to the preset empty value ratio threshold, the usage rate data in the usage rate sequence that is less than a first usage rate threshold is deleted to obtain the target usage rate sequence; wherein the first usage rate threshold is calculated by the usage rate peak value; When the usage rate null value ratio is less than the preset null value ratio threshold, the usage data in the usage rate sequence that is less than the second usage rate threshold is deleted to obtain the target usage rate sequence; wherein the second usage rate threshold is obtained by calculating the average value of all the usage data in the usage rate sequence.

4. The method according to claim 1, characterized in that: The determining whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than a preset time threshold includes: Setting a sliding window representing a time period, wherein the width of the sliding window is used to represent the time during which the target usage rate data is continuously greater than the usage rate peak value; Traversing the target usage rate sequence, fixing the left side of the sliding window at the first target usage rate data; wherein the first target usage rate data is the target usage rate data in the target usage rate sequence that is greater than the usage rate peak value for the first time; When the second target usage rate data is greater than the usage rate peak value, slide the right side of the sliding window to the right, and continue to traverse the target usage rate sequence to obtain the target width of the sliding window; wherein the second target usage rate data is the target usage rate data adjacent to the right side of the first target usage rate data in the target usage rate sequence; When the second target usage rate data is not greater than the usage rate peak value, adding the second target usage rate data to the backup data sequence; Determining whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtaining the target width according to the determination result; When the target width is greater than the preset time threshold, it is determined that the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold.

5. The method according to claim 1, characterized in that The determining whether to slide the right side of the sliding window to the right according to the backup data sequence, and obtaining the target width according to the determination result includes: Adding a preset number of backup usage rate data to the backup data sequence; wherein the backup usage rate data is the preset number of target usage rate data adjacent to the right of the second target usage rate data in the target usage rate sequence; Acquire the number of the backup usage rate data in the backup data sequence that is greater than the usage rate peak value to obtain a third data number, and calculate the average value of all the backup usage rate data in the backup data sequence to obtain a first average value data; When the first average value data is not greater than the first usage rate threshold, and the third data quantity is not greater than the preset quantity threshold, the right side of the sliding window is kept stationary to obtain the target width, and the backup data sequence is cleared; When the first average value data is greater than the first usage threshold, or the third data quantity is greater than the preset quantity threshold, the right side of the sliding window is slid to the right, and the target usage sequence is continued to be traversed to obtain the target width of the sliding window.

6. The method according to claim 1, characterized in that Before adding the target usage rate sequence to a preprocessing queue for preprocessing and obtaining a preprocessing result, the method further includes: Obtaining all influencing factors affecting the target usage rate data, and obtaining an initial confidence level corresponding to each of the influencing factors; Predicting the main influencing factors among the influencing factors by a preset probability algorithm, and performing resource scheduling processing on the designated target usage rate data according to the main influencing factors to obtain a first scheduling result; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage rate data, and the designated target usage rate data is the target usage rate data that is greater than the usage rate peak value; In the case where the first scheduling result indicates that the designated target usage rate data is less than the usage rate peak, the initial confidence corresponding to the main influencing factor is updated to a first confidence, and the initial confidence corresponding to other influencing factors is updated to a second confidence; wherein the other influencing factors are all influencing factors except the main influencing factor among the influencing factors; Calculating a first feedback coefficient according to the first confidence level, and updating the usage peak according to the first feedback coefficient to obtain an updated usage peak; wherein the updated usage peak is used as a parameter for resource scheduling of a usage sequence at a next adjacent moment of the target usage sequence; When the first scheduling result indicates that the designated target usage rate data is not less than the usage rate peak, updating the initial confidence level corresponding to the main influencing factor to a third confidence level, and updating the initial confidence levels corresponding to other influencing factors to a fourth confidence level; A second feedback coefficient is calculated according to the third confidence level, and the usage peak value is updated according to the second feedback coefficient to obtain the updated usage peak value.

7. The method according to claim 1, characterized in that The step of adding the target usage rate sequence to a preprocessing queue for preprocessing to obtain a preprocessing result includes: Acquire all influencing factors that affect the target usage rate data, and predict the main influencing factors among the influencing factors through a preset probability algorithm; wherein the main influencing factor is the factor among the influencing factors that has the greatest impact on the target usage rate data; Merging all the target usage rate data in the target usage rate sequence to obtain merged data; The combined data is subjected to resource scheduling processing according to the main influencing factors to obtain the preprocessing result.

8. The method according to claim 7, characterized in that After adding the target usage rate sequence to a preprocessing queue for preprocessing and obtaining a preprocessing result, the method further includes: In the case where it is determined according to the preprocessing result that the target usage rate data is reduced, resource scheduling processing is performed on the merged data according to the main influencing factors, and the target usage rate sequence is deleted from the preprocessing queue.

9. The method according to claim 1, characterized in that: Before determining whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, the method further includes: Determine whether a historical usage peak value is obtained; wherein the historical usage peak value is obtained by updating the usage sequence at the previous adjacent moment of the target usage sequence during the resource scheduling process through a feedback coefficient; When the historical usage peak value is obtained, the historical usage peak value is used as the usage peak value; When the historical usage peak value is not obtained, a preset usage peak value is obtained as the usage peak value.

10. A resource scheduling device, characterized in that: include: An arranging unit, configured to arrange the acquired usage rate data according to the time series information corresponding to each of the usage rate data to obtain a usage rate sequence; A calculation unit, used to calculate the usage rate null value ratio in the usage rate sequence; wherein the usage rate null value ratio is the ratio between the usage rate data greater than a first preset threshold and all the usage rate data in the usage rate sequence; a screening unit, configured to determine whether the usage rate to null value ratio is greater than a preset null value ratio threshold, and to screen the usage rate sequence according to the determination result to obtain a target usage rate sequence; A first judgment unit is used to judge whether the target usage rate data in the target usage rate sequence is greater than the usage rate peak value, and whether the first time is greater than a preset time threshold; wherein the target usage rate data is any usage rate data in the target usage rate sequence, and the first time is obtained according to the number of target usage rate data that are continuously greater than the usage rate peak value; an adding unit, configured to add the target usage rate sequence to a preprocessing queue for preprocessing operation to obtain a preprocessing result when the target usage rate data is greater than the usage rate peak value and the first time is greater than the preset time threshold; The scheduling unit is used to add the target device to the scheduling stack for resource scheduling processing when it is determined according to the preprocessing result that the target usage data has not decreased, wherein the target device is the device that generates the usage data.

11. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

12. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

13. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 9.