Computing power scheduling system

By designing a computing power scheduling system in the learning model and simulation environment related to the charging strategy of new energy vehicles, adjusting the physical machine equipment resources in real time, solving the problems of poor real-time and inefficiency caused by manual allocation, and achieving efficient resource utilization and charging strategies Generate efficient operation of the model.

CN114168313BActive Publication Date: 2024-12-03STATE GRID BEIJING ELECTRIC POWER CO +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111028837.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-02
Publication Date
2024-12-03
Estimated Expiration
2041-09-02

AI Technical Summary

Technical Problem

In the prior art, learning models or simulation environments related to charging strategies of new energy vehicles have poor real-time and low efficiency in computing power allocation, which is mainly due to the manual allocation of physical machine equipment resources, resulting in insufficient resource utilization.

Method used

A computing power scheduling system was designed, including physical machine equipment, user management module and computing power scheduling module. By adjusting the number of physical machine equipment in real time, resources are automatically allocated according to the operating status of computing power units, ensuring the charging strategy generation model and charging Efficient operation of network simulation environment.

Benefits of technology

Automatic scheduling of computing power resources is realized, resource utilization is improved, the problems of poor real-time and inefficiency caused by manual allocation are solved, and the operation efficiency of charging strategy generation and simulation environment are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114168313B_ABST
    Figure CN114168313B_ABST
Patent Text Reader

Abstract

The present application discloses a computing power scheduling system. The system includes: a physical machine device, which is at least used to provide a physical machine device for the operation of a computing power unit, and the computing power unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task respectively; a user management module, which is at least used to call the first number of physical machine devices according to the target object configuration, wherein the first number is the maximum number of physical machine devices that can be used when running the computing power unit; a computing power scheduling module, which is used to adjust the second number of physical machine devices in real time according to the operating status of the computing power unit, wherein the first number is greater than the second number. The present application solves the technical problems of poor real-time performance and low efficiency caused by the manual allocation of physical machine device resources for the computing power unit in the related art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computers, and more specifically, to a computing power scheduling system. Background Art

[0002] Under the policy background of accelerating the development of electric vehicles and promoting the replacement of traditional fuels, the new energy vehicle industry has developed rapidly, strongly supporting the market demand for charging piles in this city. Special plans and documents for charging piles have been formulated at the national and local levels, which have a guiding role in the development of urban charging facilities. my country regards the development of new energy vehicles as an important strategic measure to alleviate energy and environmental pressures and promote the transformation and upgrading of the automobile industry. The construction and operation of new energy vehicle charging piles is an important infrastructure guarantee to support the development of new energy vehicles. The country has introduced encouraging policies for several consecutive years and formulated relevant special plans. It has now become the world's largest market for the application of new energy vehicles, built the world's largest urban charging pile network, and built a charging pile system with balanced development of public piles, special piles, and private piles.

[0003] However, when a learning model or simulation environment related to the charging strategy of new energy vehicles is running, it is necessary to provide corresponding computing power (the amount of resources called) for the relevant learning model or simulation environment. In related technologies, computing power is often allocated manually. For example, when the simulation environment is running, a fixed number of CPUs are manually configured to perform the simulation task. Obviously, this method has technical problems such as poor real-time performance, waste of manpower and low efficiency when allocating physical machine equipment resources.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiment of the present application provides a computing power scheduling system to at least solve the technical problems of poor real-time performance and low efficiency caused by manually allocating physical machine equipment resources to computing power units in related technologies.

[0006] According to one aspect of an embodiment of the present application, a computing power scheduling system is provided, including: a physical machine device, at least used to provide a physical machine device for the operation of a computing power unit, the computing power unit is used to configure a charging strategy generation model and a charging network simulation environment as a first target task and a second target task, respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of a sample object and a label for identifying a charging price policy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model; a user management module, at least used to call a first number of physical machine devices according to the target object configuration, wherein the first number is the maximum number of physical machine devices that can be used when running the computing power unit; a computing power scheduling module, used to adjust the second number of physical machine devices in real time according to the operating status of the computing power unit, wherein the first number is greater than the second number.

[0007] Optionally, the computing power unit corresponds one-to-one to the sandbox, and the sandbox is used to run the first target task and the second target task.

[0008] Optionally, the second number of physical machine devices is adjusted in real time according to the running status of the computing power unit, including: obtaining the running status of the first target task, and when the first target task is in an idle state, allocating the third number of physical machine devices corresponding to the first target task to the second target task; obtaining the running status of the second target task, and when the second target task is in an idle state, allocating the fourth number of physical machine devices corresponding to the second target task to the first target task.

[0009] Optionally, the computing power scheduling module is also used to withdraw the first target task and / or the second target task from the scheduling sequence when the first target task and / or the second target task are completed, wherein the scheduling sequence includes multiple tasks to be executed and physical machine devices corresponding to the tasks to be executed.

[0010] Optionally, the computing power scheduling module is also used to determine the third target task and temporarily suspend the third target task according to the priority of each system module when the remaining number corresponding to the physical machine equipment is less than a predetermined threshold, wherein the system module includes: a computing power scheduling module, a user management module and a data analysis module.

[0011] Optionally, the user management module has the highest priority, and the third target task is determined according to the priorities of each system module, and the third target task is temporarily suspended, including: receiving an input instruction of the target object, wherein the input instruction is used to indicate the priority of the computing power scheduling module or the data analysis module; when the input instruction indicates that the priority of the computing power scheduling module is lower than the priority of the data analysis module, the running task of the computing power module is used as the third target task, and the third target task is temporarily suspended; when the input instruction indicates that the priority of the computing power scheduling module is higher than the priority of the data analysis module, the running task of the data analysis module is used as the third target task, and the third target task is temporarily suspended.

[0012] Optionally, the physical machine device includes: a central processing unit CPU and a graphics processing unit GPU.

[0013] According to another aspect of an embodiment of the present application, a computing power scheduling method is also provided, which is applied to a distributed platform, including: obtaining the number of currently available physical machine devices; determining the target number of physical machine devices required by the computing power unit; allocating the target number of physical machine devices required by the computing power unit to the computing power unit, wherein the computing power unit is used to configure a charging strategy generation model and a charging network simulation environment as a first target task and a second target task, respectively, wherein the charging strategy generation model is obtained through multiple groups of training data, and each group of data in the multiple groups of training data includes: charging behavior characteristic parameters of a sample object and a label for identifying a charging price strategy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is also provided, and the non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above-mentioned computing power scheduling method.

[0015] According to another aspect of an embodiment of the present application, a processor is also provided, and the processor is used to run a program, wherein the above-mentioned computing power scheduling method is executed when the program is running.

[0016] In an embodiment of the present application, a method of automatically scheduling hardware resources is adopted, and a physical machine device is used to at least provide a physical machine device for the operation of a computing unit. The computing unit is used to configure a charging strategy generation model and a charging network simulation environment as a first target task and a second target task, respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of a sample object and a label for identifying a charging price policy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model; a user management module is used to at least call a first number of physical machine devices according to the target object configuration, wherein the first number is the maximum number of physical machine devices that can be used when running the computing unit; a computing power scheduling module is used to adjust the second number of physical machine devices in real time according to the operating status of the computing unit, wherein the first number is greater than the second number, thereby achieving a technical effect of automatically adjusting the physical machine device resources in real time according to the computing unit, thereby solving the technical problems of poor real-time performance and low efficiency caused by manually allocating physical machine device resources to the computing unit in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a schematic diagram of the structure of an optional computing power scheduling system according to an embodiment of the present application;

[0019] Figure 2 It is a flowchart of an optional computing power scheduling method according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] According to an embodiment of the present application, an embodiment of a computing power scheduling system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] Figure 1 A computing power scheduling system according to an embodiment of the present application is provided. Figure 1 As shown, the computing power scheduling system includes:

[0024] The physical machine device 01 is at least used to provide a physical machine device for the operation of the computing unit, and the computing unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of the sample object and a label for identifying the charging price policy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model;

[0025] The user management module 02 is at least used to call a first number of physical machine devices according to the target object configuration, wherein the first number is the maximum number of physical machine devices that can be used when running the computing unit;

[0026] The computing power scheduling module 03 is used to adjust the second number of physical machine devices in real time according to the operating status of the computing power unit, wherein the first number is greater than the second number.

[0027] In the computing power scheduling system, the physical machine device 01 is at least used to provide physical machine devices for the operation of the computing power unit, and the computing power unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of the sample object and labels for identifying the charging price strategy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide labels for the charging strategy generation model; the user management module 02 is at least used to call the first number of physical machine devices according to the target object configuration, wherein the first number is the maximum number of physical machine devices that can be used when running the computing power unit; the computing power scheduling module 03 is used to adjust the second number of physical machine devices in real time according to the operating status of the computing power unit, wherein the first number is greater than the second number, thereby achieving the technical effect of automatically adjusting the physical machine device resources in real time according to the computing power unit, thereby solving the technical problems of poor real-time performance and low efficiency caused by manually allocating physical machine device resources to the computing power unit in the related technology.

[0028] It should be noted that the computing power unit corresponds one-to-one to the sandbox. It can be understood that the sandbox is used to run the first target task and the second target task.

[0029] In some embodiments of the present application, the second number of physical machine devices can be adjusted in real time according to the running status of the computing power unit. Specifically: the running status of the first target task is obtained, and when the first target task is in an idle state, the third number of physical machine devices corresponding to the first target task is allocated to the second target task; the running status of the second target task is obtained, and when the second target task is in an idle state, the fourth number of physical machine devices corresponding to the second target task is allocated to the first target task.

[0030] In some optional embodiments of the present application, the computing power scheduling module is also used to exit the first target task and / or the second target task from the scheduling sequence when the first target task and / or the second target task is completed, wherein the scheduling sequence includes multiple tasks to be executed and physical machine devices corresponding to the tasks to be executed.

[0031] In some embodiments of the present application, the computing power scheduling module is also used to determine the third target task and temporarily suspend the third target task according to the priority of each system module when the remaining number corresponding to the physical machine device is less than a predetermined threshold, wherein the system module includes: a computing power scheduling module, a user management module and a data analysis module.

[0032] In some optional embodiments of the present application, the user management module has the highest priority. The third target task can be determined according to the priorities of each system module, and the third target task can be temporarily suspended. Specifically: an input instruction of the target object is received, wherein the input instruction is used to indicate the priority of the computing power scheduling module or the data analysis module; when the input instruction indicates that the priority of the computing power scheduling module is lower than the priority of the data analysis module, the running task of the computing power module is used as the third target task, and the third target task is temporarily suspended; when the input instruction indicates that the priority of the computing power scheduling module is higher than the priority of the data analysis module, the running task of the data analysis module is used as the third target task, and the third target task is temporarily suspended.

[0033] It should be noted that the physical machine equipment includes but is not limited to: a central processing unit CPU and a graphics processing unit GPU.

[0034] The computing power scheduling system in some embodiments of the present application can be a distributed computing platform. Specifically, the tasks performed by the computing power scheduling module are completed on different physical machines. For example, the training and simulation environment of the charging model are completed on different physical machines. The tasks corresponding to the computing power scheduling module, the data analysis module, and the user management module can also be completed on different physical machines. The charging strategy model and the charging network simulation environment are planned as independent executable programs as a computing power unit that can be scheduled, and the system assigns the priority of the computing power unit, and then multiple sandboxes are started for the verification of the charging strategy, and each sandbox corresponds to a computing power unit.

[0035] The computing power scheduling module is responsible for allocating resources that respond to computing power. The computing power units that have completed their work exit the scheduling sequence and return the processing results to the upper-level data analysis module. The processing results include but are not limited to: the convergence of the objective function and the simulation effect of the trained model. When computing power resources are insufficient, the computing power scheduling system will automatically (temporarily) remove the low-priority computing power units from the scheduling sequence to ensure the computing power requirements of high-priority events. The user management module can allocate the maximum computing power required to different users, that is, the maximum number threshold of physical machine devices.

[0036] It can be understood that the computing power scheduling system in the embodiment of the present application has a distributed computing platform, including server hardware, a computing power scheduling module, a data analysis module and a user management module. The charging strategy model and the charging network simulation environment are planned as independently executable programs. As a computing power unit that can be scheduled, the system assigns the priority of the computing power unit. When the computing power resources are insufficient, the computing power scheduling system will automatically remove the computing power units with low priority from the scheduling sequence, so that the computing power requirements of the charging strategy model and the simulation environment can be reasonably allocated and optimized, thereby improving the utilization efficiency of the hardware system.

[0037] Figure 2 A computing power scheduling method according to an embodiment of the present application can be applied to distributed platforms, such as Figure 2 As shown, including:

[0038] S102, obtaining the number of currently available physical machine devices;

[0039] S104, determining the target number of physical machines required by the computing unit;

[0040] S106, allocate the target number of physical machine devices required by the computing power unit to the computing power unit, wherein the computing power unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of the sample object and a label for identifying the charging price strategy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model.

[0041] In the computing power scheduling method, the number of currently available physical machine devices is obtained; the target number of physical machine devices required by the computing power unit is determined; and the target number of physical machine devices required by the computing power unit is allocated to the computing power unit, wherein the computing power unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task, respectively, wherein the charging strategy generation model is obtained through multiple groups of training data, and each group of data in the multiple groups of training data includes: charging behavior characteristic parameters of the sample object and a label for identifying the charging price policy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model, thereby achieving the technical effect of automatically adjusting the physical machine device resources in real time according to the computing power unit, thereby solving the technical problems of poor real-time performance and low efficiency caused by the manual allocation of physical machine device resources to the computing power unit in the related technology.

[0042] In an embodiment of the present application, a method of automatically scheduling hardware resources is adopted, and a physical machine device is used to at least provide a physical machine device for the operation of a computing unit. The computing unit is used to configure a charging strategy generation model and a charging network simulation environment as a first target task and a second target task, respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of a sample object and a label for identifying a charging price policy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model; a user management module is used to at least call a first number of physical machine devices according to the target object configuration, wherein the first number is the maximum number of physical machine devices that can be used when running the computing unit; a computing power scheduling module is used to adjust the second number of physical machine devices in real time according to the operating status of the computing unit, wherein the first number is greater than the second number, thereby achieving a technical effect of automatically adjusting the physical machine device resources in real time according to the computing unit, thereby solving the technical problems of poor real-time performance and low efficiency caused by manually allocating physical machine device resources to the computing unit in the related art.

[0043] According to another aspect of an embodiment of the present application, a non-volatile storage medium is also provided, and the non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above-mentioned computing power scheduling method.

[0044] Specifically, the above storage medium is used to store program instructions for executing the following functions to achieve the following functions:

[0045] Obtain the number of currently available physical machine devices; determine the target number of physical machine devices required by the computing power unit; allocate the target number of physical machine devices required by the computing power unit to the computing power unit, wherein the computing power unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task, respectively, wherein the charging strategy generation model is obtained through multiple groups of training data, and each group of data in the multiple groups of training data includes: charging behavior characteristic parameters of the sample object and a label for identifying the charging price strategy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model.

[0046] According to another aspect of an embodiment of the present application, a processor is also provided, and the processor is used to run a program, wherein the above-mentioned computing power scheduling method is executed when the program is running.

[0047] Specifically, the processor is used to call the program instructions in the memory to implement the following functions:

[0048] Obtain the number of currently available physical machine devices; determine the target number of physical machine devices required by the computing power unit; allocate the target number of physical machine devices required by the computing power unit to the computing power unit, wherein the computing power unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task, respectively, wherein the charging strategy generation model is obtained through multiple groups of training data, and each group of data in the multiple groups of training data includes: charging behavior characteristic parameters of the sample object and a label for identifying the charging price strategy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide a label for the charging strategy generation model.

[0049] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0050] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0051] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0052] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0053] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0054] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0055] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A computing power scheduling system, It is characterized in that include: A physical machine device, at least used to provide a physical machine device for the operation of a computing unit, wherein the computing unit is used to configure a charging strategy generation model and a charging network simulation environment as a first target task and a second target task, respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of a sample object and a label for identifying a charging price strategy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide the label for the charging strategy generation model; A user management module is at least used to call a first number of the physical machine devices according to the target object configuration, wherein the first number is a maximum number of physical machine devices that can be used when running the computing unit; A computing power scheduling module, configured to adjust the second number of the physical machine devices in real time according to the operating status of the computing power unit, wherein the first number is greater than the second number; when the remaining number corresponding to the physical machine devices is less than a predetermined threshold, determine a third target task according to the priority of each system module, and temporarily suspend the third target task, wherein the system module includes: the computing power scheduling module, the user management module and the data analysis module; The user management module has the highest priority. According to the priorities of each system module, the third target task is determined and the third target task is temporarily suspended, including: receiving an input instruction of the target object, wherein the input instruction is used to indicate the priority of the computing power scheduling module or the data analysis module; when the input instruction indicates that the priority of the computing power scheduling module is lower than the priority of the data analysis module, the running task of the computing power scheduling module is used as the third target task, and the third target task is temporarily suspended; when the input instruction indicates that the priority of the computing power scheduling module is higher than the priority of the data analysis module, the running task of the data analysis module is used as the third target task, and the third target task is temporarily suspended.

2. The system according to claim 1, It is characterized in that The computing power units correspond one to one with the sandboxes, and the sandboxes are used to run the first target task and the second target task.

3. The system according to claim 1, It is characterized in that Adjusting the second number of the physical machine devices in real time according to the operating state of the computing unit includes: Acquire the running status of the first target task, and when the first target task is in an idle state, allocate a third number of physical machine devices corresponding to the first target task to the second target task; The running state of the second target task is acquired, and when the second target task is in an idle state, a fourth number of physical machine devices corresponding to the second target task are allocated to the first target task.

4. The system according to claim 1, It is characterized in that The computing power scheduling module is also used to withdraw the first target task and / or the second target task from the scheduling sequence when the first target task and / or the second target task are completed, wherein the scheduling sequence includes multiple tasks to be executed and the physical machine devices corresponding to the tasks to be executed.

5. The system according to any one of claims 1 to 4, It is characterized in that The physical machine device includes: a central processing unit CPU and a graphics processing unit GPU.

6. A computing power scheduling method, It is characterized in that The method is applied on a distributed platform, including: Get the number of currently available physical machine devices; Determine the target number of physical machines required for the computing unit; Allocate the target number of physical machine devices required by the computing power unit to the computing power unit, wherein the computing power unit is used to configure the charging strategy generation model and the charging network simulation environment as the first target task and the second target task respectively, wherein the charging strategy generation model is obtained through multiple sets of training data, and each set of data in the multiple sets of training data includes: charging behavior characteristic parameters of the sample object and a label for identifying the charging price policy corresponding to the charging behavior characteristic parameters of the sample object, wherein the charging network simulation environment is used to provide the label for the charging strategy generation model; When the remaining number corresponding to the physical machine device is less than a predetermined threshold, a third target task is determined according to the priority of each system module, and the third target task is temporarily suspended, wherein the system module includes: a computing power scheduling module, a user management module and a data analysis module; The user management module has the highest priority. According to the priorities of each system module, the third target task is determined and the third target task is temporarily suspended, including: receiving an input instruction of the target object, wherein the input instruction is used to indicate the priority of the computing power scheduling module or the data analysis module; when the input instruction indicates that the priority of the computing power scheduling module is lower than the priority of the data analysis module, the running task of the computing power scheduling module is used as the third target task, and the third target task is temporarily suspended; when the input instruction indicates that the priority of the computing power scheduling module is higher than the priority of the data analysis module, the running task of the data analysis module is used as the third target task, and the third target task is temporarily suspended.

7. A non-volatile storage medium, It is characterized in that The non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the computing power scheduling method described in claim 6.

8. A processor, It is characterized in that The processor is used to run a program, wherein the computing power scheduling method described in claim 6 is executed when the program is run.