Single data center time domain migration task scheduling method, system and device and storage medium

Abstract

The invention discloses a single data center time domain migration task scheduling method, system and device and a storage medium. The method comprises the following steps: acquiring green power parameters in a power grid; a green electricity parameter is used as an optimal target, an optimization target function is constructed, and an optimization scheduling model and an optimal economic model mechanism based on a single data center are established; setting decision variables and constraint conditions of the optimization scheduling model based on the single data center, solving an optimal solution of the optimization scheduling model based on the single data center and the optimal economic model mechanism by adopting a deep learning algorithm, and obtaining a final optimization result and a scheduling optimization scheme by taking the optimal solution as a basis of power grid optimization scheduling; the system comprises a data acquisition module, a model construction module and a model solving module. According to the method, optimization and adjustment of green power and economic operation data are facilitated, the resource utilization rate and the new energy scheduling efficiency are improved, and the scheduling cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data center resource optimization and regulation for green electricity consumption and economic operation, and in particular to a method, system, device and storage medium for scheduling time-domain migration tasks in a single data center. Background Art

[0002] With the rapid development of distributed energy, it can not only make full use of renewable energy such as wind, light, and water, but also provide a power supply method for remote areas that saves transmission costs and improves power supply reliability. However, distributed energy such as wind power and photovoltaic power is limited by the characteristics of the resources themselves, and has characteristics such as randomness and intermittency, making it difficult to accurately predict the output. At the same time, the characteristics of small capacity, large number, and geographical dispersion further increase the grid connection cost and management difficulty of distributed energy.

[0003] The energy dispatching system is an organic coordination of energy networks, energy production, conversion, storage, consumption and terminal use participants. It is a complex multi-energy coupling system. Due to the diverse energy needs of multiple users in the energy dispatching system, different types of energy are tightly coupled and flexibly converted, which brings huge challenges to the coordinated operation and energy management of the system. Due to the different transmission stability of green electricity production and traditional electricity production, when facing the data volume of data center resources for green electricity consumption and economic operation, due to the differences in various constraints, the scheduling plan often changes, and there is no certain long-term regularity to follow. Therefore, there is an urgent need for a single data center time domain migration task scheduling method that can adapt green electricity and economy to obtain the best resource scheduling plan. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide a method, system, device and storage medium for scheduling time-domain migration tasks in a single data center.

[0005] In order to achieve the above technical objectives and the above technical effects, the present invention is implemented through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for scheduling time domain migration tasks in a single data center, comprising:

[0007] Obtain green power parameters in the power grid;

[0008] Taking green electricity parameters as the optimal target, construct the optimization objective function, and establish the optimization scheduling model and optimal economic model mechanism based on a single data center;

[0009] The decision variables and constraints of the optimization scheduling model based on a single data center are set, and the deep learning algorithm is used to obtain the optimal solution of the optimization scheduling model based on a single data center and the optimal economic model mechanism. The optimal solution is used as the basis for the optimal scheduling of the power grid to obtain the final optimization result and scheduling optimization plan.

[0010] Furthermore, the green electricity parameters include a green electricity part, and the green electricity part includes a green electricity production cost, a green electricity consumption ratio, a green electricity local consumption rate, a green electricity production ratio, a solar curtailment ratio, and a green electricity dispatching cost.

[0011] The calculation formula of green electricity production cost W1(T) is as follows:

[0012]

[0013] Where: t represents the time, a(t) represents the green electricity purchase price, b(t) represents the green electricity produced at time t, m(t) represents the total electricity produced by the power grid at time t, and μ represents the dispatching green electricity storage conversion rate;

[0014] The calculation formula of green electricity consumption ratio W2(T) is as follows:

[0015]

[0016] The calculation formula of green power grid connection rate W3(T) is as follows:

[0017]

[0018] Among them, C t is the load power consumption at time t, D t is the amount of green electricity discharged at time t, P t is the solar power generation at time t;

[0019] The calculation formula of green electricity generation ratio W4(T) is as follows:

[0020]

[0021] The calculation formula of abandoned light ratio W5(T) is as follows:

[0022]

[0023] Among them, P l The amount of abandoned photovoltaic power at time t:

[0024] The calculation formula of green electricity dispatch cost W6(T) is as follows:

[0025]

[0026] Where: subscript t represents the dispatch time, subscript s represents the energy dispatch service provider, C g，b represents the cost of unit solar energy dispatch, is the solar power generation dispatched by the energy dispatch service provider s at time i; C h，b represents the unit hydropower dispatching cost, is the amount of water and electricity dispatched by the energy dispatch service provider s at time t, C H2，b represents the unit wind power dispatch cost; is the wind power generation dispatched by the energy dispatch service provider s at time t.

[0027] Furthermore, the green electricity parameter includes a non-green electricity part, and the non-green electricity part includes the power consumption of a single data center, and the calculation formula is as follows:

[0028]

[0029] in: is the power consumption of a single data center device in time period t, n is the number of single data center devices; G f and G i are the maximum power and zero-load power of a single data center device respectively; δ c is the arithmetic memory operation rate of the devices in the single data center c.

[0030] Furthermore, the optimization objective function calculation formula is as follows:

[0031]

[0032] Among them, H is the optimal economic objective function value, Δ S The profit value of energy dispatching service providers participating in dispatching. is the profit value of the i-th energy dispatch service provider participating in the dispatch, ω i is the contribution value of the i-th green electricity dispatching system, σ is the repayment coefficient of the i-th green electricity dispatching system, and ε is the correction coefficient.

[0033] Furthermore, the deep learning algorithm is a neural network algorithm based on the time domain changes of green power consumption, and its activation function

[0034]

[0035] Where n is the number of objective functions, W n (T) is the target optimization function, and x is the input of the activation function.

[0036] In a second aspect, the present invention provides a single data center time domain migration task scheduling system, comprising:

[0037] A data acquisition module is used to obtain green power parameters in the power grid;

[0038] The model building module is used to construct the optimization objective function with green electricity parameters as the optimal target, and to establish the optimization scheduling model and the optimal economic model mechanism based on a single data center;

[0039] The model solving module is used to set the decision variables and constraints of the optimization scheduling model based on the single data center, and use the deep learning algorithm to obtain the optimal solution of the optimization scheduling model based on the single data center and the optimal economic model mechanism. The optimal solution is used as the basis for the optimal scheduling of the power grid to obtain the final optimization result and scheduling optimization plan.

[0040] Furthermore, the data acquisition module is used to acquire green power parameters in the power grid;

[0041] The green electricity parameters include the green electricity part, which includes the green electricity production cost, green electricity consumption ratio, green electricity local consumption rate, green electricity production ratio, abandoned solar ratio and green electricity dispatching cost.

[0042] The calculation formula of green electricity production cost W1(T) is as follows:

[0043]

[0044] Where: t represents the time, a(t) represents the green electricity purchase price, b(t) represents the green electricity produced at time t, m(t) represents the total electricity produced by the power grid at time t, and μ represents the dispatching green electricity storage conversion rate;

[0045] The calculation formula of green electricity consumption ratio W2(T) is as follows:

[0046]

[0047] The calculation formula of green power grid connection rate W3(T) is as follows:

[0048]

[0049] Among them, C t is the load power consumption at time t, D t is the amount of green electricity discharged at time t, P t is the solar power generation at time t;

[0050] The calculation formula of green electricity generation ratio W4(T) is as follows:

[0051]

[0052] The calculation formula of abandoned light ratio W5(T) is as follows:

[0053]

[0054] Among them, P l The amount of abandoned photovoltaic power at time t:

[0055] The calculation formula of green electricity dispatch cost W6(T) is as follows:

[0056]

[0057] Where: subscript t represents the dispatch time, subscript s represents the energy dispatch service provider, C g，b represents the cost of unit solar energy dispatch, is the solar power generation dispatched by the energy dispatch service provider s at time t; C h，b represents the unit hydropower dispatching cost, is the amount of water and electricity dispatched by the energy dispatch service provider s at time i, C H2，b represents the unit wind power dispatch cost; is the wind power generation dispatched by the energy dispatch service provider s at time t.

[0058] Furthermore, the data acquisition module is used to acquire green power parameters in the power grid;

[0059] The green electricity parameter includes the non-green electricity part, and the non-green electricity part includes the power consumption of a single data center. The calculation formula is as follows:

[0060]

[0061] in: is the power consumption of a single data center device in time period t, n is the number of single data center devices; G f and G i are the maximum power and zero-load power of a single data center device; δ c is the arithmetic memory operation rate of the devices in the single data center c.

[0062] Furthermore, the model building module is used to construct an optimization objective function using green electricity parameters as the optimal target, and to establish an optimization scheduling model and an optimal economic model mechanism based on a single data center;

[0063] The optimization objective function calculation formula is as follows:

[0064]

[0065] Among them, H is the optimal economic objective function value, Δ S The profit value of energy dispatching service providers participating in dispatching. is the profit value of the i-th energy dispatch service provider participating in the dispatch, ω i is the contribution value of the i-th green electricity dispatching system, σ is the repayment coefficient of the i-th green electricity dispatching system, and ε is the correction coefficient.

[0066] Furthermore, the model solving module is used to set the decision variables and constraints of the optimization scheduling model based on the single data center, use the deep learning algorithm to find the optimal solution of the optimization scheduling model based on the single data center and the optimal economic model mechanism, and use the optimal solution as the basis for the power grid optimization scheduling to obtain the final optimization result and scheduling optimization plan.

[0067] The deep learning algorithm is a neural network algorithm based on the time domain changes of green power consumption, and its activation function k(x) is:

[0068]

[0069] Where n is the number of objective functions, W n (T) is the target optimization function, and x is the input of the activation function.

[0070] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the program is executed, the steps of the single data center time domain migration task scheduling method are implemented.

[0071] In a fourth aspect, the present invention provides a computer-readable storage medium, hereinafter referred to as the storage medium, in which a computer program is stored, and the storage medium is designed to implement the steps of the single data center time domain migration task scheduling method when running.

[0072] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages: based on some existing green electricity scheduling optimization objective function models, considering the use of a single data center to solve the problem of excessive equipment redundancy, and considering the equipment power consumption and green electricity scheduling cost factors, building an optimization scheduling model based on a single data center, and establishing an optimal economic model mechanism to optimize and adjust using constraints; based on the neural network algorithm of the time domain changes in green electricity consumption, improving its activation function to find the optimal solution of the scheduling model, thereby improving resource utilization, improving the scheduling efficiency of new energy, and reducing scheduling costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 is a flow chart of the present invention;

[0074] Figure 2 It is a schematic diagram of the task scheduling structure of the present invention;

[0075] Figure 3 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION

[0076] The technical solution of the present invention is further described below in conjunction with the accompanying drawings. It will be understood by those skilled in the art that the purposes and advantages that can be achieved by the present invention are not limited to the specific description of the above beneficial effects, and the above and other purposes that can be achieved by the present invention will be more clearly understood based on the following detailed description.

[0077] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed in the present invention can be implemented in hardware, software or a combination of the two. Whether it is implemented in hardware or software depends on the specific application and design of the technical solution. Professional and technical personnel can use different methods to implement the functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0078] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0079] Embodiment 1

[0080] The present invention provides a method for scheduling time domain migration tasks in a single data center, such as Figure 1 As shown, the following steps are included:

[0081] Obtain green electricity parameters in the power grid, including green electricity and non-green electricity. The green electricity part includes green electricity production cost, green electricity consumption ratio, green electricity local consumption rate, green electricity production ratio, abandoned light ratio and green electricity dispatching cost. The non-green electricity part includes the power consumption of a single data center.

[0082] Taking green electricity parameters as the optimal target, construct the optimization objective function, and establish the optimization scheduling model and optimal economic model mechanism based on a single data center;

[0083] The decision variables and constraints of the optimization scheduling model based on a single data center are set, and the deep learning algorithm is used to obtain the optimal solution of the optimization scheduling model based on a single data center and the optimal economic model mechanism. The optimal solution is used as the basis for the optimal scheduling of the power grid to obtain the final optimization result and scheduling optimization plan.

[0084] The green electricity part includes green electricity production cost, green electricity consumption ratio, green electricity local consumption rate, green electricity production ratio, abandoned solar ratio and green electricity dispatching cost.

[0085] The calculation formula of green electricity production cost W1(T) is as follows:

[0086]

[0087] Where: t represents the time, a(t) represents the green electricity purchase price, b(t) represents the green electricity produced at time t, m(t) represents the total electricity produced by the power grid at time t, and μ represents the dispatching green electricity storage conversion rate;

[0088] The calculation formula of green electricity consumption ratio W2(T) is as follows:

[0089]

[0090] The calculation formula of green power grid connection rate W3(T) is as follows:

[0091]

[0092] Among them, C t is the load power consumption at time t, D t is the amount of green electricity discharged at time t, P t is the solar power generation at time t;

[0093] The calculation formula of green electricity generation ratio W4(T) is as follows:

[0094]

[0095] The calculation formula of abandoned light ratio W5(T) is as follows:

[0096]

[0097] Among them, P l The amount of abandoned photovoltaic power at time t:

[0098] The calculation formula of green electricity dispatch cost W6(T) is as follows:

[0099]

[0100] Where: subscript t represents the dispatch time, subscript s represents the energy dispatch service provider, C g，b represents the cost of unit solar energy dispatch, is the solar power generation dispatched by the energy dispatch service provider s at time i; C h，b represents the unit hydropower dispatching cost, is the amount of water and electricity dispatched by the energy dispatch service provider s at time t, C H2，b represents the unit wind power dispatch cost; is the wind power generation dispatched by the energy dispatch service provider s at time t.

[0101] The non-green electricity part includes the power consumption of a single data center, and the calculation formula is as follows:

[0102]

[0103] in: is the power consumption of a single data center device in time period t, n is the number of single data center devices; G f and G i are the maximum power and zero-load power of a single data center device respectively; δ c is the arithmetic memory operation rate of the devices in the single data center c.

[0104] The optimization objective function calculation formula is as follows:

[0105]

[0106] Among them, H is the optimal economic objective function value, Δ S The profit value of energy dispatching service providers participating in dispatching. is the profit value of the i-th energy dispatch service provider participating in the dispatch, ω i is the contribution value of the i-th green electricity dispatching system, σ is the repayment coefficient of the i-th green electricity dispatching system, and ε is the correction coefficient.

[0107] Embodiment 2

[0108] In addition, based on the same inventive concept, an embodiment of the present invention further provides a single data center time domain migration task scheduling system, including:

[0109] A data acquisition module is used to obtain green power parameters in the power grid;

[0110] The model building module is used to construct the optimization objective function with green electricity parameters as the optimal target, and to establish the optimization scheduling model and the optimal economic model mechanism based on a single data center;

[0111] The model solving module is used to set the decision variables and constraints of the optimization scheduling model based on the single data center, and use the deep learning algorithm to obtain the optimal solution of the optimization scheduling model based on the single data center and the optimal economic model mechanism. The optimal solution is used as the basis for the optimal scheduling of the power grid to obtain the final optimization result and scheduling optimization plan.

[0112] The data acquisition module is used to acquire green power parameters in the power grid;

[0113] The green electricity parameters include the green electricity part, which includes the green electricity production cost, green electricity consumption ratio, green electricity local consumption rate, green electricity production ratio, abandoned solar ratio and green electricity dispatching cost.

[0114] The calculation formula of green electricity production cost W1(T) is as follows:

[0115]

[0116] Where: t represents the time, a(t) represents the green electricity purchase price, b(t) represents the green electricity produced at time t, m(t) represents the total electricity produced by the power grid at time t, and μ represents the dispatching green electricity storage conversion rate;

[0117] The calculation formula of green electricity consumption ratio W2(T) is as follows:

[0118]

[0119] The calculation formula of green power grid connection rate W3(T) is as follows:

[0120]

[0121] Among them, C t is the load power consumption at time t, D t is the amount of green electricity discharged at time t, P t is the solar power generation at time t;

[0122] The calculation formula of green electricity generation ratio W4(T) is as follows:

[0123]

[0124] The calculation formula of abandoned light ratio W5(T) is as follows:

[0125]

[0126] Among them, P l The amount of abandoned photovoltaic power at time t:

[0127] The calculation formula of green electricity dispatch cost W6(T) is as follows:

[0128]

[0129] Where: subscript t represents the dispatch time, subscript s represents the energy dispatch service provider, C g，b represents the cost of unit solar energy dispatch, is the solar power generation dispatched by the energy dispatch service provider s at time i; C h，b represents the unit hydropower dispatching cost, is the amount of water and electricity dispatched by the energy dispatch service provider s at time i, C H2，b represents the unit wind power dispatch cost; is the wind power generation dispatched by the energy dispatch service provider s at time i.

[0130] The data acquisition module is used to acquire green power parameters in the power grid;

[0131] The green electricity parameter includes the non-green electricity part, and the non-green electricity part includes the power consumption of a single data center. The calculation formula is as follows:

[0132]

[0133] in: is the power consumption of a single data center device in time period t, n is the number of single data center devices; G f and G i are the maximum power and zero-load power of a single data center device respectively; δ c is the arithmetic memory operation rate of the devices in the single data center c.

[0134] The model building module is used to construct an optimization objective function with green electricity parameters as the optimal target, and to establish an optimization scheduling model and an optimal economic model mechanism based on a single data center;

[0135] The optimization objective function calculation formula is as follows:

[0136]

[0137] Among them, H is the optimal economic objective function value, Δ S The profit value of energy dispatching service providers participating in dispatching. is the profit value of the i-th energy dispatch service provider participating in the dispatch, ω i is the contribution value of the i-th green electricity dispatching system, σ is the repayment coefficient of the i-th green electricity dispatching system, and ε is the correction coefficient.

[0138] The model solving module is used to set the decision variables and constraints of the optimization scheduling model based on the single data center, use the deep learning algorithm to find the optimal solution of the optimization scheduling model based on the single data center and the optimal economic model mechanism, and use the optimal solution as the basis for the optimization scheduling of the power grid to obtain the final optimization result and scheduling optimization plan

[0139] The deep learning algorithm is a neural network algorithm based on the time domain changes of green power consumption, and its activation function k(x) is:

[0140]

[0141] Where n is the number of objective functions, W n (T) is the target optimization function, and x is the input of the activation function.

[0142] Embodiment 3

[0143] In addition, based on the same inventive concept, an embodiment of the present invention also provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the single data center time domain migration task scheduling method are implemented.

[0144] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0145] Embodiment 4

[0146] In addition, based on the same inventive concept, an embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is designed to implement the steps of the single data center time domain migration task scheduling method when running.

[0147] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0148] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0149] The computer-readable storage medium mentioned above may be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0150] The specific description above further illustrates the purpose, technical solutions and beneficial effects of the invention in detail. It should be understood that the above is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for scheduling time-domain migration tasks in a single data center, characterized in that: include: Obtain green power parameters in the power grid; Taking green electricity parameters as the optimal target, construct the optimization objective function, and establish the optimization scheduling model and optimal economic model mechanism based on a single data center; The decision variables and constraints of the optimization scheduling model based on a single data center are set, and the deep learning algorithm is used to obtain the optimal solution of the optimization scheduling model based on a single data center and the optimal economic model mechanism. The optimal solution is used as the basis for the optimal scheduling of the power grid to obtain the final optimization result and scheduling optimization plan.

2. The method for scheduling time-domain migration tasks of a single data center according to claim 1, characterized in that: The green electricity parameters include the green electricity part, which includes the green electricity production cost, green electricity consumption ratio, green electricity local consumption rate, green electricity production ratio, abandoned solar power ratio and green electricity dispatching cost. The calculation formula of green electricity production cost W1(T) is as follows: Where: t represents the time, a(t) represents the green electricity purchase price, b(t) represents the green electricity produced at time t, m(t) represents the total electricity produced by the power grid at time t, and μ represents the dispatching green electricity storage conversion rate; The calculation formula of green electricity consumption ratio W2(T) is as follows: The calculation formula of green power grid connection rate W3(T) is as follows: Among them, C t is the load power consumption at time t, D t is the amount of green electricity discharged at time t, P t is the solar power generation at time t; The calculation formula of green electricity generation ratio W4(T) is as follows: The calculation formula of abandoned light ratio W5(T) is as follows: Among them, Pl is the amount of abandoned photovoltaic power at time t: The calculation formula of green electricity dispatch cost W6(T) is as follows: Where: subscript t represents the dispatch time, subscript s represents the energy dispatch service provider, C g，b represents the cost of unit solar energy dispatch, is the solar power generation dispatched by the energy dispatch service provider s at time t; C h，b represents the unit hydropower dispatching cost, is the amount of water and electricity dispatched by the energy dispatch service provider s at time t, C H2，b represents the unit wind power dispatch cost; is the wind power generation dispatched by the energy dispatch service provider s at time t.

3. The method for scheduling time-domain migration tasks of a single data center according to claim 1, characterized in that: The green electricity parameter includes a non-green electricity part, and the non-green electricity part includes the power consumption of a single data center, and the calculation formula is as follows: in: is the power consumption of a single data center device in time period t, n is the number of single data center devices; G f and G i are the maximum power and zero-load power of a single data center device respectively; δ c is the arithmetic memory operation rate of the devices in the single data center c.

4. The method for scheduling time-domain migration tasks of a single data center according to claim 1, characterized in that: The optimization objective function calculation formula is as follows: Among them, H is the optimal economic objective function value, Δ S The profit value of energy dispatching service providers participating in dispatching. is the profit value of the i-th energy dispatch service provider participating in the dispatch, ω i is the contribution value of the i-th green electricity dispatching system, σ is the repayment coefficient of the i-th green electricity dispatching system, and ε is the correction coefficient.

5. The method for scheduling time-domain migration tasks of a single data center according to claim 1, characterized in that: The deep learning algorithm is a neural network algorithm based on the time domain changes of green power consumption, and its activation function k(x) is: Where n is the number of objective functions, W n (T) is the target optimization function, and x is the input of the activation function.

6. A single data center time domain migration task scheduling system, characterized in that: include: A data acquisition module is used to obtain green power parameters in the power grid; The model building module is used to construct the optimization objective function with green electricity parameters as the optimal target, and to establish the optimization scheduling model and the optimal economic model mechanism based on a single data center; The model solving module is used to set the decision variables and constraints of the optimization scheduling model based on the single data center, and use the deep learning algorithm to obtain the optimal solution of the optimization scheduling model based on the single data center and the optimal economic model mechanism. The optimal solution is used as the basis for the optimal scheduling of the power grid to obtain the final optimization result and scheduling optimization plan.

7. The single data center time domain migration task scheduling system according to claim 6 is characterized in that: The data acquisition module is used to acquire green power parameters in the power grid; The green electricity parameters include the green electricity part, which includes the green electricity production cost, green electricity consumption ratio, green electricity local consumption rate, green electricity production ratio, abandoned solar ratio and green electricity dispatching cost. The calculation formula of green electricity production cost W1(T) is as follows: Where: t represents the time, a(t) represents the green electricity purchase price, b(t) represents the green electricity produced at time t, m(t) represents the total electricity produced by the power grid at time t, and μ represents the dispatching green electricity storage conversion rate; The calculation formula of green electricity consumption ratio W2(T) is as follows: The calculation formula of green power grid connection rate W3(T) is as follows: Among them, C t is the load power consumption at time t, D t is the amount of green electricity discharged at time t, P t is the solar power generation at time t; The calculation formula of green electricity generation ratio W4(T) is as follows: The calculation formula of abandoned light ratio W5(T) is as follows: Among them, P l The amount of abandoned photovoltaic power at time t: The calculation formula of green electricity dispatch cost W6(T) is as follows: Where: subscript t represents the dispatch time, subscript s represents the energy dispatch service provider, C g，b represents the cost of unit solar energy dispatch, is the solar power generation dispatched by the energy dispatch service provider s at time t; C h，b represents the unit hydropower dispatching cost, is the amount of water and electricity dispatched by the energy dispatch service provider s at time t, C H2，b represents the unit wind power dispatch cost; is the wind power generation dispatched by the energy dispatch service provider s at time t.

8. The single data center time domain migration task scheduling system according to claim 6, characterized in that: The data acquisition module is used to acquire green power parameters in the power grid; The green electricity parameter includes the non-green electricity part, and the non-green electricity part includes the power consumption of a single data center. The calculation formula is as follows: in: is the power consumption of a single data center device in time period t, n is the number of single data center devices; G f and G i are the maximum power and zero-load power of a single data center device respectively; δ c is the arithmetic memory operation rate of the devices in the single data center c.

9. The single data center time domain migration task scheduling system according to claim 6, characterized in that: The model building module is used to construct an optimization objective function with green electricity parameters as the optimal target, and to establish an optimization scheduling model and an optimal economic model mechanism based on a single data center; The optimization objective function calculation formula is as follows: Among them, H is the optimal economic objective function value, Δ S The profit value of energy dispatching service providers participating in dispatching. is the profit value of the i-th energy dispatch service provider participating in the dispatch, ω i is the contribution value of the i-th green electricity dispatching system, σ is the repayment coefficient of the i-th green electricity dispatching system, and ε is the correction coefficient.

10. The single data center time domain migration task scheduling system according to claim 6, characterized in that: The model solving module is used to set the decision variables and constraints of the optimization scheduling model based on the single data center, use the deep learning algorithm to find the optimal solution of the optimization scheduling model based on the single data center and the optimal economic model mechanism, and use the optimal solution as the basis for the optimization scheduling of the power grid to obtain the final optimization result and scheduling optimization plan The deep learning algorithm is a neural network algorithm based on the time domain changes of green power consumption, and its activation function k(x) is: Where n is the number of objective functions, W n (T) is the target optimization function, and x is the input of the activation function.

11. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the single data center time domain migration task scheduling method is implemented according to any one of claims 1-5.

12. A storage medium storing a computer program, characterized in that: The computer program is designed to implement the single data center time domain migration task scheduling method according to any one of claims 1-5 when running.

Images