Data center load control method, device and system

Abstract

The invention relates to a data center load control method, device and system. The method comprises the following steps: acquiring different electricity price scheme information for a data center, and determining a data center optimization target of each piece of electricity price scheme information based on a data center system operation optimization model; determining an electricity selling object optimization target based on the electricity selling object decision model according to the power grid power supply information and the data center optimization target; preset data center control strategy information is adopted, and target electricity price scheme information is obtained according to the data center optimization target and the electricity selling object optimization target of each piece of electricity price scheme information; obtaining a load optimization result according to the data center optimization target of the target electricity price scheme information; and processing a load optimization result by combining an electricity selling object optimization target of the target electricity price scheme information, a data center system operation optimization model and an electricity selling object decision model to obtain load control information of the data center. By adopting the method, the load optimization of the data center can be realized.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a data center load control method, device, system, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] There are a large number of data centers in industrial parks and their energy consumption demand is increasing. Optimizing their energy demand and reducing energy costs are crucial for data center operators. Power demand response can support the interaction between the power grid and data centers and optimize the energy demand of data centers.

[0003] In traditional technology, two models are usually used to promote data centers and their park tenants to participate in power demand response. The first model is that the power grid provides sufficient incentive signals and encourages park tenants to voluntarily shut down unused servers to reduce load and participate in power demand response through electricity fee subsidies; the second model is that the data center operator reduces its dependence on the power grid during the demand response period by using backup power sources such as diesel generators. With the popularization of integrated energy systems, a large number of park data centers have begun to deploy integrated energy equipment for the sake of power supply reliability. How to formulate a reasonable price-based demand response pricing strategy for data centers is an urgent problem to be solved. Summary of the invention

[0004] Based on this, it is necessary to provide a data center load control method, device, system, computer equipment, computer-readable storage medium and computer program product that can improve the data center load control effect in response to the above technical problems.

[0005] In a first aspect, the present application provides a data center load control method, comprising:

[0006] Obtaining different electricity price scheme information for the data center, and determining the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0007] Based on the decision model for the electricity sales object, according to the power supply information of the power grid and the optimization target of the data center of each of the electricity price scheme information, the optimization target of the electricity sales object of each of the electricity price scheme information is determined; the optimization target of the electricity sales object is used to characterize the monthly power operation status of the electricity sales object;

[0008] Using the preset data center control strategy information, according to the data center optimization target and the power sales object optimization target of each of the electricity price plan information, the target electricity price plan information is obtained;

[0009] Obtaining a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0010] In combination with the optimization target of the power selling object of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model, the load optimization result is processed to obtain the load control information of the data center; the load control information includes the optimization result of the comprehensive energy system and the power purchase result of the power grid.

[0011] In one embodiment, the step of determining the data center optimization target of each electricity price scheme information based on the data center system operation optimization model includes:

[0012] According to each of the electricity price scheme information, the data center system operation optimization model is used as a constraint condition to solve the data center optimization target of each of the electricity price scheme information; the data center system operation optimization model is used to constrain the load optimization strategy information of the data center;

[0013] Among them, the data center system operation optimization model includes a workload measurement model, a server start and stop quantity constraint model, a server start and stop margin constraint model, a server start and stop number constraint model, and a data center system energy consumption model.

[0014] In one embodiment, the decision model based on the electricity selling object determines the optimization target of the electricity selling object of each electricity price scheme information according to the power supply information of the power grid and the optimization target of the data center of each electricity price scheme information, including:

[0015] Obtaining a load optimization strategy feedback result according to the data center optimization target of each of the electricity price scheme information;

[0016] Based on the power supply information of the power grid and the feedback result of the load optimization strategy, the power sales object decision model is used as a constraint condition to solve the optimization target of the power sales object of each electricity price scheme information; the power sales object decision model is used to constrain the comprehensive energy system optimization strategy information and the power grid purchase strategy information of the data center;

[0017] Among them, the optimization objectives of the power sales object include the power grid purchase cost model, the comprehensive energy system operation cost model, and the demand response benefit model; the power sales object decision model includes the cogeneration unit operation constraint model, the diesel generator operation constraint model, the data center waste heat recovery model, the data center power balance model, and the electricity price incentive signal constraint model.

[0018] In one embodiment, the preset data center control strategy information is used to obtain the target electricity price scheme information according to the data center optimization target and the electricity sales object optimization target of each electricity price scheme information, including:

[0019] The improved beetle whisker search algorithm in the data center control strategy information is adopted to perform iterative processing according to the data center optimization target and the power sales object optimization target of each electricity price plan information until the preset iteration end condition is met to obtain the target electricity price plan information; the data center control strategy information is used to calculate the electricity price pricing strategy information of the data center.

[0020] In one embodiment, the method further comprises:

[0021] According to the data center optimization objective function and the electricity sales object optimization objective function, the Tianniu optimization function is constructed;

[0022] Based on the randomly generated electricity price plan information of each iteration, the data center optimization objective function and the electricity sales object optimization objective function are used to perform calculations to obtain the optimization objective function processing result;

[0023] The Tianniu optimization function is used to calculate the processing result of the optimization objective function to obtain the electricity price pricing strategy information of each iteration.

[0024] In a second aspect, the present application also provides a data center load control device, comprising:

[0025] A data center optimization target determination module is used to obtain different electricity price scheme information for the data center, and determine the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0026] The power selling object optimization target determination module is used to determine the power selling object optimization target of each power price scheme information based on the power selling object decision model and the data center optimization target of the power grid power supply information and each power price scheme information; the power selling object optimization target is used to characterize the monthly power operation status of the power selling object;

[0027] A target electricity price scheme information acquisition module is used to obtain target electricity price scheme information based on the data center optimization target and the electricity sales object optimization target of each electricity price scheme information by using preset data center control strategy information;

[0028] A load optimization result obtaining module, used to obtain a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0029] The load control information obtaining module is used to process the load optimization results in combination with the power sales object optimization target of the target electricity price plan information, the data center system operation optimization model, and the power sales object decision model to obtain the load control information of the data center; the load control information includes the comprehensive energy system optimization results and the power grid purchase results.

[0030] In a third aspect, the present application also provides a data center load control system, the system comprising a data center, a power sales object, an integrated energy system, and a power grid:

[0031] The electricity selling object is used to generate different electricity price plan information for the data center;

[0032] The data center is used to obtain the information of the different electricity price plans, and determine the data center optimization target of each of the electricity price plan information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0033] The power selling object is used to determine the optimization target of the power selling object of each of the electricity price scheme information based on the power selling object decision model, according to the power grid power supply information provided by the power grid and the data center optimization target of each of the electricity price scheme information; the power selling object optimization target is used to characterize the monthly power operation status of the power selling object;

[0034] The electricity selling object is used to adopt the preset data center control strategy information, and obtain the target electricity price scheme information according to the data center optimization target and the electricity selling object optimization target of each electricity price scheme information;

[0035] The data center is used to obtain a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0036] The power selling object is used to process the load optimization result in combination with the power selling object optimization target of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model to obtain the load control information of the data center; the load control information includes the comprehensive energy system optimization result and the power grid purchase result;

[0037] The electricity selling object is used to output the optimization result of the integrated energy system to the integrated energy system, and output the power grid purchase result to the power grid.

[0038] In a fourth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the data center load control method as described in the first aspect are implemented.

[0039] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the data center load control method as described in the first aspect are implemented.

[0040] In a sixth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the data center load control method as described in the first aspect.

[0041] The above-mentioned data center load control method, device, system, computer equipment, computer-readable storage medium and computer program product obtain different electricity price plan information for the data center, determine the data center optimization target of each electricity price plan information based on the data center system operation optimization model, and the data center optimization target is used to characterize the monthly power operation of the data center. Based on the power sales object decision model, according to the power supply information of the power grid and the data center optimization target of each electricity price plan information, determine the power sales object optimization target of each electricity price plan information, and the power sales object optimization target is used to characterize the monthly power operation of the power sales object. Then, the preset data center control strategy information is used to obtain the target electricity price plan information according to the data center optimization target of each electricity price plan information and the power sales object optimization target. According to the data center optimization target of the target electricity price plan information, the load optimization result is obtained. Then, combined with the power sales object optimization target of the target electricity price plan information, the data center system operation optimization model, and the power sales object decision model, the load optimization result is processed to obtain the load control information of the data center. The load control information includes the optimization result of the comprehensive energy system and the power purchase result of the power grid, thereby realizing the load optimization of the park data center, being able to design a reasonable electricity price plan for the data center, and effectively improving the load control effect of the data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic diagram of a flow chart of a data center load control method in one embodiment;

[0044] Figure 2 A schematic diagram of a process flow of a price-based demand response pricing strategy for a data center in one embodiment;

[0045] Figure 3A schematic diagram of a load optimization process of a park data center in one embodiment;

[0046] Figure 4 is a flow chart of a data center load control method according to another embodiment;

[0047] Figure 5 is a structural block diagram of a data center load control device in one embodiment;

[0048] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] In an exemplary embodiment, Figure 1 As shown, a data center load control method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 101 to 104. Among them:

[0051] Step 101, obtain different electricity price plan information for the data center, and determine the data center optimization target for each of the electricity price plan information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center.

[0052] In practical applications, power demand side management can be performed based on the data center load control system, such as Figure 2 As shown, the data center load control system may include a data center, a power sales object (such as Figure 2 The electricity sales company), integrated energy system, and power grid can generate pricing strategies for different electricity price plans (i.e., information on different electricity price plans) and send them to the data center. The data center can use the data center system operation optimization model as a constraint condition based on the different electricity price plans obtained to solve the optimal data center optimization objectives under different electricity price plans (i.e., the data center optimization objectives of each electricity price plan information).

[0053] Specifically, the data center can optimize the data center based on the information of each electricity price plan, and DC (which represents the monthly operating cost of the data center) and the load optimization strategy P d，t (which represents the energy consumption of the data center in time period t), (which represents the capacity of the data center participating in demand response regulation during period t on day d) is fed back to the electricity seller.

[0054] Step 102, based on the power selling object decision model, according to the power supply information of the power grid and the data center optimization target of each of the power price plan information, determine the power selling object optimization target of each of the power price plan information; the power selling object optimization target is used to characterize the monthly power operation status of the power selling object.

[0055] In the specific implementation, Figure 2 As shown, the power sales object can be based on the power grid's electricity price incentive signal (i.e., the power grid power supply information), combined with the data center feedback results, and use the power sales object decision model as a constraint condition to solve the optimal power sales object optimization target under different electricity price schemes (i.e., the power sales object optimization target of each electricity price scheme information).

[0056] Optionally, comprehensive energy system optimization strategies can also be obtained (which represents the amount of natural gas consumed by the cogeneration unit on day d in period t), (which represents the electrical power output of the cogeneration machine at time t on day d), (its cogeneration unit is turned on at time t on day d), (which represents the heat load output by the CHP unit at time t on day d), (which indicates that the diesel generator is turned on at time t on day d), (which represents the electrical power output by the diesel generator at time t on day d), (which represents the energy demand of the data center at time t on day d), (which represents the heat load output by the heat pump after waste heat recovery at time t on day d), (which represents the power required for heat pump operation during waste heat recovery at time period t on day d) and power purchase strategy from the power grid (It represents the power supply provided by the power grid to the data center during time period t on day d).

[0057] Step 103, using the preset data center control strategy information, according to the data center optimization target and the power sales object optimization target of each of the electricity price plan information, obtain the target electricity price plan information.

[0058] Specifically, after determining the optimization target of the data center and the optimization target of the power sales object for each electricity price scheme information, the power sales object can use the improved beetle whisker search algorithm to perform iterative calculations based on the preset data center control strategy information, and interact with the data center to confirm until the iteration is completed. Then, the power sales object can use the final iterative pricing strategy q r+1(i.e. target electricity price plan information) is fed back to the data center.

[0059] Step 104, obtaining a load optimization result according to the data center optimization target of the target electricity price scheme information.

[0060] For example, the data center can output the final load optimization strategy P d，t , , that is, the load optimization result is obtained and can be fed back to the electricity sales object.

[0061] Step 105, combining the optimization target of the power selling object of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model, the load optimization result is processed to obtain the load control information of the data center; the load control information includes the optimization result of the integrated energy system and the power purchase result of the power grid.

[0062] In one example, the power seller can obtain the final comprehensive energy system optimization strategy based on the final load optimization strategy output by the data center, combined with the optimization target of the power seller of the target electricity price scheme information, the data center system operation optimization model, and the power seller decision model. , , , , , , , , Power purchase strategy with the power grid (i.e., load control information includes the results of integrated energy system optimization and power grid purchase results), such as Figure 2 As shown, the final integrated energy system optimization strategy and power grid power purchase strategy can be output to the integrated energy system and the power grid respectively.

[0063] Compared with the traditional method, the technical solution of this embodiment designs a reasonable electricity price plan for the data center and takes into account the pricing issue of waste heat in the process of selling waste heat to energy suppliers. The park energy supplier can use the electricity price package design to enable the data center to spontaneously adjust its electricity demand and adjust the losses caused by the data center load based on the incentive subsidies given. The park energy supplier can also recycle the low-grade waste heat of the data center and sell it to other users in the park, and can optimize the load of the park data center in combination with the integrated energy system.

[0064] In the above-mentioned data center load control method, by obtaining different electricity price plan information for the data center, based on the data center system operation optimization model, the data center optimization target of each electricity price plan information is determined, based on the power sales object decision model, according to the power supply information of the power grid and the data center optimization target of each electricity price plan information, the power sales object optimization target of each electricity price plan information is determined, and then the preset data center control strategy information is adopted, according to the data center optimization target of each electricity price plan information and the power sales object optimization target, the target electricity price plan information is obtained, and according to the data center optimization target of the target electricity price plan information, the load optimization result is obtained, and then combined with the power sales object optimization target of the target electricity price plan information, the data center system operation optimization model, and the power sales object decision model, the load optimization result is processed to obtain the load control information of the data center, thereby realizing the load optimization of the park data center, being able to design a reasonable electricity price plan for the data center, and effectively improving the load control effect of the data center.

[0065] In an exemplary embodiment, the step of determining the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model may include the following steps:

[0066] According to each of the electricity price plan information, the data center system operation optimization model is used as a constraint condition to solve the data center optimization target of each of the electricity price plan information; the data center system operation optimization model is used to constrain the load optimization strategy information of the data center.

[0067] Among them, the data center system operation optimization model may include a workload measurement model, a server start and stop quantity constraint model, a server start and stop margin constraint model, a server start and stop number constraint model, and a data center system energy consumption model.

[0068] In practical applications, such as Figure 3 As shown, a data center optimization target can be constructed, and the data center optimization target can be expressed as follows:

[0069]

[0070] Among them, C DC It can represent the monthly operating cost of the data center (i.e., the monthly power operation of the data center); T represents the time period set of a day; D represents the day set of a month; D dr represents the set of demand response days; T dr represents the set of demand response periods in a day; q d，t P represents the electricity price of the data center in time period t on day d, which is set by the electricity seller; d，t is the energy consumption of the data center in period t, e d，tThe unit subsidy given by the electricity seller to the data center for participating in demand response in time period t, represents the capacity of the data center participating in demand response regulation in time period t on day d, t is the calculation time interval; is the unit price of heat load sold by the data center in time period t. is the heat load sold by the data center to campus users at time period t on day d.

[0071] In one example, if Figure 3 As shown, a data center system operation optimization model can be constructed, which can be used to constrain the load optimization strategy of the data center. The data center system operation optimization model includes a workload measurement model, a server start and stop quantity constraint model, a server start and stop margin constraint model, a server start and stop number constraint model, and a data center system energy consumption model.

[0072] The workload calculation model is:

[0073]

[0074] in, It represents the predicted computing demand of the data center at time period t on day d, expressed in the form of a set; is the reduction factor; The sampling interval for measuring workload; To measure the number of samples taken during the workload; represents the maximum computing demand for time period t on day d; Represents the minimum computational requirement for time period t on the dth day.

[0075] The server start and stop quantity constraint model is:

[0076]

[0077] Among them, d，n，t and os d，n，t is an auxiliary variable introduced; N represents the total number of servers in the data center; is the penalty factor of the data center user regarding the server start and stop margin in time period t; represents the server CPU processing rate of data center server n in time period t on day d; The maximum processing rate of the server CPU; is the minimum processing rate of the server CPU; d，n，t represents the server startup status of data center server n at time period t on day d; M is a maximum value; n d，t The number of servers enabled for a data center at time period t on day d.

[0078] The server start-stop margin constraint model is:

[0079]

[0080] in, Representation calculation The average value of a collection.

[0081] The server start and stop times constraint model is:

[0082]

[0083] Wherein, L represents the upper limit of the number of times that server n in the data center is started and stopped within one day T.

[0084] The energy consumption model of the data center system is:

[0085]

[0086] in, represents the energy efficiency of data center; P base Represents the static power of a single server in a data center; P dyn Indicates the peak power of a single server in a data center; represents the energy demand of the data center at time t on day d; Represents the proportion of load that the grid expects data centers to drop when performing power demand response.

[0087] In an exemplary embodiment, the power selling object decision model is based on the power supply information of the power grid and the data center optimization target of each of the power price scheme information, and the power selling object optimization target of each of the power price scheme information is determined, which may include the following steps:

[0088] According to the data center optimization target of each of the electricity price plan information, the load optimization strategy feedback result is obtained; based on the power supply information of the power grid and the load optimization strategy feedback result, the power sales object decision model is used as a constraint condition to solve the power sales object optimization target of each of the electricity price plan information; the power sales object decision model is used to constrain the comprehensive energy system optimization strategy information and the power grid power purchase strategy information of the data center.

[0089] Among them, the optimization objectives of the power sales object may include the power grid purchase cost model, the comprehensive energy system operation cost model, and the demand response benefit model; the power sales object decision model may include the cogeneration unit operation constraint model, the diesel generator operation constraint model, the data center waste heat recovery model, the data center power balance model, and the electricity price incentive signal constraint model.

[0090] In the specific implementation, the optimization target of the electricity sales object can be constructed (such as Figure 3 The optimization target of the power sales company can include the power grid purchase cost model, the comprehensive energy system operation cost model, and the demand response benefit model. The optimization target of the power sales object can be expressed as follows:

[0091]

[0092] in, It represents the electricity purchase cost incurred by the electricity seller when purchasing electricity from the power grid on day d in period t; It represents the operating cost incurred by the electricity seller using the integrated energy system in time period t on day d; C represents the revenue obtained by the data center of the electricity sales object from participating in the demand response in the period t of the day d; ieo It indicates the monthly operating cost of the electricity sales object (i.e. the monthly electricity operation status of the electricity sales object).

[0093] The power grid purchase cost model is:

[0094]

[0095] in, It represents the electricity price of the power grid in time period t, and assumes that the power grid's month-end electricity price catalog does not change; It indicates the power supply provided by the power grid to the data center at time period t on day d.

[0096] The operating cost model of the integrated energy system is:

[0097]

[0098] in, represents the operating cost of using the CHP machine in time period t on day d; represents the operating cost of using a heat pump to recover waste heat from the data center during time period t on day d; represents the operating cost of using the diesel generator on day d during period t; q gas represents the natural gas sales price; represents the amount of natural gas consumed by the CHP unit on day d in period t; represents the electrical power required for heat pump operation during waste heat recovery in period t on day d; It represents the unit fuel cost of diesel generator; It represents the electric power of the diesel generator on day d in time period t.

[0099] The demand response revenue model is:

[0100]

[0101] in, It indicates the demand response incentive given by the power grid to the electricity sellers during the period t on the dth day.

[0102] In one example, a decision model for electricity sales objects can be constructed (e.g. Figure 3 The decision model for power sales companies in China) can be used to constrain the optimization strategy of the comprehensive energy system and the power grid purchase strategy. The decision model for power sales objects can include a cogeneration unit operation constraint model, a diesel generator operation constraint model, a data center waste heat recovery model, a data center power balance model, and an electricity price incentive signal constraint model.

[0103] The operation constraint model of the combined heat and power unit is:

[0104]

[0105] in, represents the electric power output of the CHP machine at time period t on day d; Indicates the status of the CHP generator being turned on at time period t on day d, if turned on, it is 1, otherwise it is 0; P chp,max represents the maximum electric power output of the cogeneration unit in time period t; γ1 represents the energy efficiency coefficient of the cogeneration unit; γ2 represents the calorific value of natural gas; P chp represents the ramp power of the cogeneration unit; γ3 represents the heating coefficient taking into account the heat loss and waste heat recovery efficiency of the cogeneration unit; It represents the heat load output by the CHP generator at time t on day d.

[0106] The diesel generator operation constraint model is:

[0107]

[0108] in, represents the electric power output by the diesel generator at time period t on day d; Indicates the diesel generator is turned on at time period t on day d, 1 if turned on, 0 otherwise; P dg Indicates the diesel generator climbing power.

[0109] The waste heat recovery model of the data center is:

[0110]

[0111] Among them, θ1 is the waste heat loss rate of the data center; θ2 is the efficiency of electricity consumption during the heat pump heating process; θ3 is the heating efficiency of the heat pump; It is the heat load output by the heat pump after waste heat recovery in period t on day d.

[0112] The data center power balance model is:

[0113]

[0114] in, It represents the heat load demand of the data center at time t on day d.

[0115] The electricity price incentive signal constraint model is:

[0116]

[0117] in, It is the maximum profit coefficient that the power sales company can obtain through agency power purchase, which is used to limit the upper limit of profit.

[0118] In an exemplary embodiment, the method of using the preset data center control strategy information to obtain the target electricity price scheme information according to the data center optimization target and the electricity sales object optimization target of each electricity price scheme information may include the following steps:

[0119] The improved beetle whisker search algorithm in the data center control strategy information is adopted to perform iterative processing according to the data center optimization target and the power sales object optimization target of each electricity price plan information until the preset iteration end condition is met to obtain the target electricity price plan information; the data center control strategy information is used to calculate the electricity price pricing strategy information of the data center.

[0120] In an alternative embodiment, if Figure 3 As shown, a data center control strategy (i.e., data center control strategy information) based on the improved beetle whisker search algorithm can be constructed, which can be used to calculate the electricity price pricing strategy of the data center. The improved beetle whisker search algorithm processing can include the following steps:

[0121] 1. Initialize the number of iterations r and the maximum number of iterations R, and set r=1.

[0122] 2. Randomly generate electricity price matrix:

[0123]

[0124] Among them, q r represents the |D|*|T| electricity price matrix generated in the rth iteration, It means that the rth iteration generates the 1*|T| electricity price matrix for the data center on the dth day; Satisfy the electricity price incentive signal constraint model.

[0125] 3. Randomly generate electricity price plan:

[0126]

[0127] Among them, δ r is the search parameter of Tianniu algorithm, d is the normalized |D|*|T| random variable matrix; The electricity price scheme 1 generated for the rth iteration, Electricity price scheme 2 generated for the rth iteration.

[0128] 4. Generate random variable matrix d:

[0129]

[0130] Among them, rands(.) is a random function, and ‖.‖ is the norm of the calculated matrix.

[0131] In an exemplary embodiment, the following steps may also be included:

[0132] According to the data center optimization objective function and the power sales object optimization objective function, a Tianniu optimization function is constructed; based on the randomly generated electricity price plan information of each iteration, the data center optimization objective function and the power sales object optimization objective function are used to perform calculations to obtain the optimization objective function processing results; the Tianniu optimization function is used to calculate the optimization objective function processing results to obtain the electricity price pricing strategy information of each iteration.

[0133] In one example, the process of improving the longicorn beard search algorithm may also include the following steps:

[0134] 5. Generate optimization objective function:

[0135]

[0136] Among them, f1 and f2 are the data center optimization objective function and the power sales object optimization objective function respectively. The data center optimization objective function f1 takes the data center optimization objective as the solution objective and the data center system operation optimization model as the constraint condition for calculation; the power sales object optimization objective function f2 takes the power sales object optimization objective as the solution objective and the power sales object decision model as the constraint condition for calculation. The calculation method can adopt the mixed integer linear programming algorithm.

[0137] 6. Construct the Tianniu optimization function:

[0138]

[0139] 7. and Substitute the two electricity price schemes (i.e., randomly generated electricity price scheme information) into the data center optimization objective function f1, and use the mixed integer linear programming algorithm to calculate and output the C of the data center under different electricity price schemes. DC and load optimization strategies .Will Substitute the optimization objective function f2 of the power sales object into the calculation, use the mixed integer linear programming algorithm to output the C of the power sales object under different electricity price schemes ieo , and integrated energy system optimization strategies , , Power grid purchasing strategy .

[0140] 8. C based on the output of step 7 DC and C ieo (i.e., the processing result of the optimization objective function), the Tianniu optimization function in step 6 is used to calculate f under different electricity price schemes, and the r-th iteration electricity price matrix is ​​updated (i.e., the electricity price pricing strategy information for each iteration).

[0141]

[0142] Among them, sign represents the sign calculation formula, which outputs 1 if it is greater than 1, otherwise it outputs -1.

[0143] 9. Update the search parameters of Tianniu algorithm:

[0144]

[0145] Among them, ω is the update coefficient.

[0146] 10. Determine whether the condition r≤R is met. If so, return to step 3. Otherwise, end and output the pricing strategy for the electricity sales object. The pricing strategy is .

[0147] In an exemplary embodiment, Figure 4 As shown, a flow chart of another data center load control method is provided. In this embodiment, the method includes the following steps:

[0148] In step 401, different electricity price scheme information for the data center is obtained. According to each electricity price scheme information, the data center system operation optimization model is used as a constraint condition to solve the data center optimization target of each electricity price scheme information. In step 402, the load optimization strategy feedback result is obtained according to the data center optimization target of each electricity price scheme information. In step 403, based on the power supply information of the power grid and the feedback result of the load optimization strategy, the power selling object decision model is used as a constraint condition to solve the optimization target of the power selling object of each electricity price scheme information. In step 404, the improved beetle search algorithm in the data center control strategy information is used to iterate according to the data center optimization target and the power selling object optimization target of each electricity price scheme information until the preset iteration end condition is met to obtain the target electricity price scheme information. In step 405, the load optimization result is obtained according to the data center optimization target of the target electricity price scheme information. In step 406, the load optimization result is processed in combination with the power selling object optimization target of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model to obtain the load control information of the data center. It should be noted that the specific limitations of the above steps can be found in the above specific limitations of a data center load control method, which will not be repeated here.

[0149] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0150] Based on the same inventive concept, the embodiment of the present application also provides a data center load control device for implementing the data center load control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more data center load control device embodiments provided below can refer to the limitations of the data center load control method above, and will not be repeated here.

[0151] In an exemplary embodiment, Figure 5 As shown, a data center load control device is provided, comprising:

[0152] The data center optimization target determination module 501 is used to obtain different electricity price scheme information for the data center, and determine the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0153] The power selling object optimization target determination module 502 is used to determine the power selling object optimization target of each power price scheme information based on the power selling object decision model and the data center optimization target of the power grid power supply information and each power price scheme information; the power selling object optimization target is used to characterize the monthly power operation status of the power selling object;

[0154] The target electricity price scheme information obtaining module 503 is used to obtain the target electricity price scheme information according to the data center optimization target and the electricity sales object optimization target of each electricity price scheme information by adopting the preset data center control strategy information;

[0155] A load optimization result obtaining module 504 is used to obtain a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0156] The load control information obtaining module 505 is used to process the load optimization results in combination with the power sales object optimization target of the target electricity price plan information, the data center system operation optimization model, and the power sales object decision model to obtain the load control information of the data center; the load control information includes the comprehensive energy system optimization results and the power grid purchase results.

[0157] In one embodiment, the data center optimization target determination module 501 includes:

[0158] A data center optimization target solving submodule is used to solve the data center optimization target of each electricity price scheme information by taking the data center system operation optimization model as a constraint condition according to each electricity price scheme information; the data center system operation optimization model is used to constrain the load optimization strategy information of the data center;

[0159] Among them, the data center system operation optimization model includes a workload measurement model, a server start and stop quantity constraint model, a server start and stop margin constraint model, a server start and stop number constraint model, and a data center system energy consumption model.

[0160] In one embodiment, the electricity sales object optimization target determination module 502 includes:

[0161] A load optimization strategy feedback result obtaining submodule is used to obtain a load optimization strategy feedback result according to the data center optimization target of each electricity price scheme information;

[0162] The power selling object optimization target solving submodule is used to solve the power selling object optimization target of each of the electricity price scheme information based on the power supply information of the power grid and the feedback result of the load optimization strategy, taking the power selling object decision model as a constraint condition; the power selling object decision model is used to constrain the comprehensive energy system optimization strategy information and the power grid power purchase strategy information of the data center;

[0163] Among them, the optimization objectives of the power sales object include the power grid purchase cost model, the comprehensive energy system operation cost model, and the demand response benefit model; the power sales object decision model includes the cogeneration unit operation constraint model, the diesel generator operation constraint model, the data center waste heat recovery model, the data center power balance model, and the electricity price incentive signal constraint model.

[0164] In one embodiment, the target electricity price scheme information obtaining module 503 includes:

[0165] An iterative calculation submodule is used to adopt the improved beetle whisker search algorithm in the data center control strategy information, and perform iterative processing according to the data center optimization target and the power sales object optimization target of each electricity price plan information until the preset iteration end condition is met to obtain the target electricity price plan information; the data center control strategy information is used to calculate the electricity price pricing strategy information of the data center.

[0166] In one embodiment, the apparatus further comprises:

[0167] The Tianniu optimization function building module is used to build the Tianniu optimization function according to the data center optimization objective function and the electricity sales object optimization objective function;

[0168] An optimization objective function processing module is used to calculate the optimization objective function of the data center and the optimization objective function of the electricity sales object based on the randomly generated electricity price plan information of each iteration, so as to obtain the optimization objective function processing result;

[0169] The module for obtaining the result of each iteration is used to calculate the processing result of the optimization objective function by using the Tianniu optimization function to obtain the electricity price pricing strategy information of each iteration.

[0170] Each module in the above data center load control device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0171] Based on the same inventive concept, the embodiment of the present application also provides a data center load control system for implementing the data center load control method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more data center load control system embodiments provided below can refer to the limitations of the data center load control method above, and will not be repeated here.

[0172] In an exemplary embodiment, a data center load control system is provided, the system comprising a data center, a power sales object, an integrated energy system, and a power grid:

[0173] The electricity selling object is used to generate different electricity price plan information for the data center;

[0174] The data center is used to obtain the information of the different electricity price plans, and determine the data center optimization target of each of the electricity price plan information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0175] The power selling object is used to determine the optimization target of the power selling object of each of the electricity price scheme information based on the power selling object decision model, according to the power grid power supply information provided by the power grid and the data center optimization target of each of the electricity price scheme information; the power selling object optimization target is used to characterize the monthly power operation status of the power selling object;

[0176] The electricity selling object is used to adopt the preset data center control strategy information, and obtain the target electricity price scheme information according to the data center optimization target and the electricity selling object optimization target of each electricity price scheme information;

[0177] The data center is used to obtain a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0178] The power selling object is used to process the load optimization result in combination with the power selling object optimization target of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model to obtain the load control information of the data center; the load control information includes the comprehensive energy system optimization result and the power grid purchase result;

[0179] The electricity selling object is used to output the optimization result of the integrated energy system to the integrated energy system, and output the power grid purchase result to the power grid.

[0180] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for a data center load control system is implemented.

[0181] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0182] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0183] Obtaining different electricity price scheme information for the data center, and determining the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0184] Based on the decision model for the electricity sales object, according to the power supply information of the power grid and the optimization target of the data center of each of the electricity price scheme information, the optimization target of the electricity sales object of each of the electricity price scheme information is determined; the optimization target of the electricity sales object is used to characterize the monthly power operation status of the electricity sales object;

[0185] Using the preset data center control strategy information, according to the data center optimization target and the power sales object optimization target of each of the electricity price plan information, the target electricity price plan information is obtained;

[0186] Obtaining a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0187] In combination with the optimization target of the power selling object of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model, the load optimization result is processed to obtain the load control information of the data center; the load control information includes the optimization result of the comprehensive energy system and the power purchase result of the power grid.

[0188] In one embodiment, when the processor executes the computer program, it also implements the steps of the data center load control method in the other embodiments described above.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0190] Obtaining different electricity price scheme information for the data center, and determining the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0191] Based on the decision model for the electricity sales object, according to the power supply information of the power grid and the optimization target of the data center of each of the electricity price scheme information, the optimization target of the electricity sales object of each of the electricity price scheme information is determined; the optimization target of the electricity sales object is used to characterize the monthly power operation status of the electricity sales object;

[0192] Using the preset data center control strategy information, according to the data center optimization target and the power sales object optimization target of each of the electricity price plan information, the target electricity price plan information is obtained;

[0193] Obtaining a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0194] In combination with the optimization target of the power selling object of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model, the load optimization result is processed to obtain the load control information of the data center; the load control information includes the optimization result of the comprehensive energy system and the power purchase result of the power grid.

[0195] In one embodiment, when the computer program is executed by a processor, the steps of the data center load control method in the other embodiments described above are also implemented.

[0196] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0197] Obtaining different electricity price scheme information for the data center, and determining the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center;

[0198] Based on the decision model for the electricity sales object, according to the power supply information of the power grid and the optimization target of the data center of each of the electricity price scheme information, the optimization target of the electricity sales object of each of the electricity price scheme information is determined; the optimization target of the electricity sales object is used to characterize the monthly power operation status of the electricity sales object;

[0199] Using the preset data center control strategy information, according to the data center optimization target and the power sales object optimization target of each of the electricity price plan information, the target electricity price plan information is obtained;

[0200] Obtaining a load optimization result according to the data center optimization target of the target electricity price scheme information;

[0201] In combination with the optimization target of the power selling object of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model, the load optimization result is processed to obtain the load control information of the data center; the load control information includes the optimization result of the comprehensive energy system and the power purchase result of the power grid.

[0202] In one embodiment, when the computer program is executed by a processor, the steps of the data center load control method in the other embodiments described above are also implemented.

[0203] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0204] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0205] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0206] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A data center load control method, characterized in that: The method comprises: Obtaining different electricity price scheme information for the data center, and determining the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center; Based on the decision model for the electricity sales object, according to the power supply information of the power grid and the optimization target of the data center of each of the electricity price scheme information, the optimization target of the electricity sales object of each of the electricity price scheme information is determined; the optimization target of the electricity sales object is used to characterize the monthly power operation status of the electricity sales object; Using the preset data center control strategy information, according to the data center optimization target and the power sales object optimization target of each of the electricity price plan information, the target electricity price plan information is obtained; Obtaining a load optimization result according to the data center optimization target of the target electricity price scheme information; In combination with the optimization target of the power selling object of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model, the load optimization result is processed to obtain the load control information of the data center; the load control information includes the optimization result of the comprehensive energy system and the power purchase result of the power grid.

2. The method according to claim 1, characterized in that The data center system operation optimization model is based on determining the data center optimization target of each electricity price scheme information, including: According to each of the electricity price scheme information, the data center system operation optimization model is used as a constraint condition to solve the data center optimization target of each of the electricity price scheme information; the data center system operation optimization model is used to constrain the load optimization strategy information of the data center; Among them, the data center system operation optimization model includes a workload measurement model, a server start and stop quantity constraint model, a server start and stop margin constraint model, a server start and stop number constraint model, and a data center system energy consumption model.

3. The method according to claim 1, characterized in that The decision model based on the electricity selling object determines the optimization target of the electricity selling object of each electricity price scheme information according to the power supply information of the power grid and the optimization target of the data center of each electricity price scheme information, including: Obtaining a load optimization strategy feedback result according to the data center optimization target of each of the electricity price scheme information; Based on the power supply information of the power grid and the feedback result of the load optimization strategy, the power sales object decision model is used as a constraint condition to solve the optimization target of the power sales object of each electricity price scheme information; the power sales object decision model is used to constrain the comprehensive energy system optimization strategy information and the power grid purchase strategy information of the data center; Among them, the optimization objectives of the power sales object include the power grid purchase cost model, the comprehensive energy system operation cost model, and the demand response benefit model; the power sales object decision model includes the cogeneration unit operation constraint model, the diesel generator operation constraint model, the data center waste heat recovery model, the data center power balance model, and the electricity price incentive signal constraint model.

4. The method according to claim 1, characterized in that: The preset data center control strategy information is adopted to obtain the target electricity price scheme information according to the data center optimization target and the electricity sales object optimization target of each electricity price scheme information, including: The improved beetle whisker search algorithm in the data center control strategy information is adopted to perform iterative processing according to the data center optimization target and the power sales object optimization target of each electricity price plan information until the preset iteration end condition is met to obtain the target electricity price plan information; the data center control strategy information is used to calculate the electricity price pricing strategy information of the data center.

5. The method according to claim 4, characterized in that The method further comprises: According to the data center optimization objective function and the electricity sales object optimization objective function, the Tianniu optimization function is constructed; Based on the randomly generated electricity price plan information of each iteration, the data center optimization objective function and the electricity sales object optimization objective function are used to perform calculations to obtain the optimization objective function processing result; The Tianniu optimization function is used to calculate the processing result of the optimization objective function to obtain the electricity price pricing strategy information of each iteration.

6. A data center load control device, characterized in that: The device comprises: A data center optimization target determination module is used to obtain different electricity price scheme information for the data center, and determine the data center optimization target of each of the electricity price scheme information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center; The power selling object optimization target determination module is used to determine the power selling object optimization target of each power price scheme information based on the power selling object decision model and the data center optimization target of the power grid power supply information and each power price scheme information; the power selling object optimization target is used to characterize the monthly power operation status of the power selling object; A target electricity price scheme information acquisition module is used to obtain target electricity price scheme information based on the data center optimization target and the electricity sales object optimization target of each electricity price scheme information by using preset data center control strategy information; A load optimization result obtaining module, used to obtain a load optimization result according to the data center optimization target of the target electricity price scheme information; The load control information obtaining module is used to process the load optimization results in combination with the power sales object optimization target of the target electricity price plan information, the data center system operation optimization model, and the power sales object decision model to obtain the load control information of the data center; the load control information includes the comprehensive energy system optimization results and the power grid purchase results.

7. A data center load control system, characterized in that: The system includes data center, electricity sales object, integrated energy system, and power grid: The electricity selling object is used to generate different electricity price plan information for the data center; The data center is used to obtain the information of the different electricity price plans, and determine the data center optimization target of each of the electricity price plan information based on the data center system operation optimization model; the data center optimization target is used to characterize the monthly power operation status of the data center; The power selling object is used to determine the optimization target of the power selling object of each of the power price scheme information based on the power selling object decision model and according to the power grid power supply information provided by the power grid and the data center optimization target of each of the power price scheme information; The optimization target of the electricity sales object is used to characterize the monthly electricity operation status of the electricity sales object; The electricity selling object is used to adopt the preset data center control strategy information, and obtain the target electricity price scheme information according to the data center optimization target and the electricity selling object optimization target of each electricity price scheme information; The data center is used to obtain a load optimization result according to the data center optimization target of the target electricity price scheme information; The power selling object is used to process the load optimization result in combination with the power selling object optimization target of the target electricity price scheme information, the data center system operation optimization model, and the power selling object decision model to obtain the load control information of the data center; the load control information includes the comprehensive energy system optimization result and the power grid purchase result; The electricity selling object is used to output the optimization result of the integrated energy system to the integrated energy system, and output the power grid purchase result to the power grid.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images