Power dispatching control method and device based on data center

Abstract

The embodiment of the invention provides a power dispatching control method and device based on a data center, and the method comprises the steps: obtaining a target parameter of the data center at a first time, and enabling the impact degree of the target parameter on a power demand to be greater than a preset degree threshold value; inputting the target parameter into a pre-established prediction model, and predicting a predicted power demand at a second time; determining a power dispatching strategy at least based on the predicted power demand; and the power system is controlled based on the power dispatching strategy, so that the use efficiency of energy can be improved, and the power cost is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of data centers, and in particular, relates to a control method and device for power dispatching based on data centers. Background Art

[0002] As the core facilities of the information age, the power consumption of data centers has always been the focus of the industry. Traditional power demand side response (DSR) methods mainly rely on predetermined rules and plans to regulate power usage, resulting in high energy consumption and high power costs. Summary of the invention

[0003] In response to the above problems, the embodiments of the present application provide a control method and device for power scheduling based on a data center, which can improve energy efficiency and reduce electricity costs.

[0004] The embodiment of the present application provides a control method for power dispatching based on a data center, including:

[0005] Obtaining a target parameter of the data center at a first time, wherein the target parameter has an impact on power demand that is greater than a preset threshold;

[0006] inputting the input into a pre-established prediction model to predict the predicted power demand at a second time, the second time being after the first time;

[0007] determining a power dispatch strategy based at least on the predicted power demand;

[0008] The power system is controlled based on the power dispatching strategy.

[0009] In some embodiments, determining a power dispatch strategy based at least on the predicted power demand includes:

[0010] Obtain power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization goals;

[0011] Based on power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization goals, a planning algorithm is used to find the optimal solution to obtain a power dispatch strategy.

[0012] In some embodiments, the method further comprises:

[0013] obtaining actual power demand at the second time;

[0014] determining a forecast deviation based on the actual power demand and the forecast power demand;

[0015] The prediction model and the planning algorithm are optimized based on the prediction deviation.

[0016] In some embodiments, the method further comprises:

[0017] Get historical data from the data center;

[0018] Determine a target parameter and a power demand corresponding to the target parameter based on the historical data;

[0019] A prediction model is established based on the target parameters and the power demand corresponding to the target parameters.

[0020] In some embodiments, determining the target parameter and the power demand corresponding to the target parameter based on the historical data includes:

[0021] Performing data cleaning on the historical data to obtain cleaned historical data;

[0022] Performing standardization processing on the cleaned historical data to obtain standardized historical data;

[0023] Target parameters and power demands corresponding to the target parameters are extracted from the standardized historical data.

[0024] In some embodiments, extracting the target parameter and the power demand corresponding to the target parameter from the standardized historical data includes:

[0025] Calculate information gain based on standardized historical data;

[0026] A target parameter and a power demand corresponding to the target parameter are extracted from the historical data based on the information gain.

[0027] In some embodiments, the prediction model includes: a prediction model based on a random forest algorithm, the target parameters include: power usage information, operating status of each device in the data center, environmental information, and the optimization goals include: minimizing costs, maximizing revenue, and minimizing environmental impact.

[0028] The present application provides a control device, including:

[0029] A first acquisition module is used to acquire a target parameter of the data center at a first time, wherein the impact of the target parameter on the power demand is greater than a preset threshold;

[0030] a prediction module, configured to input the input into a pre-established prediction model to predict the power demand at a second time, the second time being after the first time;

[0031] A first determination module, configured to determine a power dispatching strategy based at least on the predicted power demand;

[0032] A control module is used to control the power system based on the power dispatching strategy.

[0033] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described methods when executing the computer program.

[0034] An embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned methods is implemented.

[0035] An embodiment of the present application provides a computer program product. When the computer program product is executed on a terminal device, the electronic device executes any one of the above methods.

[0036] The embodiments of the present application provide a control method and device for power dispatch based on a data center, which obtains target parameters of the data center at a first time, wherein the influence of the target parameters on the power demand is greater than a preset threshold; inputs the obtained parameters into a pre-established prediction model to predict the power demand at a second time; determines a power dispatch strategy based at least on the predicted power demand; and controls the power system based on the power dispatch strategy, thereby improving energy utilization efficiency and reducing power costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Hereinafter, the present application will be described in more detail based on embodiments and with reference to the accompanying drawings.

[0038] Figure 1 A schematic diagram of an implementation flow of a control method for power dispatch based on a data center provided for the implementation of this application;

[0039] Figure 2 A schematic diagram of the structure of a control device provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0041] In the drawings, the same components use the same selection of welding guns, and the drawings are not drawn according to the actual scale. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0043] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0044] If similar descriptions of "first\second\third" appear in the application documents, the following instructions are added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0046] Based on the problems existing in the related art, the embodiment of the present application provides a control method for power dispatch based on a data center. The control method for power dispatch based on a data center provided in the embodiment of the present application can be applied to mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA) and other electronic devices. The embodiment of the present application does not impose any restrictions on the specific type of electronic device. The electronic device can be connected to the data center and the power grid system. The function implemented by the control method for power dispatch based on a data center provided in the embodiment of the present application can be implemented by calling the program code by the processor of the electronic device, wherein the program code can be stored in a computer storage medium.

[0047] The present application provides a control method for power dispatching based on a data center. Figure 1 A schematic diagram of the implementation flow of a control method for power dispatching based on a data center provided for the implementation of this application is shown in FIG. Figure 1 As shown, including:

[0048] Step S101, obtaining a target parameter of a data center at a first time, wherein the impact of the target parameter on power demand is greater than a preset threshold.

[0049] In the embodiment of the present application, the data center generally includes: servers, network equipment, storage equipment, power supply equipment, etc. The first time may be the current time, and the target parameters may include: power usage information, operating status of each device in the data center, and environmental information.

[0050] In the embodiment of the present application, the operating status may include: memory usage, etc., and the environmental information may include: temperature, etc.

[0051] In an embodiment of the present application, a preset degree threshold can be configured, and the correlation or degree of influence between each parameter and power demand can be determined through historical parameters of the data center by statistical methods or machine learning algorithms, and then the correlation or degree of influence is compared with the preset degree threshold to determine the target parameter.

[0052] In the embodiment of the present application, sensors may be installed to obtain the power consumption of the data center, the operating status of each device in the data center, and environmental information through sensors or monitoring systems.

[0053] Step S102: input the target parameter into a pre-established prediction model to predict the power demand at a second time, where the second time is after the first time.

[0054] In the embodiment of the present application, the predicted power demand at the second time is how much power is needed at the second time.

[0055] In the embodiment of the present application, the prediction model can be a neural network model, the input of the prediction model is the target parameter, and the output of the prediction model is the predicted power demand. In the embodiment of the present application, the neural network model shown can be a regression model based on machine learning, an ARIMA model, or a prediction model based on a random forest algorithm.

[0056] In an embodiment of the present application, before inputting the target parameters into the prediction model, the data may be preprocessed, and the preprocessing includes: normalization processing.

[0057] Step S103: determining a power dispatching strategy based at least on the predicted power demand.

[0058] In the embodiments of the present application, the power dispatching strategy may include: power generation dispatching strategy, transmission dispatching strategy, load-side management strategy, etc. The power generation dispatching strategy includes power generation plan, unit output control, unit start-stop strategy, etc., aiming to achieve balance and optimization of power supply. Transmission dispatching strategy: including power grid planning, power grid operation dispatching, power grid fault handling, etc., aiming to ensure the safe and stable operation of the power system. Load-side management strategy: including load forecasting, load control, energy efficiency management, etc., aiming to optimize the power consumption structure and improve energy utilization efficiency.

[0059] In the embodiment of the present application, step S103 can be implemented by the following steps:

[0060] Step S1031, obtaining power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization goals.

[0061] Step S1032, based on power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization goals, a planning algorithm is used to search for the best solution to obtain a power dispatching strategy.

[0062] In the embodiment of the present application, a mathematical model can be established based on the predicted power demand and optimization objectives to transform the power dispatch problem into a planning problem. The objective function may include minimizing costs, maximizing revenue, minimizing environmental impact, etc.

[0063] In the embodiment of the present application, constraints can be established based on power safety restrictions, power supply restrictions and environmental protection requirements. These constraints may include power supply and demand balance, power generation equipment operation restrictions, transmission line capacity restrictions, environmental emission standards, etc. Then, a suitable planning algorithm can be selected, and the defined objective function and constraints can be solved using the selected planning algorithm to obtain the optimal power dispatch strategy.

[0064] In the embodiment of the present application, the planning algorithm may be a linear planning algorithm, and the preset conditions of the linear planning algorithm include: power safety of data center equipment, power supply restrictions, cost and revenue optimization goals, environmental protection requirements, etc. The formula of the linear planning algorithm includes:

[0065] Maximize c T x

[0066] subject to Ax≤b;

[0067] Where x is the decision variable, c is the coefficient vector, and A and b define the constraints.

[0068] Based on the prediction results and constraints, an optimization strategy for electricity use is formulated to minimize costs, maximize demand-side response benefits, and minimize environmental impacts.

[0069] Step S104: controlling the power system based on the power dispatching strategy.

[0070] In an embodiment of the present application, specific operation instructions can be generated according to the optimized power dispatching strategy, including generator output adjustment, switching operation of transmission lines, charge and discharge control of energy storage equipment, etc. These instructions need to take into account the real-time operating status of the system and the dispatchability of the equipment. The generated dispatching instructions are sent to the corresponding power system equipment, and the instructions can be sent through an automated control system or manually by a dispatcher. Once the power system receives the operation instruction, the power system equipment will make corresponding adjustments, such as changes in generator output, line switching, etc. At the same time, it is necessary to monitor the operating status of the system in real time to ensure that the execution of the operation instructions meets expectations.

[0071] An embodiment of the present application provides a control method for power dispatch based on a data center, which obtains target parameters of the data center at a first time, wherein the influence of the target parameters on the power demand is greater than a preset threshold; inputs the obtained parameters into a pre-established prediction model to predict the power demand at a second time; determines a power dispatch strategy based at least on the predicted power demand; and controls the power system based on the power dispatch strategy, thereby improving energy utilization efficiency and reducing power costs.

[0072] In some embodiments, after step S104, the method further includes:

[0073] Step S105, obtaining the actual power demand at the second time.

[0074] In the embodiment of the present application, the actual power demand can be obtained through real-time monitoring data of the power system, which can be provided by the SCADA system or smart meters of the power system. These devices can monitor the power consumption of the data center in real time and record the actual power demand data.

[0075] Step S106: determining a prediction deviation based on the actual power demand and the predicted power demand.

[0076] In the embodiment of the present application, the prediction deviation can be determined by comparing the actual power demand with the predicted power demand. The difference between the actual power demand and the predicted power demand can be calculated to evaluate the accuracy and deviation of the prediction.

[0077] Step S107: optimizing the prediction model and the planning algorithm based on the prediction deviation.

[0078] In the embodiment of the present application, the prediction deviation is determined, and the prediction model and planning algorithm can be optimized according to the deviation. For the prediction model, it is possible to consider introducing more characteristic variables, improving the training algorithm of the model, adjusting the hyperparameters of the model, etc. to improve the accuracy of the prediction. For the planning algorithm, it is possible to consider introducing a deviation correction factor, adjusting the optimization objective function or constraint conditions, etc. to optimize the power dispatch strategy.

[0079] In some embodiments, before step S101, the method further includes:

[0080] Step S1, obtaining historical data of the data center.

[0081] In the embodiment of the present application, the historical data includes: historical power usage information, historical operating status of each device in the data center, and historical environmental information.

[0082] Step S2: determining a target parameter and a power demand corresponding to the target parameter based on the historical data.

[0083] In the embodiment of the present application, step S2 can be implemented by the following steps:

[0084] Step S21, performing data cleaning on the historical data to obtain cleaned historical data.

[0085] In the embodiment of the present application, data cleaning may include: removing outliers, missing data and noise to ensure the accuracy and consistency of the data.

[0086] In some embodiments, the historical data may also be processed to delete missing values, repair erroneous values, or fill in missing values ​​using an interpolation method.

[0087] Step S22, standardize the cleaned historical data to obtain standardized historical data.

[0088] In the present application, the data is normalized to ensure that the numerical ranges of different features are similar. Common normalization methods include minimum-maximum normalization and Z-score normalization. This can ensure that the impact of different features on modeling is similar.

[0089] In the embodiment of the present application, the normalized formula includes:

[0090]

[0091] Where x is the original data, x norm is the normalized data.

[0092] Step S23, extracting target parameters and power demand corresponding to the target parameters from the standardized historical data.

[0093] In the embodiment of the present application, statistical methods or machine learning algorithms can be used to analyze the standardized historical data to determine the relationship between the target parameter and the power demand. Correlation analysis, regression analysis or other data analysis methods can be used to find out the degree of influence of the target parameter on the power demand, and based on the results of the data analysis, the target parameters that have the greatest impact on the power demand are determined, and these parameters and their corresponding power demand data are extracted.

[0094] In the embodiment of the present application, step S23 can be implemented by the following steps:

[0095] Step S231, calculating information gain based on the standardized historical data.

[0096] In the embodiment of the present application, the information gain of each feature for the power demand is calculated. Information gain is usually related to entropy, which measures the degree to which the uncertainty of the power demand is reduced when the feature is given. Information gain in the decision tree algorithm or the feature selection method based on entropy can be used to calculate information gain.

[0097] In the embodiment of the present application, the calculation formula of information gain may include:

[0098] Information gain formula:

[0099] IG(D,F)=H(D)-H(D|F);

[0100] Used to measure the importance of features. IG is the information gain, H(D) is the entropy of the dataset D, and H(D|F) is the conditional entropy of D given feature F.

[0101] Step S232: extracting target parameters and power demand corresponding to the target parameters from historical data based on the information gain.

[0102] In the embodiment of the present application, according to the calculation result of information gain, features with information gain greater than the information gain threshold are selected as target parameters. These features will be used to predict power demand.

[0103] In the embodiment of the present application, the selected target parameters and their corresponding power demand data are extracted from the historical data based on the result of feature selection.

[0104] Step S3, establishing a prediction model based on the target parameter and the power demand corresponding to the target parameter.

[0105] In an embodiment of the present application, the prediction model may be a prediction model established based on a random forest algorithm.

[0106] In the embodiment of the present application, the random forest algorithm formula can be expressed as:

[0107]

[0108] Where N is the number of trees, y i is the prediction result of the i-th tree.

[0109] In the embodiment of the present application, step S3 can be implemented in the following manner:

[0110] The extracted target parameters and their corresponding power demands are preprocessed by data cleaning, normalization, etc. to facilitate subsequent modeling and analysis. Based on the target parameters and their corresponding power demands, feature vectors are constructed, including historical features, time series features, statistical features, and frequency domain features.

[0111] In the embodiment of the present application, a sample data set can be established based on the target parameter and the power demand corresponding to the target parameter, and then the data set can be divided into a training set and a validation set. The model is trained by the training set, and the trained model is evaluated using the validation set, including indicators such as mean square error and mean absolute error. If the performance of the model is not good enough, the model parameters can be adjusted or the model can be replaced.

[0112] Based on the foregoing embodiments, an embodiment of the present application provides a control method for power scheduling based on a data center, which is applied to a control system, wherein the control system includes: a data center power monitoring module, a demand side response (DSR) mechanism module, and an artificial intelligence (AI) scheduling module.

[0113] In the embodiment of the present application, the monitoring module is responsible for real-time monitoring of the power usage of the data center, which includes not only the total amount of power consumption, but also the operating status and efficiency of each device. Through high-precision sensors and advanced monitoring equipment, power usage data can be collected and transmitted in real time to ensure the real-time and accuracy of information, thereby providing accurate data support for demand-side response.

[0114] Demand-side response mechanism module: The demand-side response mechanism module focuses on the macro level and analyzes the demand of the entire power grid and the dynamic changes of the power market. By dynamically adjusting the power usage pattern in the data center, responding to external power grid demand and power market changes, efficient energy configuration is achieved.

[0115] Artificial intelligence dispatching module: The artificial intelligence dispatching module is the intelligent core of the system. It uses advanced machine learning algorithms to train high-precision models based on a large amount of historical data. It can not only accurately predict the future trend of electricity demand, but also the AI ​​dispatching algorithm can formulate the optimal power dispatching strategy based on these prediction results to achieve efficiency improvement, cost reduction and increase revenue.

[0116] The monitoring module continuously collects the power usage data of the data center, including but not limited to power consumption, operating status of each device, ambient temperature, etc.

[0117] In the embodiment of the present application, sensors and monitoring equipment are installed in key locations of the data center to comprehensively collect data such as power usage, equipment operating status, and ambient temperature and humidity.

[0118] The AI ​​scheduling module conducts in-depth analysis of the collected data, using advanced data processing technology to predict future power demand and identify potential energy-saving points. Advanced data analysis technologies such as deep learning are used to analyze factors such as power consumption patterns, equipment efficiency, and environmental impact. Based on historical data and real-time data, future power demand trends are predicted and energy-saving optimization points are identified. According to the overall demand of the power grid and market conditions, targeted power scheduling strategies are formulated to ensure the normal operation of the data center and optimize power usage efficiency.

[0119] The system automatically adjusts the power distribution and usage within the data center according to the established strategy to achieve the goal of optimizing efficiency. The automation system adjusts the power distribution within the data center according to the strategy to optimize resource allocation.

[0120] In the embodiment of the present application, it is necessary to monitor the effect of scheduling execution and make real-time adjustments according to actual conditions to improve power utilization efficiency and overall operational efficiency.

[0121] The control method based on power dispatching of the data center provided in the embodiment of the present application can improve the energy efficiency of the data center and reduce waste through intelligent dispatching. By optimizing power usage, especially increasing the load during periods with lower electricity prices, the operating costs of the data center can be significantly reduced. By reducing energy usage during peak demand, it helps to ease the load on the power grid and improve the overall stability of the power grid.

[0122] Helps reduce carbon emissions and promote environmental sustainability through more efficient electricity usage.

[0123] Based on the foregoing embodiments, an embodiment of the present application provides a control device, and the modules included in the device, as well as the units included in each module, can be implemented by a processor in a computer device; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Microprocessor Unit), a digital signal processor (DSP, Digital Signal Processing) or a field programmable gate array (FPGA, Field Programmable Gate Array), etc.

[0124] The present application embodiment provides a control device, Figure 2A schematic diagram of the structure of a control device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the control device 200 includes:

[0125] A first acquisition module 201 is used to acquire a target parameter of a data center at a first time, wherein the impact of the target parameter on power demand is greater than a preset threshold;

[0126] A prediction module 202, configured to input the target parameter into a pre-established prediction model to predict the power demand at a second time, the second time being after the first time;

[0127] A first determination module 203, configured to determine a power dispatching strategy based at least on the predicted power demand;

[0128] The control module 204 is used to control the power system based on the power dispatching strategy.

[0129] In some embodiments, the first determining module includes:

[0130] An acquisition unit, used to acquire power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization targets;

[0131] The optimization unit is used to optimize the power dispatching strategy by using a planning algorithm based on power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization goals.

[0132] In some embodiments, the control device further comprises:

[0133] A second acquisition module, used to acquire the actual power demand at the second time;

[0134] A second determination module, configured to determine a prediction deviation based on the actual power demand and the predicted power demand;

[0135] An optimization module is used to optimize the prediction model and the planning algorithm based on the prediction deviation.

[0136] In some embodiments, the control device further comprises:

[0137] The third acquisition module is used to acquire historical data of the data center;

[0138] A third determination module, configured to determine a target parameter and a power demand corresponding to the target parameter based on the historical data;

[0139] A module is established for establishing a prediction model based on target parameters and power demand corresponding to the target parameters.

[0140] In some embodiments, the third determination module includes:

[0141] A cleaning unit, used for cleaning the historical data to obtain cleaned historical data;

[0142] A standardization processing unit, used for performing standardization processing on the cleaned historical data to obtain standardized historical data;

[0143] The extraction unit is used to extract the target parameter and the power demand corresponding to the target parameter from the standardized historical data.

[0144] In some embodiments, the extraction unit comprises:

[0145] A calculation subunit, used for calculating information gain based on the standardized historical data;

[0146] The extraction subunit is used to extract the target parameter and the power demand corresponding to the target parameter from the historical data based on the information gain.

[0147] In some embodiments, the prediction model includes: a prediction model based on a random forest algorithm, the target parameters include: power usage information, operating status of each device in the data center, environmental information, and the optimization goals include: minimizing costs, maximizing revenue, and minimizing environmental impact.

[0148] An embodiment of the present application provides an electronic device, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the electronic device 600 includes: a processor 601, at least one communication bus 602, a user interface 603, at least one external communication interface 604, and a memory 605. The communication bus 602 is configured to realize connection and communication between these components. The user interface 603 may include a display screen, and the external communication interface 604 may include a standard wired interface and a wireless interface. The processor 601 is configured to execute a program of a control method for power dispatch based on a data center stored in the memory to implement the steps in the control method for power dispatch based on a data center provided in the above embodiment.

[0149] In the embodiment of the present application, if the above-mentioned control method for power dispatching based on the data center is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read Only Memory), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0150] Accordingly, an embodiment of the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the control method for power scheduling based on a data center provided in the above embodiment are implemented.

[0151] An embodiment of the present application further provides a computer program product. When the computer program product is executed on a terminal device, the electronic device executes any of the above-mentioned control methods for power scheduling based on a data center.

[0152] The description of the above electronic device and storage medium embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the computer device and storage medium embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0153] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0154] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0155] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0156] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0157] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0158] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read Only Memory), disks or optical disks, etc. Various media that can store program codes.

[0159] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a controller to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0160] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A control method for power dispatching based on a data center, characterized in that: include: Obtaining a target parameter of the data center at a first time, wherein the target parameter has an impact on power demand that is greater than a preset threshold; Inputting the target parameter into a pre-established prediction model to predict the power demand at a second time, the second time being after the first time; determining a power dispatch strategy based at least on the predicted power demand; The power system is controlled based on the power dispatching strategy.

2. The method according to claim 1, characterized in that The determining of a power dispatch strategy based at least on the predicted power demand comprises: Obtain power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization goals; Based on power safety restrictions, power supply restrictions, environmental protection requirements, predicted power demand and optimization goals, a planning algorithm is used to find the optimal solution to obtain a power dispatch strategy.

3. The method according to claim 2, characterized in that The method further comprises: obtaining actual power demand at the second time; determining a forecast deviation based on the actual power demand and the forecast power demand; The prediction model and the planning algorithm are optimized based on the prediction deviation.

4. The method according to claim 2, characterized in that: The method further comprises: Get historical data from the data center; Determine a target parameter and a power demand corresponding to the target parameter based on the historical data; A prediction model is established based on the target parameters and the power demand corresponding to the target parameters.

5. The method according to claim 4, characterized in that The determining the target parameter and the power demand corresponding to the target parameter based on the historical data includes: Performing data cleaning on the historical data to obtain cleaned historical data; Performing standardization processing on the cleaned historical data to obtain standardized historical data; Target parameters and power demands corresponding to the target parameters are extracted from the standardized historical data.

6. The method according to claim 5, characterized in that The step of extracting the target parameter and the power demand corresponding to the target parameter from the standardized historical data includes: Calculate information gain based on standardized historical data; A target parameter and a power demand corresponding to the target parameter are extracted from the historical data based on the information gain.

7. The method according to claim 6, characterized in that The prediction model includes: a prediction model based on a random forest algorithm, the target parameters include: power usage information, the operating status of each device in the data center, and environmental information, and the optimization goals include: minimizing costs, maximizing revenue, and minimizing environmental impact.

8. A control device, characterized in that: include: A first acquisition module is used to acquire a target parameter of the data center at a first time, wherein the impact of the target parameter on the power demand is greater than a preset threshold; a prediction module, configured to input the target parameter into a pre-established prediction model to predict the power demand at a second time, the second time being after the first time; A first determining module, configured to determine a power dispatching strategy based at least on the predicted power demand; A control module is used to control the power system based on the power dispatching strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the control method for power dispatching based on a data center as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a control method for power dispatching based on a data center as claimed in any one of claims 1 to 7 is implemented.

Images